<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Customer Success Story Archives - Sensr</title>
	<atom:link href="https://www.sensr.ai/category/customer-succes-story/feed/" rel="self" type="application/rss+xml" />
	<link>https://www.sensr.ai/category/customer-succes-story/</link>
	<description>Advanced Analytics on Industrial Data. Turning unplannable into achievable.</description>
	<lastBuildDate>Fri, 24 Apr 2026 12:17:03 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	
	<item>
		<title>From Road to Data: How Stad Roeselare Automated Traffic Sign Inventory with Computer Vision</title>
		<link>https://www.sensr.ai/2026/04/17/from-road-to-data-how-stad-roeselare-automated-traffic-sign-inventory-with-computer-vision/</link>
					<comments>https://www.sensr.ai/2026/04/17/from-road-to-data-how-stad-roeselare-automated-traffic-sign-inventory-with-computer-vision/#respond</comments>
		
		<dc:creator><![CDATA[Imke Heusschen]]></dc:creator>
		<pubDate>Fri, 17 Apr 2026 06:44:49 +0000</pubDate>
				<category><![CDATA[Customer Success Story]]></category>
		<guid isPermaLink="false">https://www.sensr.ai/?p=1277</guid>

					<description><![CDATA[<p>From Road to Data: How Stad Roeselare Automated Traffic Sign Inventory with Computer Vision  How a Belgian municipality transformed mobile sensor captures into a living traffic sign database.      Introduction: The Municipal Data Challenge  Traffic signs are among the most ubiquitous and overlooked assets in any city's infrastructure  [...]</p>
<p>The post <a href="https://www.sensr.ai/2026/04/17/from-road-to-data-how-stad-roeselare-automated-traffic-sign-inventory-with-computer-vision/">From Road to Data: How Stad Roeselare Automated Traffic Sign Inventory with Computer Vision</a> appeared first on <a href="https://www.sensr.ai">Sensr</a>.</p>
]]></description>
										<content:encoded><![CDATA[<div class="fusion-fullwidth fullwidth-box fusion-builder-row-1 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-padding-bottom:7rem;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-0 fusion_builder_column_1_2 1_2 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:50%;--awb-margin-top-large:0px;--awb-spacing-right-large:3.84%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:3.84%;--awb-width-medium:50%;--awb-order-medium:0;--awb-spacing-right-medium:3.84%;--awb-spacing-left-medium:3.84%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-title title fusion-title-1 fusion-sep-none fusion-title-text fusion-title-size-two" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h2 class="fusion-title-heading title-heading-left" style="margin:0;">From Road to Data: How Stad Roeselare Automated Traffic Sign Inventory with Computer Vision</h2></div><div class="fusion-title title fusion-title-2 fusion-sep-none fusion-title-text fusion-title-size-six" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;--awb-font-size:1.75rem;"><h6 class="fusion-title-heading title-heading-left" style="margin:0;font-size:1em;"><p data-local-id="7d15196ce7a3" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em data-prosemirror-content-type="mark" data-prosemirror-mark-name="em"><span id="7554a9cb-689b-4e89-8cc8-b0f45e4777dd" data-mark-type="annotation" data-mark-annotation-type="inlineComment" data-id="7554a9cb-689b-4e89-8cc8-b0f45e4777dd" data-prosemirror-content-type="mark" data-prosemirror-mark-name="annotation">How a Belgian municipality transformed mobile sensor captures into a living traffic sign database.</span></em></p></h6></div></div></div><div class="fusion-layout-column fusion_builder_column fusion-builder-column-1 fusion_builder_column_1_2 1_2 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:50%;--awb-margin-top-large:0px;--awb-spacing-right-large:3.84%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:3.84%;--awb-width-medium:50%;--awb-order-medium:0;--awb-spacing-right-medium:3.84%;--awb-spacing-left-medium:3.84%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-image-element" style="text-align:right;--awb-margin-right:2rem;--awb-max-width:70%;--awb-caption-title-font-family:var(--h2_typography-font-family);--awb-caption-title-font-weight:var(--h2_typography-font-weight);--awb-caption-title-font-style:var(--h2_typography-font-style);--awb-caption-title-size:var(--h2_typography-font-size);--awb-caption-title-transform:var(--h2_typography-text-transform);--awb-caption-title-line-height:var(--h2_typography-line-height);--awb-caption-title-letter-spacing:var(--h2_typography-letter-spacing);"><span class=" fusion-imageframe imageframe-none imageframe-1 hover-type-none"><img fetchpriority="high" decoding="async" width="967" height="923" title="stad_roeselare_logo_kleur_rgb" src="https://www.sensr.ai/wp-content/uploads/2026/04/stad_roeselare_logo_kleur_rgb.png" alt class="img-responsive wp-image-1306" srcset="https://www.sensr.ai/wp-content/uploads/2026/04/stad_roeselare_logo_kleur_rgb-200x191.png 200w, https://www.sensr.ai/wp-content/uploads/2026/04/stad_roeselare_logo_kleur_rgb-400x382.png 400w, https://www.sensr.ai/wp-content/uploads/2026/04/stad_roeselare_logo_kleur_rgb-600x573.png 600w, https://www.sensr.ai/wp-content/uploads/2026/04/stad_roeselare_logo_kleur_rgb-800x764.png 800w, https://www.sensr.ai/wp-content/uploads/2026/04/stad_roeselare_logo_kleur_rgb.png 967w" sizes="(max-width: 640px) 100vw, 600px" /></span></div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-2 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-2 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-title title fusion-title-3 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="9b980218cf3f" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">Introduction: The Municipal Data Challenge</p></h4></div><div class="fusion-text fusion-text-1"><p data-local-id="3bc3e228ca22" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><span id="28d5c51a-86e2-4143-856f-c4aed7f18e82" data-mark-type="annotation" data-mark-annotation-type="inlineComment" data-id="28d5c51a-86e2-4143-856f-c4aed7f18e82" data-prosemirror-content-type="mark" data-prosemirror-mark-name="annotation">Traffic signs are among the most ubiquitous and overlooked assets in any city&#8217;s infrastructure portfolio</span>. Speed limits, parking restrictions, priority rules, pedestrian zones: thousands of signs govern daily traffic flow, each carrying legal weight and maintenance responsibilities. Yet across Europe, municipal traffic sign databases remain surprisingly fragmented, outdated and incomplete.</p>
<p data-local-id="8fdbdc6c02fb" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">The consequences of inaccurate inventories extend beyond administrative inconvenience. When a sign is missing from the database, maintenance schedules skip it. When records show a sign that no longer exists, crews waste time searching for phantom infrastructure. When citizen complaints arrive about unclear or damaged signage, response times stretch while staff manually verify what&#8217;s actually installed.</p>
<p data-local-id="11e20700f4da" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">Stad Roeselare recognized an opportunity to break this cycle. Rather than treating traffic sign inventory as a periodic project, they envisioned it as a continuous process, one that could leverage mobile sensing technology already deployed across their fleet or fleet of partners servicing the city.</p>
</div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-3 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-3 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:2rem;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;" data-scroll-devices="small-visibility,medium-visibility,large-visibility"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-image-element" style="text-align:center;--awb-caption-title-font-family:var(--h2_typography-font-family);--awb-caption-title-font-weight:var(--h2_typography-font-weight);--awb-caption-title-font-style:var(--h2_typography-font-style);--awb-caption-title-size:var(--h2_typography-font-size);--awb-caption-title-transform:var(--h2_typography-text-transform);--awb-caption-title-line-height:var(--h2_typography-line-height);--awb-caption-title-letter-spacing:var(--h2_typography-letter-spacing);"><span class=" fusion-imageframe imageframe-none imageframe-2 hover-type-none"><img decoding="async" width="2560" height="1829" alt="Traffic Signs" title="traffic-signs" src="https://www.sensr.ai/wp-content/uploads/2026/04/traffic-signs-scaled.png" class="img-responsive wp-image-1283" srcset="https://www.sensr.ai/wp-content/uploads/2026/04/traffic-signs-200x143.png 200w, https://www.sensr.ai/wp-content/uploads/2026/04/traffic-signs-400x286.png 400w, https://www.sensr.ai/wp-content/uploads/2026/04/traffic-signs-600x429.png 600w, https://www.sensr.ai/wp-content/uploads/2026/04/traffic-signs-800x572.png 