Smart decision engine for quality control on production line

‍Problem description

• On the production line, a scheduled reference change occurs every two hours. This requires the use of different components. 
• If the engineer anticipates the use of 200 components for a particular reference, and only 180 are available, the line will halt. An alert is then sent to the engineer, indicating that the reference needs to be changed and a different product must be produced, as there are insufficient components for Reference B. 
• The engineer must personally intervene on the production line to make the necessary adjustments.

Challenge

Can the decision engine autonomously plan a change in references based on the available components and switch the production line to the next reference?

Solution

• Integrations of many data points into one workflow
• Prepared and deployed the forecast algorithms which indicate when the next reference should start in
• Prepared BI reporting and alerting mechanism if reference couldn't be made

Key Results

• Cost savings: calculate cost savings resulting from reduced downtime, improved component management, and optimized production scheduling. This include savings on labor, reduced component waste, and lower maintenance costs.
• Reduced downtime: the primary goal of the decision engine is to minimize downtime caused by component shortages. Key results in this area include a significant reduction in unplanned production line halts due to insufficient components. This is quantified by measuring the number of downtime incidents before and after implementing the decision engine.
• Improved component management: measure how effectively the decision engine manages available components. Key results include a reduction in component waste, optimized component utilization, and a decrease in the number of occasions where production has to be switched to a different reference due to shortages.

Why Choose SLS?

The SLS platform revolutionizes quality control by:  

• Leveraging AI to automate inspections and deliver precise damage assessments.  
• Enhancing production line efficiency through reduced downtime and improved defect detection.  
• Ensuring consistent quality standards with real-time feedback and continuous learning.  
  

With SLS, manufacturers can achieve superior product quality while optimizing production processes. 

Questions Answered:

How can we improve quality control and detect defects in real-time?  

• Answer: By deploying the SLS platform's machine learning model, which inspects components in real-time and provides actionable insights.  

How can we reduce false alarms and unnecessary interruptions on the production line?  

• Answer: SLS uses self-learning algorithms to improve decision accuracy, ensuring only genuine issues trigger alerts.