Locate source(s) of failure in axle assemblies Reduce failure and rework rates using automotive manufacturing data Objectives Assemblies require >200 measurements across 20 different operations to produce one unit Multiple sources contributed to variance in component selection Challenge LinePulse's recommendations reduced failure and rework rate by 65% Significant improvements to manufacturing throughput and cost optimization Results Acerta initially deployed the LinePulse Anomaly Detection module in order to identify the source(s) of assembly issues resulting in backlash failures. LinePulse identified several key measurements from the manufacturing process that most reliably predicted backlash failures. This enabled the client to narrow down the list of likely causes of the failures— Results The impacts on cost optimization and throughput observed in initial deployments of LinePulse have led the customer to utilize Acerta's platform across facilities globally and prioritize investment into these Industry 4.0 and AI initiatives. The implemented system achieved a 65% reduction in failure and rework rates, leading to a significant improvement in first time through yield (FTT) and cost reductions for the client. acerta.ai +1 (519) 341-6080 [email protected] AI-Driven Assembly LinePulse Case Study Background A major Tier 1 supplier was looking to leverage machine learning techniques on production assembly data to reduce the rate of product fallout and associated rework for axle assemblies. A company-wide initiative to deploy such advanced manufacturing solutions resulted in an engagement with Acerta, the only SaaS provider that demonstrated an extensive history of automotive manufacturing use cases for machine learning. Several production facilities were considered for the initial deployment, with LinePulse ultimately being utilized globally on multiple lines in several manufacturing facilities to provide insights across the client’s supply chain. Problem Just one of the client’s production lines consists of more than 20 different operations which collectively generate over 200 measurements per assembled unit. Given the number of available measurements that can influence each unit, narrowing down the sources of failures was critical. This difficulty was compounded by the existence of multiple failure modes, each of which could have a different underlying set of causes. Solution Process including previously unsuspected relationships resulting from measurements across operations—without the usual manual effort involved in sifting through large volumes of production data. These early results convinced the client to deploy LinePulse's Intelligent Component Selection to analyze the complex interactions between signals and provide automated recommendations during sub-assembly component selection. The client’s existing component selection process was based on an arithmetic formula that engineers would adjust manually whenever the failure rate exceeded a certain threshold. The implementation of Intelligent Component Selection replaced this approach with a set of machine learning models that are dynamically retrained through the LinePulse platform to consistently maintain superior performance. This approach was initially utilized to optimize the rework process for failed parts. However, due to the success of this early implementation, the client chose to deploy LinePulse as part of the ongoing assembly process to optimize component selection and minimize assembly failures.
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Locate source(s) of failure in axleassembliesReduce failure and rework ratesusing automotive manufacturingdata
ObjectivesAssemblies require >200measurements across 20 differentoperations to produce one unitMultiple sources contributed tovariance in component selection
ChallengeLinePulse's recommendationsreduced failure and rework rate by65%Significant improvements tomanufacturing throughput and costoptimization
Results
Acerta initially deployed the LinePulse Anomaly Detectionmodule in order to identify the source(s) of assembly issuesresulting in backlash failures. LinePulse identified several keymeasurements from the manufacturing process that mostreliably predicted backlash failures. This enabled the client tonarrow down the list of likely causes of the failures—
Results The impacts on cost optimization and throughput observed ininitial deployments of LinePulse have led the customer toutilize Acerta's platform across facilities globally and prioritizeinvestment into these Industry 4.0 and AI initiatives. Theimplemented system achieved a 65% reduction in failure andrework rates, leading to a significant improvement in first timethrough yield (FTT) and cost reductions for the client.
acerta.ai +1 (519) [email protected]
AI-Driven AssemblyLinePulse Case Study
Background A major Tier 1 supplier was looking to leverage machinelearning techniques on production assembly data to reduce therate of product fallout and associated rework for axleassemblies. A company-wide initiative to deploy suchadvanced manufacturing solutions resulted in an engagementwith Acerta, the only SaaS provider that demonstrated anextensive history of automotive manufacturing use cases formachine learning. Several production facilities were consideredfor the initial deployment, with LinePulse ultimately beingutilized globally on multiple lines in several manufacturingfacilities to provide insights across the client’s supply chain.
ProblemJust one of the client’s production lines consists of more than20 different operations which collectively generate over 200measurements per assembled unit. Given the number ofavailable measurements that can influence each unit,narrowing down the sources of failures was critical. Thisdifficulty was compounded by the existence of multiple failuremodes, each of which could have a different underlying set ofcauses.
Solution Process
including previously unsuspected relationships resulting frommeasurements across operations—without the usual manualeffort involved in sifting through large volumes of productiondata.
These early results convinced the client to deploy LinePulse'sIntelligent Component Selection to analyze the complexinteractions between signals and provide automatedrecommendations during sub-assembly component selection.The client’s existing component selection process was basedon an arithmetic formula that engineers would adjust manuallywhenever the failure rate exceeded a certain threshold. Theimplementation of Intelligent Component Selection replacedthis approach with a set of machine learning models that aredynamically retrained through the LinePulse platform toconsistently maintain superior performance.
This approach was initially utilized to optimize the reworkprocess for failed parts. However, due to the success of thisearly implementation, the client chose to deploy LinePulse aspart of the ongoing assembly process to optimize componentselection and minimize assembly failures.
Related Documents