800w, https://www.sensr.ai/wp-content/uploads/2026/04/traffic-signs-1200x857.png 1200w, https://www.sensr.ai/wp-content/uploads/2026/04/traffic-signs-scaled.png 2560w" sizes="(max-width: 640px) 100vw, 1200px" /></span></div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-4 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-4 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-title title fusion-title-4 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="36ff06c9f9db" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The Challenge: From Mobile Capture to Actionable Insights</p></h4></div><div class="fusion-text fusion-text-2"><p data-local-id="3bc3e228ca22" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><span id="28d5c51a-86e2-4143-856f-c4aed7f18e82" data-mark-type="annotation" data-mark-annotation-type="inlineComment" data-id="28d5c51a-86e2-4143-856f-c4aed7f18e82" data-prosemirror-content-type="mark" data-prosemirror-mark-name="annotation">Traffic signs are among the most ubiquitous and overlooked assets in any city&#8217;s infrastructure portfolio</span>. Speed limits, parking restrictions, priority rules, pedestrian zones: thousands of signs govern daily traffic flow, each carrying legal weight and maintenance responsibilities. Yet across Europe, municipal traffic sign databases remain surprisingly fragmented, outdated and incomplete.</p>
<p data-local-id="8fdbdc6c02fb" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">The consequences of inaccurate inventories extend beyond administrative inconvenience. When a sign is missing from the database, maintenance schedules skip it. When records show a sign that no longer exists, crews waste time searching for phantom infrastructure. When citizen complaints arrive about unclear or damaged signage, response times stretch while staff manually verify what&#8217;s actually installed.</p>
<p data-local-id="11e20700f4da" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">Stad Roeselare recognized an opportunity to break this cycle. Rather than treating traffic sign inventory as a periodic project, they envisioned it as a continuous process, one that could leverage mobile sensing technology already deployed across their fleet or fleet of partners servicing the city.</p>
</div><div class="fusion-title title fusion-title-5 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="37f1922b65b2" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em>Real-World Technical Obstacles</em></p></h5></div><div class="fusion-text fusion-text-3"><p data-local-id="3050ffe91627" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The transition from concept to deployment revealed challenges familiar to anyone working with computer vision in uncontrolled environments:</p>
<ul class="ak-ul" data-local-id="9ee00249-8b01-4a93-b07e-02fd0bcd2249" data-prosemirror-content-type="node" data-prosemirror-node-name="bulletList" data-prosemirror-node-block="true">
<li data-local-id="734e02b4-bd92-479c-9116-762b2824fa42" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="2a95e6c399bf" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Variable lighting conditions</strong>: Morning glare, afternoon shadows, overcast days, … or typical Belgian weather in a nutshell.</p>
</li>
<li data-local-id="bfbff163-72af-41a6-a0c4-e11af209a199" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="62897bc4ca0f" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Oblique camera angles</strong>: Signs photographed from passing vehicles at unpredictable angles</p>
</li>
<li data-local-id="576bb540-1da6-4263-aaf0-f99f0585f3da" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="e61f2e59a131" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Partial occlusions</strong>: Parked cars, overgrown vegetation, construction barriers</p>
</li>
<li data-local-id="52779882-7022-44a1-9ceb-5d6cdd6c63c4" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="a1eb0eaa1dfa" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Sign degradation</strong>: Weathering, vandalism, stickers and fading</p>
</li>
<li data-local-id="22eaf8ee-0fd2-42da-b8e9-b073cbe6841f" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="a4aa3eff4aff" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Diverse sign taxonomy</strong>: Belgian traffic signs span multiple categories (Warning, Priority, Prohibition, Mandatory, Parking, Additional) with dozens of subtypes</p>
</li>
</ul>
<p data-local-id="c85195354d24" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">These challenges aren&#8217;t unique to Roeselare. As research from the ViCoS Lab [<span class="inlineCardView-content-wrap inlineNodeView" data-prosemirror-content-type="node" data-prosemirror-node-name="inlineCard" data-prosemirror-node-inline="true"><span class="card" aria-busy="true"><a href="https://www.vicos.si/research/traffic-sign-detection/" target="_blank" rel="noopener" data-inline-card="" data-card-data="" data-local-id="14627097fb6a">Traffic-sign detection</a></span></span>] highlights, automating traffic sign inventory management requires deep learning models that can handle the gap between idealized training data and messy real-world captures.</p>
</div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-5 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-5 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-image-element" style="--awb-caption-title-font-family:var(--h2_typography-font-family);--awb-caption-title-font-weight:var(--h2_typography-font-weight);--awb-caption-title-font-style:var(--h2_typography-font-style);--awb-caption-title-size:var(--h2_typography-font-size);--awb-caption-title-transform:var(--h2_typography-text-transform);--awb-caption-title-line-height:var(--h2_typography-line-height);--awb-caption-title-letter-spacing:var(--h2_typography-letter-spacing);"><span class=" fusion-imageframe imageframe-none imageframe-3 hover-type-none"><img decoding="async" width="1576" height="1438" alt="Unreadable Traffic Signs" title="TrafficSigns" src="https://www.sensr.ai/wp-content/uploads/2026/04/TrafficSigns.png" class="img-responsive wp-image-1299" srcset="https://www.sensr.ai/wp-content/uploads/2026/04/TrafficSigns-200x182.png 200w, https://www.sensr.ai/wp-content/uploads/2026/04/TrafficSigns-400x365.png 400w, https://www.sensr.ai/wp-content/uploads/2026/04/TrafficSigns-600x547.png 600w, https://www.sensr.ai/wp-content/uploads/2026/04/TrafficSigns-800x730.png 800w, https://www.sensr.ai/wp-content/uploads/2026/04/TrafficSigns-1200x1095.png 1200w, https://www.sensr.ai/wp-content/uploads/2026/04/TrafficSigns.png 1576w" sizes="(max-width: 640px) 100vw, 1200px" /></span></div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-6 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-6 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-title title fusion-title-6 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="8ce338b34a9b" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The Solution: Custom AI on the Mobile Sensor Unit</p></h4></div><div class="fusion-text fusion-text-4"><p data-local-id="db0f0cb1d6d7" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">Working with Stad Roeselare, the Sensr team developed a two-stage AI pipeline: detection on the edge, classification in the cloud.</p>
</div><div class="fusion-title title fusion-title-7 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="cf634816f7be" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em>Stage 1: Detection on the MSU</em></p></h5></div><div class="fusion-text fusion-text-5"><p data-local-id="a711ee542b32" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The team selected <strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">YOLOv11n</strong> as the base detection model, balancing speed and accuracy for real-time detection during MSU operations. This choice reflects broader industry trends. Research shows YOLO variants consistently outperform other architectures for traffic sign detection, achieving mAP50 scores exceeding 90% in controlled settings [<span class="inlineCardView-content-wrap inlineNodeView" data-prosemirror-content-type="node" data-prosemirror-node-name="inlineCard" data-prosemirror-node-inline="true"><span class="card" aria-busy="true"><a href="https://www.mdpi.com/2227-7390/12/2/297" target="_blank" rel="noopener" data-inline-card="" data-card-data="" data-local-id="dcb3dd5b2828">Traffic Sign Detection and Recognition Using YOLO Object Detection Algorithm: A Systematic Review</a></span></span>].</p>
</div><div class="fusion-title title fusion-title-8 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="6233fcf40faa" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em>Stage 2: Hierarchical Classification Architecture</em></p></h5></div><div class="fusion-text fusion-text-6"><p data-local-id="8e868219da30" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">Rather than training a single monolithic classifier, the solution employs a <strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">hierarchical classification approach</strong> with specialized sub-models for categories A (Warning), B (Priority), C (Prohibition), D (Mandatory), E (Parking), and M (Additional).</p>
<p data-local-id="6fa7599ca456" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">How it works:</strong></p>
<ol class="ak-ol" start="1" data-local-id="a4b4a226-965e-4912-af6a-cf69c67aafdc" data-prosemirror-content-type="node" data-prosemirror-node-name="orderedList" data-prosemirror-node-block="true">
<li data-local-id="95c32b94-ad2a-49e4-9ccd-5b78680cadd8" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="5098fd4407fc" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">The high-level classifier determines the main category (e.g., &#8220;This is a prohibition sign&#8221;)</p>
</li>
<li data-local-id="4371f182-a266-4ea7-b657-5bc06726081e" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="b156643bd7ad" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">A specialized sub-model for that category identifies the specific type (e.g., &#8220;B1: Priority from the right&#8221;)</p>
</li>
<li data-local-id="79f50f0a-0bf6-4fed-ad79-597d2637a335" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="500a6a12b55e" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">For edge cases like M3bis/M11 signs, a dedicated ensemble model combining optical character recognition (OCR) with pixel analysis provides fine-grained classification</p>
</li>
</ol>
<p data-local-id="145f901b9f67" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">This architecture offers several advantages:</strong></p>
<ul class="ak-ul" data-local-id="5f3e39f9-e533-4d2d-9dc9-0989df2b6380" data-prosemirror-content-type="node" data-prosemirror-node-name="bulletList" data-prosemirror-node-block="true">
<li data-local-id="9efa7423-1ec8-43c7-a520-f38740061f21" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="27be09ec358c" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Specialization</strong>: Each sub-model focuses on distinguishing signs within a single category, improving accuracy</p>
</li>
<li data-local-id="faea4f19-df57-4b82-b903-dc70275dd1e0" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="f4c699b1a032" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Robustness</strong>: If the high-level classifier is uncertain, the system can flag the detection for human review rather than forcing a potentially wrong classification</p>
</li>
<li data-local-id="dadc6c3d-5118-4643-8b75-321cb793afb5" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="76d93c4116b3" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Extensibility</strong>: New sign types can be added by training additional sub-models without retraining the entire system</p>
</li>
</ul>
<p data-local-id="684e2e29c329" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">Classification accuracy across the hierarchy ranged from <strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">85.7% to 99.7%</strong> depending on the category, with the most common sign types achieving the highest performance.</p>
</div><div class="fusion-title title fusion-title-9 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="77afd1c76742" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em>Cloud-Native Inference Infrastructure</em></p></h5></div><div class="fusion-text fusion-text-7"><p data-local-id="f54346a5cac0" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The classification pipeline runs on Microsoft Azure with a serverless architecture designed for cost efficiency:</p>
<ul class="ak-ul" data-local-id="8523785d-d250-49f3-b033-d975e1d83ae6" data-prosemirror-content-type="node" data-prosemirror-node-name="bulletList" data-prosemirror-node-block="true">
<li data-local-id="aa4e0915-e029-4adc-83ae-8c660553a6c2" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="1f2926eb03e4" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">FastAPI</strong>: Handles inference requests with low-latency response times</p>
</li>
<li data-local-id="80f93565-8a00-436f-9bd0-b702a43eba64" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="cbd6d19028c1" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Azure Service Bus</strong>: Manages asynchronous message queuing between the API and processing layer</p>
</li>
<li data-local-id="37fb0b7e-2a2e-4a61-aa7a-af8a3e3e17b1" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="d71ab9d8ed1a" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Inference Processor</strong>: Downloads images, applies classification, returns results to Stad Roeselare’s Data Platforms.</p>
</li>
<li data-local-id="d22552ca-9a8f-4579-b91b-b7362ffa68fc" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="97f61deec06f" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">PostgreSQL</strong>: Stores structured results with geolocation metadata and observability data via OpenTelemetry</p>
</li>
<li data-local-id="1b2d2d3e-facf-4d9c-97a3-e2a727e7679a" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="82a2f5963ed5" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Scale-to-zero capability</strong>: Compute resources scale down when idle, minimizing costs during gaps between MSU deployments</p>
</li>
</ul>
<p data-local-id="3823465eba7a" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">This architecture mirrors patterns we&#8217;ve described in our earlier post on <a href="https://www.sensr.ai/a-robust-deployment-pattern-for-ml-models-at-the-edge/" target="_blank" rel="noopener" data-prosemirror-content-type="mark" data-prosemirror-mark-name="link">A Robust Deployment Pattern for ML Models at the Edge</a>, where we emphasized the importance of designing for unreliable connectivity and variable processing loads.</p>
</div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-7 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-7 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-title title fusion-title-10 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="c9acc3efbe9d" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">Results: Accuracy Meets Practicality</p></h4></div><div class="fusion-text fusion-text-8"><p data-local-id="488348276685" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The deployed system achieved the following detection performance:</p>
</div>
<div class="table-1" style="--awb-margin-bottom:2rem;">
<table width="100%">
<thead>
<tr>
<th align="left">Test Condition</th>
<th align="left">Detection Accuracy</th>
</tr>
</thead>
<tbody>
<tr>
<td align="left">Clean Database Images</td>
<td align="left">93%</td>
</tr>
<tr>
<td align="left">Real-world MSU rides</td>
<td align="left">77%</td>
</tr>
</tbody>
</table>
</div>
<div class="fusion-text fusion-text-9"><p data-local-id="f88493ab5d59" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The gap between these numbers tells an important story. In controlled conditions with clean images, optimal angles, good lighting, the model performs excellently. In real-world deployment, performance drops but remains practically useful. This pattern is consistent with findings from traffic sign detection research, where models achieving 90%+ mAP in benchmarks typically see reduced performance on in-the-wild data.</p>
</div><div class="fusion-title title fusion-title-11 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="c263e0cd7300" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em><span id="5e4a8219-ad93-4097-b6cb-98266e8ff73e" data-mark-type="annotation" data-mark-annotation-type="inlineComment" data-id="5e4a8219-ad93-4097-b6cb-98266e8ff73e" data-prosemirror-content-type="mark" data-prosemirror-mark-name="annotation">Why 77% is still a win</span></em></p></h5></div><div class="fusion-text fusion-text-10"><p data-local-id="bab5ee242097" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">For Stad Roeselare, the goal wasn&#8217;t perfect detection, it was operational improvement. The system:</p>
<ul class="ak-ul" data-local-id="7f8b629c-68de-4bb1-9e0e-f1f3ac8903b3" data-prosemirror-content-type="node" data-prosemirror-node-name="bulletList" data-prosemirror-node-block="true">
<li data-local-id="a4a46911-2bb7-491b-8d5e-729c37508da5" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="6deb18e73d0d" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Runs continuously</strong>: Every MSU ride automatically updates the inventory</p>
</li>
<li data-local-id="b00528b4-ef65-489e-bf0a-b22f92096320" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="df10d8ba3d17" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Reduces manual effort</strong>: Staff no longer drive dedicated survey routes</p>
</li>
<li data-local-id="4151858e-35bd-40c7-9220-6df3ebaf4924" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="4748de62c949" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Enables faster response</strong>: Current sign locations are always available for maintenance planning</p>
</li>
<li data-local-id="1004f247-45f3-4b5c-8bff-aa3a42d6c80a" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="3cffcd658cec" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Catches changes</strong>: New signs, removed signs and relocated signs are detected automatically</p>
</li>
</ul>
<p data-local-id="40057141e3c3" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">As Roadscan&#8217;s case studies [<span class="inlineCardView-content-wrap inlineNodeView" data-prosemirror-content-type="node" data-prosemirror-node-name="inlineCard" data-prosemirror-node-inline="true"><span class="card" aria-busy="true"><a href="https://roadscan.ai/article/ai-revolutionizes-traffic-sign-management" target="_blank" rel="noopener" data-inline-card="" data-card-data="" data-local-id="429acb65b83f">RoadScan | Smart Roads Safer Tomorrow</a></span></span>] demonstrate, AI-powered traffic sign management can transform month-long manual processes into operations completed in days, with greater accuracy and consistency.</p>
</div><div class="fusion-title title fusion-title-12 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="d89709bb5852" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em><span id="e155f16e-4e09-471a-930a-4059263b2e88" data-mark-type="annotation" data-mark-annotation-type="inlineComment" data-id="e155f16e-4e09-471a-930a-4059263b2e88" data-prosemirror-content-type="mark" data-prosemirror-mark-name="annotation">Operational Impact</span></em></p></h5></div><div class="fusion-text fusion-text-11"><ul class="ak-ul" data-local-id="b9feba58-e8ff-4a86-8256-c34461fb8625" data-prosemirror-content-type="node" data-prosemirror-node-name="bulletList" data-prosemirror-node-block="true" data-pm-slice="3 3 &#091;&#093;">
<li data-local-id="2c37f253-46e1-49a3-bccb-c79b4bc883a3" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="d95c62fe350b" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Continuous inventory updates</strong>: Database reflects ongoing MSU captures</p>
</li>
<li data-local-id="5b5ef27d-36b7-4bcd-821b-8fee23e1a3db" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="38fe544497c0" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Resource reallocation</strong>: Staff focus on higher-value activities like sign maintenance and citizen response</p>
</li>
<li data-local-id="1ae1d82f-0530-4a7c-9529-36e2a438b294" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="2dd319689559" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Reduced survey costs</strong>: Eliminating dedicated survey vehicles and crews</p>
</li>
<li data-local-id="05912ceb-4eb2-41aa-8d5c-d8075c7343d6" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="9de5b38ec00f" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true"><strong data-prosemirror-content-type="mark" data-prosemirror-mark-name="strong">Faster response times</strong>: Current imagery and sign locations always available</p>
</li>
</ul>
</div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-8 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-8 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-title title fusion-title-13 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="18a413556b5c" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><span id="d3c6f77b-5770-4823-a3c1-45cb18177ff0" data-mark-type="annotation" data-mark-annotation-type="inlineComment" data-id="d3c6f77b-5770-4823-a3c1-45cb18177ff0" data-prosemirror-content-type="mark" data-prosemirror-mark-name="annotation">Lessons Learned: What Made This Work</span></p></h4></div><div class="fusion-title title fusion-title-14 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="08c9ddb73e24" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em>1. Hierarchical Design Beats Monolithic Models</em></p></h5></div><div class="fusion-text fusion-text-12"><p data-local-id="ea3bf1285054" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The decision to use specialized classifiers for each sign category proved crucial. Belgian traffic signs include over 1000 distinct (sub)types. A single model trying to distinguish all of them would struggle with the long-tail distribution. By breaking the problem into manageable sub-problems, each model could focus on the distinctions that matter most.</p>
</div><div class="fusion-title title fusion-title-15 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="0e390dc6d8d9" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em>2. Real-World Data is Irreplaceable</em></p></h5></div><div class="fusion-text fusion-text-13"><p data-local-id="5773fd3998ea" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">Training solely on clean databases would have produced a model that failed in deployment. The reference ride footage, despite its lower quality, was essential for teaching the model what signs actually look like from a moving vehicle on Belgian roads.</p>
</div><div class="fusion-title title fusion-title-16 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="0a45ed72acb3" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em>3. Integration Matters as Much as Accuracy</em></p></h5></div><div class="fusion-text fusion-text-14"><p data-local-id="f83f1b3ab90f" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The most sophisticated model is useless if it can&#8217;t feed results into existing workflows. The Sensr team invested heavily in integration with Stad Roeselare&#8217;s data platforms, ensuring that classified signs appeared where municipal staff already worked.</p>
<p data-local-id="a2b870044e3f" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">This philosophy, technology serving existing processes, not demanding new ones, echoes our work with <a href="https://www.sensr.ai/putting-data-to-work-at-electrolux/" target="_blank" rel="noopener" data-prosemirror-content-type="mark" data-prosemirror-mark-name="link">Electrolux&#8217;s EMC² platform</a>, where we emphasized that the human role remains essential in the synergy between technology and human expertise.</p>
</div><div class="fusion-title title fusion-title-17 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="22b434004f06" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em>4. Honest Expectations Enable Success</em></p></h5></div><div class="fusion-text fusion-text-15"><p data-local-id="9929fb2730ac" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The 77% real-world detection rate isn&#8217;t a failure, it&#8217;s a realistic baseline that the municipality can build on. Overpromising accuracy leads to disappointment, setting honest expectations allowed the project to be evaluated on its actual operational impact.</p>
</div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-9 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-9 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-title title fusion-title-18 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="a656f64403c0" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The Bigger Picture: Smart City Asset Management</p></h4></div><div class="fusion-text fusion-text-16"><p data-local-id="e33aaaf2d379" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">Stad Roeselare&#8217;s traffic sign project is part of a broader shift in how municipalities approach infrastructure management. As research on smart city traffic management shows, AI-driven systems can reduce travel times by 10-20% and significantly cut emissions through optimized traffic flow.</p>
<p data-local-id="bd0627f7c680" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">But the technology&#8217;s value extends beyond traffic. The same MSU that captures signs could potentially:</p>
<ul class="ak-ul" data-local-id="846856b8-9b74-4e13-9626-778347a2a753" data-prosemirror-content-type="node" data-prosemirror-node-name="bulletList" data-prosemirror-node-block="true">
<li data-local-id="f597dbd0-b28b-4151-a96c-bc5639e2e669" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="30655d971664" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">Detect road surface damage for proactive maintenance</p>
</li>
<li data-local-id="d06874e8-2970-4fad-8c33-31f9038ada3b" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="dffc9aea3599" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">Identify illegal dumping or unauthorized construction</p>
</li>
<li data-local-id="f16dd4d5-d52e-46b5-9298-4d74e9b00026" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="c1374b6d7203" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">Monitor parking compliance in restricted zones</p>
</li>
<li data-local-id="401f60d8-b39d-4055-ab42-ede602addb5a" data-prosemirror-content-type="node" data-prosemirror-node-name="listItem" data-prosemirror-node-block="true">
<p data-local-id="4cef16200f82" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">Track vegetation overgrowth affecting visibility</p>
</li>
</ul>
<p data-local-id="71704b9bef60" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">The infrastructure is in place; the limiting factor is often the availability of trained models and integration with municipal workflows.</p>
</div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-10 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-10 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-title title fusion-title-19 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="a656f64403c0" data-prosemirror-content-type="node" data-prosemirror-node-name="heading" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">Conclusion</p></h4></div><div class="fusion-text fusion-text-17"><p data-local-id="14f503dc160a" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;">The Stad Roeselare traffic sign classification project demonstrates that successful AI deployment requires more than model accuracy. It demands thoughtful architecture, seamless integration with existing systems and realistic expectations about edge-case performance.</p>
<p data-local-id="92d11dc7b575" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true">Most importantly, it shows that practical AI beats perfect AI. A system that runs continuously at 77% accuracy delivers more value than a hypothetical 99% system that never deploys. For municipalities looking to modernize infrastructure management, the lesson is clear: start with what you have, build what works, and improve iteratively.</p>
</div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-11 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-padding-bottom:10rem;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-11 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-separator fusion-full-width-sep" style="align-self: center;margin-left: auto;margin-right: auto;width:100%;"><div class="fusion-separator-border sep-single sep-solid" style="--awb-height:20px;--awb-amount:20px;--awb-sep-color:var(--awb-color2);border-color:var(--awb-color2);border-top-width:1px;"></div></div><div class="fusion-title title fusion-title-20 fusion-sep-none fusion-title-text fusion-title-size-six" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h6 class="fusion-title-heading title-heading-left" style="margin:0;"><p data-local-id="405f3da02ad2" data-prosemirror-content-type="node" data-prosemirror-node-name="paragraph" data-prosemirror-node-block="true" data-pm-slice="1 1 &#091;&#093;"><em data-prosemirror-content-type="mark" data-prosemirror-mark-name="em"><span id="a70548d3-5fe7-4804-bfc8-821f3f813049" data-mark-type="annotation" data-mark-annotation-type="inlineComment" data-id="a70548d3-5fe7-4804-bfc8-821f3f813049" data-prosemirror-content-type="mark" data-prosemirror-mark-name="annotation">Contact Sensr today to explore how advanced analytics can streamline your operations and put your data to work.</span></em></p></h6></div></div></div></div></div>
<p>The post <a href="https://www.sensr.ai/2026/04/17/from-road-to-data-how-stad-roeselare-automated-traffic-sign-inventory-with-computer-vision/">From Road to Data: How Stad Roeselare Automated Traffic Sign Inventory with Computer Vision</a> appeared first on <a href="https://www.sensr.ai">Sensr</a>.</p>
]]></content:encoded>
					
					<wfw:commentRss>https://www.sensr.ai/2026/04/17/from-road-to-data-how-stad-roeselare-automated-traffic-sign-inventory-with-computer-vision/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
			</item>
		<item>
		<title>Sensr in action: Optimizing energy usage at Etex</title>
		<link>https://www.sensr.ai/2025/06/19/sensr-in-action/</link>
		
		<dc:creator><![CDATA[Imke Heusschen]]></dc:creator>
		<pubDate>Thu, 19 Jun 2025 07:28:46 +0000</pubDate>
				<category><![CDATA[Customer Success Story]]></category>
		<category><![CDATA[Cost optimization]]></category>
		<category><![CDATA[Energy monitoring]]></category>
		<category><![CDATA[Smart Manufacturing]]></category>
		<category><![CDATA[Sustainability]]></category>
		<guid isPermaLink="false">https://www.sensr.ai/?p=1196</guid>

					<description><![CDATA[<p>Sensr in action: Optimizing energy usage at Etex    Following our breakdown of the core principles of energy monitoring, we now take a closer look at a real-world success story, showcasing energy monitoring in action. We sat down with Bart Dieusaert, Analytics Manager for Operations at Etex, to discuss how Sensr helped Etex  [...]</p>
<p>The post <a href="https://www.sensr.ai/2025/06/19/sensr-in-action/">Sensr in action: Optimizing energy usage at Etex</a> appeared first on <a href="https://www.sensr.ai">Sensr</a>.</p>
]]></description>
										<content:encoded><![CDATA[<div class="fusion-fullwidth fullwidth-box fusion-builder-row-12 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-padding-top:0px;--awb-margin-top:;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-12 fusion_builder_column_1_2 1_2 fusion-flex-column fusion-flex-align-self-stretch" style="--awb-bg-size:cover;--awb-width-large:50%;--awb-margin-top-large:0px;--awb-spacing-right-large:3.84%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:3.84%;--awb-width-medium:50%;--awb-order-medium:0;--awb-spacing-right-medium:3.84%;--awb-spacing-left-medium:3.84%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-center fusion-content-layout-column"><div class="fusion-title title fusion-title-21 fusion-sep-none fusion-title-text fusion-title-size-two" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h2 class="fusion-title-heading title-heading-left" style="margin:0;">Sensr in action: Optimizing energy usage at Etex</h2></div></div></div><div class="fusion-layout-column fusion_builder_column fusion-builder-column-13 fusion_builder_column_1_2 1_2 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:50%;--awb-margin-top-large:0px;--awb-spacing-right-large:3.84%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:3.84%;--awb-width-medium:50%;--awb-order-medium:0;--awb-spacing-right-medium:3.84%;--awb-spacing-left-medium:3.84%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-image-element" style="text-align:right;--awb-margin-right:2rem;--awb-max-width:50%;--awb-caption-title-font-family:var(--h2_typography-font-family);--awb-caption-title-font-weight:var(--h2_typography-font-weight);--awb-caption-title-font-style:var(--h2_typography-font-style);--awb-caption-title-size:var(--h2_typography-font-size);--awb-caption-title-transform:var(--h2_typography-text-transform);--awb-caption-title-line-height:var(--h2_typography-line-height);--awb-caption-title-letter-spacing:var(--h2_typography-letter-spacing);"><span class=" fusion-imageframe imageframe-none imageframe-4 hover-type-none"><img decoding="async" width="1834" height="574" title="etex_logo 1" src="https://www.sensr.ai/wp-content/uploads/2024/01/etex_logo-1.png" alt class="img-responsive wp-image-809" srcset="https://www.sensr.ai/wp-content/uploads/2024/01/etex_logo-1-200x63.png 200w, https://www.sensr.ai/wp-content/uploads/2024/01/etex_logo-1-400x125.png 400w, https://www.sensr.ai/wp-content/uploads/2024/01/etex_logo-1-600x188.png 600w, https://www.sensr.ai/wp-content/uploads/2024/01/etex_logo-1-800x250.png 800w, https://www.sensr.ai/wp-content/uploads/2024/01/etex_logo-1-1200x376.png 1200w, https://www.sensr.ai/wp-content/uploads/2024/01/etex_logo-1.png 1834w" sizes="(max-width: 640px) 100vw, 600px" /></span></div></div></div><div class="fusion-layout-column fusion_builder_column fusion-builder-column-14 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:3rem;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:10rem;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-text fusion-text-18"><p>Following our breakdown of the core principles of energy monitoring, we now take a closer look at a real-world success story, showcasing energy monitoring in action.</p>
<p>We sat down with Bart Dieusaert, Analytics Manager for Operations at Etex, to discuss how Sensr helped Etex implement Energy Monitoring Systems (EMS), optimize energy usage, and drive progress toward its sustainability goals.</p>
</div><div class="fusion-title title fusion-title-22 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;">The need for energy monitoring</h4></div><div class="fusion-text fusion-text-19"><p>In the world of building materials, Etex stands as a global innovator in lightweight construction solutions. While the company offers a diverse range of products, including plasterboards, fibre cement boards, and insulation materials, one major challenge they face is the high energy consumption required for the production of plasterboards.</p>
</div><div class="fusion-title title fusion-title-23 fusion-sep-none fusion-title-center fusion-title-text fusion-title-size-five" style="--awb-text-color:var(--awb-color5);--awb-margin-top:2rem;--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-center" style="margin:0;"><strong><em data-renderer-mark="true">“Although building plasterboard materials may seem straightforward, it remains one of our most energy-intensive processes due to the substantial energy required for heating and drying. We faced high energy costs while striving to comply with environmental regulations. This made it crucial for us to find a solution that would not only reduce energy consumption but also support our sustainability goals.”</em></strong></h5></div><div class="fusion-title title fusion-title-24 fusion-sep-none fusion-title-center fusion-title-text fusion-title-size-six" style="--awb-text-color:#a9adab;--awb-margin-top:0px;--awb-margin-bottom:3rem;--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h6 class="fusion-title-heading title-heading-center" style="margin:0;">Bart Dieusaert, Etex</h6></div><div class="fusion-text fusion-text-20"><p>To address this challenge, Etex decided to implement energy monitoring in its plasterboard plants, enabling them to track energy consumption across electricity, gas, steam, and other fuel sources. This data is then combined with quality and process data to generate actionable insights. Together with Sensr, they embarked on a journey to enhance energy efficiency.</p>
</div><div class="fusion-title title fusion-title-25 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;">Implementing energy monitoring with Sensr</h4></div><div class="fusion-text fusion-text-21"><p>Etex&#8217;s energy optimization journey began at its pilot plant in Italy, a factory with a single production line and significant energy demands, making it an ideal testing ground. The process started with the installation of sensors at critical points in production to track energy variables such as electricity, gas, and water usage. “We started by installing sensors on our plasterboard production lines,” explained Bart. “These sensors monitored the energy consumption of individual machines and the overall production line. The data was then fed into Etex&#8217;s Data Platform, providing real-time insights into our energy usage.” This real-time monitoring allowed Etex to visualize energy consumption patterns, detect inefficiencies, and make data-driven decisions to optimize energy use. For example, by measuring water loss during the drying stage, they could determine whether boards were too wet or too dry, enabling adjustments that minimized energy waste.</p>
<p>With the EMS in place, Etex was able to transform raw energy data into actionable insights. The system generated three types of reports:</p>
<ol>
<li><span style="font-family: var(--awb-text-font-family); font-size: var(--awb-font-size); font-style: var(--awb-text-font-style); letter-spacing: var(--awb-letter-spacing); text-align: var(--awb-content-alignment); text-transform: var(--awb-text-transform);"><span style="font-family: var(--awb-text-font-family); font-size: var(--awb-font-size); font-style: var(--awb-text-font-style); letter-spacing: var(--awb-letter-spacing); text-align: var(--awb-content-alignment); text-transform: var(--awb-text-transform);"><b>Real-time reports</b>: These reports provide operators with live visualizations of energy consumption on factory floor screens. Data is collected every ten minutes and displayed next to the machines, allowing operators to take immediate action if key performance indicators (KPIs) deviate from the norm. The real-time data is stored for up to eight hours, offering a short-term view that supports quick decision-making and adjustments to optimize processes and reduce energy consumption.</span></span></li>
<li><span style="font-family: var(--awb-text-font-family); font-size: var(--awb-font-size); font-style: var(--awb-text-font-style); letter-spacing: var(--awb-letter-spacing); text-align: var(--awb-content-alignment); text-transform: var(--awb-text-transform);"><span style="font-family: var(--awb-text-font-family); font-size: var(--awb-font-size); font-style: var(--awb-text-font-style); letter-spacing: var(--awb-letter-spacing); text-align: var(--awb-content-alignment); text-transform: var(--awb-text-transform);"><b>Process parameter reports</b>: Designed for process engineers, these reports provide comprehensive historical data, integrating various process parameters such as production square meters and water loss during the drying process. Engineers can use this data to identify long-term optimization opportunities and refine production processes. For example, by analyzing temperature limits in the mixing stage, they can set upper and lower thresholds to optimize energy use while maintaining product quality, preventing energy waste and ensuring product standards.</span></span></li>
<li><span style="font-family: var(--awb-text-font-family); font-size: var(--awb-font-size); font-style: var(--awb-text-font-style); letter-spacing: var(--awb-letter-spacing); text-align: var(--awb-content-alignment); text-transform: var(--awb-text-transform);"><b>Daily reports</b>: These reports consolidate daily energy data, providing plant managers with an overview of consumption patterns. They play a crucial role in strategic decision-making, helping managers identify areas for improvement and determine which production lines to investigate for potential energy savings.</span></li>
</ol>
<div>These insights directly impacted operations.</div>
</div><div class="fusion-title title fusion-title-26 fusion-sep-none fusion-title-center fusion-title-text fusion-title-size-five" style="--awb-text-color:var(--awb-color5);--awb-margin-top:2rem;--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-center" style="margin:0;"><strong><em data-renderer-mark="true">The real-time and process parameter reports have been instrumental in enabling our operators and engineers to make informed decisions quickly. The daily reports help our plant managers identify trends and make strategic decisions to further optimize our operations.”</em></strong></h5></div><div class="fusion-title title fusion-title-27 fusion-sep-none fusion-title-center fusion-title-text fusion-title-size-six" style="--awb-text-color:#a9adab;--awb-margin-top:0px;--awb-margin-bottom:3rem;--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h6 class="fusion-title-heading title-heading-center" style="margin:0;">Bart Dieusaert, Etex</h6></div><div class="fusion-title title fusion-title-28 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;">Expanding the success</h4></div><div class="fusion-text fusion-text-22" style="--awb-margin-top:1.5rem;"><p>Building on the success of the pilot project in Italy, Etex expanded the EMS to two additional plants in Latin America (Chile and Brazil) and aims to implement it across multiple plants, prioritizing those with the highest energy consumption for maximum impact.</p>
<p>Bart stated, “Working with Sensr has led to significant reductions in energy waste and cost savings for Etex. We are excited to extend these benefits to more plants worldwide.”</p>
</div><div class="fusion-title title fusion-title-29 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;">The role of Sensr</h4></div><div class="fusion-text fusion-text-23" style="--awb-margin-top:1.5rem;"><p>The success of this project has been fueled by the combined efforts of Sensr and Etex. Sensr designed the IT architecture, managed data engineering, and continues to provide hands-on support during the rollout to new locations.</p>
</div><div class="fusion-title title fusion-title-30 fusion-sep-none fusion-title-center fusion-title-text fusion-title-size-five" style="--awb-text-color:var(--awb-color5);--awb-margin-top:2rem;--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-center" style="margin:0;"><b>“The resources and flexibility provided by Sensr were crucial. Their onshore presence ensured seamless communication and adaptability, making them an invaluable ally for this project.” He added, “Working with Sensr has allowed us to bring in additional expertise and resources, which have been vital in supporting our goals for energy efficiency and sustainability.”</b></h5></div><div class="fusion-title title fusion-title-31 fusion-sep-none fusion-title-center fusion-title-text fusion-title-size-six" style="--awb-text-color:#a9adab;--awb-margin-top:0px;--awb-margin-bottom:3rem;--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h6 class="fusion-title-heading title-heading-center" style="margin:0;">Bart Dieusaert, Etex</h6></div><div class="fusion-title title fusion-title-32 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;">Future challenges</h4></div><div class="fusion-text fusion-text-24"><p>As Etex continues expanding its EMS across more factories worldwide, several challenges emerge. A key hurdle is standardizing data input and maintaining data quality across diverse manufacturing sites, each with unique configurations and local practices. Integrating advanced data analytics requires a robust data governance framework, which can be difficult to implement consistently across multiple locations.</p>
<p>Additionally, ongoing training and support for plant operators and process engineers are essential to fully harness the capabilities of energy monitoring. Ensuring seamless interaction between onshore and offshore teams, while maintaining flexibility and clear communication, will also be critical to the project&#8217;s continued success.</p>
<p>Despite these challenges, Etex&#8217;s expansion efforts continue to be driven by its commitment to sustainability and energy efficiency.</p>
</div><div class="fusion-title title fusion-title-33 fusion-sep-none fusion-title-text fusion-title-size-four" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h4 class="fusion-title-heading title-heading-left" style="margin:0;">Conclusion</h4></div><div class="fusion-text fusion-text-25"><p>The combined efforts of Etex and Sensr highlights the transformative power of energy monitoring in the industrial sector. By leveraging advanced technologies and data analytics, Etex has not only reduced its energy consumption but also made meaningful progress toward its sustainability goals. As Etex continues rolling out the EMS across its global operations, Sensr remains a dedicated ally, providing ongoing support and expertise.</p>
</div></div></div></div></div>
<p>The post <a href="https://www.sensr.ai/2025/06/19/sensr-in-action/">Sensr in action: Optimizing energy usage at Etex</a> appeared first on <a href="https://www.sensr.ai">Sensr</a>.</p>
]]></content:encoded>
					
		
		
			</item>
		<item>
		<title>Putting data to work at Electrolux</title>
		<link>https://www.sensr.ai/2024/10/08/putting-data-to-work-at-electrolux/</link>
		
		<dc:creator><![CDATA[Imke Heusschen]]></dc:creator>
		<pubDate>Tue, 08 Oct 2024 07:07:11 +0000</pubDate>
				<category><![CDATA[Customer Success Story]]></category>
		<guid isPermaLink="false">https://www.sensr.ai/?p=1120</guid>

					<description><![CDATA[<p>Putting data to work      At Sensr, we believe that no one can better assess and solve workplace problems than employees themselves. With that in mind, we are supporting Electrolux in building and rolling out an innovative cloud platform. With EMC², the home appliance manufacturer provides its operators, process experts, managers,  [...]</p>
<p>The post <a href="https://www.sensr.ai/2024/10/08/putting-data-to-work-at-electrolux/">Putting data to work at Electrolux</a> appeared first on <a href="https://www.sensr.ai">Sensr</a>.</p>
]]></description>
										<content:encoded><![CDATA[<div class="fusion-fullwidth fullwidth-box fusion-builder-row-13 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-margin-bottom:5rem;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-15 fusion_builder_column_1_2 1_2 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:50%;--awb-margin-top-large:7rem;--awb-spacing-right-large:3.84%;--awb-margin-bottom-large:7rem;--awb-spacing-left-large:3.84%;--awb-width-medium:50%;--awb-order-medium:0;--awb-spacing-right-medium:3.84%;--awb-spacing-left-medium:3.84%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-title title fusion-title-34 fusion-sep-none fusion-title-text fusion-title-size-one" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h1 class="fusion-title-heading title-heading-left" style="margin:0;">Putting data <br />to work</h1></div></div></div><div class="fusion-layout-column fusion_builder_column fusion-builder-column-16 fusion_builder_column_1_2 1_2 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:50%;--awb-margin-top-large:0px;--awb-spacing-right-large:3.84%;--awb-margin-bottom-large:20px;--awb-spacing-left-large:3.84%;--awb-width-medium:50%;--awb-order-medium:0;--awb-spacing-right-medium:3.84%;--awb-spacing-left-medium:3.84%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-image-element" style="text-align:right;--awb-margin-right:2rem;--awb-max-width:65%;--awb-caption-title-font-family:var(--h2_typography-font-family);--awb-caption-title-font-weight:var(--h2_typography-font-weight);--awb-caption-title-font-style:var(--h2_typography-font-style);--awb-caption-title-size:var(--h2_typography-font-size);--awb-caption-title-transform:var(--h2_typography-text-transform);--awb-caption-title-line-height:var(--h2_typography-line-height);--awb-caption-title-letter-spacing:var(--h2_typography-letter-spacing);"><span class=" fusion-imageframe imageframe-none imageframe-5 hover-type-none"><img decoding="async" width="2560" height="587" title="Electrolux_2015 3" src="https://www.sensr.ai/wp-content/uploads/2024/01/Electrolux_2015-3.png" alt class="img-responsive wp-image-810" srcset="https://www.sensr.ai/wp-content/uploads/2024/01/Electrolux_2015-3-200x46.png 200w, https://www.sensr.ai/wp-content/uploads/2024/01/Electrolux_2015-3-400x92.png 400w, https://www.sensr.ai/wp-content/uploads/2024/01/Electrolux_2015-3-600x138.png 600w, https://www.sensr.ai/wp-content/uploads/2024/01/Electrolux_2015-3-800x183.png 800w, https://www.sensr.ai/wp-content/uploads/2024/01/Electrolux_2015-3-1200x275.png 1200w, https://www.sensr.ai/wp-content/uploads/2024/01/Electrolux_2015-3.png 2560w" sizes="(max-width: 640px) 100vw, 600px" /></span></div></div></div></div></div><div class="fusion-fullwidth fullwidth-box fusion-builder-row-14 fusion-flex-container has-pattern-background has-mask-background nonhundred-percent-fullwidth non-hundred-percent-height-scrolling" style="--awb-border-radius-top-left:0px;--awb-border-radius-top-right:0px;--awb-border-radius-bottom-right:0px;--awb-border-radius-bottom-left:0px;--awb-flex-wrap:wrap;" ><div class="fusion-builder-row fusion-row fusion-flex-align-items-flex-start fusion-flex-content-wrap" style="max-width:1248px;margin-left: calc(-4% / 2 );margin-right: calc(-4% / 2 );"><div class="fusion-layout-column fusion_builder_column fusion-builder-column-17 fusion_builder_column_1_1 1_1 fusion-flex-column" style="--awb-bg-size:cover;--awb-width-large:100%;--awb-margin-top-large:0px;--awb-spacing-right-large:1.92%;--awb-margin-bottom-large:10rem;--awb-spacing-left-large:1.92%;--awb-width-medium:100%;--awb-order-medium:0;--awb-spacing-right-medium:1.92%;--awb-spacing-left-medium:1.92%;--awb-width-small:100%;--awb-order-small:0;--awb-spacing-right-small:1.92%;--awb-spacing-left-small:1.92%;"><div class="fusion-column-wrapper fusion-column-has-shadow fusion-flex-justify-content-flex-start fusion-content-layout-column"><div class="fusion-text fusion-text-26"><p><strong>At Sensr, we believe that no one can better assess and solve workplace problems than employees themselves. With that in mind, we are supporting Electrolux in building and rolling out an innovative cloud platform.</strong></p>
<p>With EMC², the home appliance manufacturer provides its operators, process experts, managers, &#8230; with the necessary tools to build scalable solutions that can be deployed across various sites. The platform is now fully operational, and several use cases have already been successfully rolled out. A large portion of these applications focuses on performance measurement, and who better to tell you more about these applications than our data experts at Sensr?</p>
</div><div class="fusion-title title fusion-title-35 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;">1. Faster defect detection thanks to end-of-line testing</h5></div><div class="fusion-text fusion-text-27"><p>During production, Electrolux devices undergo numerous quality checks. For refrigerators, ovens, dishwashers, and more, inspections ensure that the electronics are functioning, insulation is up to standard, and doors close properly. These quality checks are performed at Electrolux’s various production sites worldwide, and for a wide range of appliances. In the past, the results of these checks were scattered across different systems and machines at each site. Thanks to the EMC² platform, that data is now centralized. This is extremely valuable because one production site can now learn from another, and differences in the output of similar machines are detected more quickly.</p>
</div><div class="fusion-title title fusion-title-36 fusion-sep-none fusion-title-center fusion-title-text fusion-title-size-five" style="--awb-text-color:var(--awb-color5);--awb-margin-top:2rem;--awb-margin-bottom:3rem;--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-center" style="margin:0;"><p style="text-align: center;"><em><strong>&#8220;Thanks to the EMC² platform, all data is now centralized,<br />
allowing one production site to learn from another.&#8221;</strong></em></p></h5></div><div class="fusion-text fusion-text-28"><p>The next step is to link the reports from the quality checks with data from the ESMI data lake. The ESMI (Electrolux Standard Machine Interface) is an internal data standard that Electrolux uses to collect and centralize information from various production processes. This includes steps taken by machines and their configurations. By linking the quality control data with this production data, Electrolux gains better insights into which settings lead to certain issues and defects. This allows them to optimize their production processes, ensuring the quality of their products and reducing waste from defective products. This is crucial, as waste reduction is a key pillar of Electrolux&#8217;s sustainability strategy.</p>
</div><div class="fusion-image-element" style="--awb-margin-bottom:2rem;--awb-caption-title-font-family:var(--h2_typography-font-family);--awb-caption-title-font-weight:var(--h2_typography-font-weight);--awb-caption-title-font-style:var(--h2_typography-font-style);--awb-caption-title-size:var(--h2_typography-font-size);--awb-caption-title-transform:var(--h2_typography-text-transform);--awb-caption-title-line-height:var(--h2_typography-line-height);--awb-caption-title-letter-spacing:var(--h2_typography-letter-spacing);"><span class=" fusion-imageframe imageframe-none imageframe-6 hover-type-none"><img decoding="async" width="1140" height="855" title="Factory-Thailand-145_999a5d079e886f78f1202bd59f13280b" src="https://www.sensr.ai/wp-content/uploads/2024/09/Factory-Thailand-145_999a5d079e886f78f1202bd59f13280b.webp" alt class="img-responsive wp-image-1122" srcset="https://www.sensr.ai/wp-content/uploads/2024/09/Factory-Thailand-145_999a5d079e886f78f1202bd59f13280b-200x150.webp 200w, https://www.sensr.ai/wp-content/uploads/2024/09/Factory-Thailand-145_999a5d079e886f78f1202bd59f13280b-400x300.webp 400w, https://www.sensr.ai/wp-content/uploads/2024/09/Factory-Thailand-145_999a5d079e886f78f1202bd59f13280b-600x450.webp 600w, https://www.sensr.ai/wp-content/uploads/2024/09/Factory-Thailand-145_999a5d079e886f78f1202bd59f13280b-800x600.webp 800w, https://www.sensr.ai/wp-content/uploads/2024/09/Factory-Thailand-145_999a5d079e886f78f1202bd59f13280b.webp 1140w" sizes="(max-width: 640px) 100vw, 1140px" /></span></div><div class="fusion-title title fusion-title-37 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;">2. Reduced emissions and energy costs thanks to furnace optimization</h5></div><div class="fusion-text fusion-text-29"><p>Another useful application, building on the ESMI warehouse, is furnace optimization. To give some context: a large portion of the products Electrolux manufactures, such as ovens, receive a ceramic coating. This coating is applied in a massive gas furnace (about 300 m³!) that heats up to 800°C. Electrolux operates around 30 of these furnaces, which are collectively responsible for a significant portion of internal emissions. With these emissions in mind, Electrolux sought a way to use the furnaces as efficiently as possible. The room for improvement lay in the timing of when the furnaces are turned on.</p>
<p>These furnaces need time to reach the required temperature, and this warm-up period fluctuates based on factors such as the ambient temperature. So, our experts developed an algorithm that determines the ideal start time for the furnace and switches it on at the optimal moment. Whereas the furnaces were previously activated according to a fixed schedule, they are now turned on when the operator receives an email with a more precise start time. The next step is to introduce a new algorithm that directly controls the furnace.</p>
<p>While the actual savings depend on the current gas price, we’ve already achieved significant savings—both financially and in terms of CO₂ emissions—simply by correctly timing the preheating of the furnaces.</p>
</div><div class="fusion-image-element" style="--awb-margin-bottom:2rem;--awb-caption-title-font-family:var(--h2_typography-font-family);--awb-caption-title-font-weight:var(--h2_typography-font-weight);--awb-caption-title-font-style:var(--h2_typography-font-style);--awb-caption-title-size:var(--h2_typography-font-size);--awb-caption-title-transform:var(--h2_typography-text-transform);--awb-caption-title-line-height:var(--h2_typography-line-height);--awb-caption-title-letter-spacing:var(--h2_typography-letter-spacing);"><span class=" fusion-imageframe imageframe-none imageframe-7 hover-type-none"><img decoding="async" width="1140" height="855" title="Mockup_Dashboard-OEE_999a5d079e886f78f1202bd59f13280b" src="https://www.sensr.ai/wp-content/uploads/2024/09/Mockup_Dashboard-OEE_999a5d079e886f78f1202bd59f13280b.webp" alt class="img-responsive wp-image-1123" srcset="https://www.sensr.ai/wp-content/uploads/2024/09/Mockup_Dashboard-OEE_999a5d079e886f78f1202bd59f13280b-200x150.webp 200w, https://www.sensr.ai/wp-content/uploads/2024/09/Mockup_Dashboard-OEE_999a5d079e886f78f1202bd59f13280b-400x300.webp 400w, https://www.sensr.ai/wp-content/uploads/2024/09/Mockup_Dashboard-OEE_999a5d079e886f78f1202bd59f13280b-600x450.webp 600w, https://www.sensr.ai/wp-content/uploads/2024/09/Mockup_Dashboard-OEE_999a5d079e886f78f1202bd59f13280b-800x600.webp 800w, https://www.sensr.ai/wp-content/uploads/2024/09/Mockup_Dashboard-OEE_999a5d079e886f78f1202bd59f13280b.webp 1140w" sizes="(max-width: 640px) 100vw, 1140px" /></span></div><div class="fusion-title title fusion-title-38 fusion-sep-none fusion-title-text fusion-title-size-five" style="--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-left" style="margin:0;">3. Accurate reporting thanks to OEE reporting</h5></div><div class="fusion-text fusion-text-30"><p>At Electrolux, the efficiency of each production site is measured using the OEE (Overall Equipment Effectiveness) score. This score provides insights into how much of the time production lines are running, at what speed, and how many defects occur. Data for this is collected by each individual machine and read by a central platform, where the information is consolidated.</p>
<p>However advanced the technology may be, machines can still transmit incorrect data, or there may be some nuances that cause the data to be misinterpreted. That’s why the human factor is indispensable in this process—the concept of &#8220;the human in the loop&#8221; plays a crucial role. The collected data is shared via an application with the operator, who can double-check, refine, or adjust the data if necessary. This dual-check system significantly increases the reliability of the reporting, as both machine and human oversee the process. The combined data is then displayed in clear dashboards, providing a transparent view of production efficiency.</p>
</div><div class="fusion-title title fusion-title-39 fusion-sep-none fusion-title-center fusion-title-text fusion-title-size-five" style="--awb-text-color:var(--awb-color5);--awb-margin-top:2rem;--awb-margin-bottom:3rem;--awb-margin-top-small:10px;--awb-margin-right-small:0px;--awb-margin-bottom-small:10px;--awb-margin-left-small:0px;"><h5 class="fusion-title-heading title-heading-center" style="margin:0;"><p style="text-align: center;"><strong><em>&#8220;It’s the employees of Electrolux,<br />
working alongside advanced digitalization,<br />
who ensure continuous improvement of the production process.&#8221;</em></strong></p></h5></div><div class="fusion-text fusion-text-31"><p>Two key takeaways: first, this example shows that the human role remains essential in the synergy between technology and human expertise. It’s the employees of Electrolux who, together with advanced digital tools, ensure continuous improvement of the production process. Secondly, these applications help Electrolux remain not only technologically innovative but also human-centered and responsible—another key pillar in their sustainability framework.</p>
</div><div class="fusion-text fusion-text-32 fusion-text-no-margin" style="--awb-margin-bottom:4rem;"><p>This kind of success is only possible through strong collaboration. Working with Cronos aan de Leie and Electrolux has been key to driving both innovation and efficiency. At Sensr, we’re proud of what we’ve achieved so far and look forward to seeing where this partnership will go, as we continue combining technology with human expertise for future improvements.</p>
</div></div></div></div></div>
<p>The post <a href="https://www.sensr.ai/2024/10/08/putting-data-to-work-at-electrolux/">Putting data to work at Electrolux</a> appeared first on <a href="https://www.sensr.ai">Sensr</a>.</p>
]]></content:encoded>
					
		
		
			</item>
	</channel>
</rss>
