Using PLM Analytics to identify Manufacturing Defects

As a practical example to show the power of EXALEAD PLM Analytics on the 3DEXPERIENCE platform, let’s identify a trending issue from external data.

A consumer reported a defect in which the car’s plastic dashboard was melting. We analyzed public recall information from the NHTSA (National Highway Transportation Safety Administration) database to discover that rather than being an isolated case, this was a growing issue in the automotive industry.

EXALEAD PLM Analytics applied semantic and clustering algorithms in order to identify commonalities across reported issues and found 46 similar issue reports related to “dash melting.”

By investigating similar cases, we concluded that the defect was due to a faulty material being used by the supplier of the dashboards. Armed with this intelligence, the car manufacturer can create a new issue in ENOVIA on the 3DEXPERIENCE platform to enable team collaboration to solve the defect. The resolution of the issue may then lead to:

  • Issuing a service bulletin to instruct retailers and garages on how to correct the problem when it occurs; and
  • Issuing a change to correct the defect at the source of the problem—whether within the supply chain, the design phase, manufacturing or testing.

Despite the many different ways of describing issues with the defective dashboard, Machine Learning coupled with an algorithm that extracts semantic meaning from text was able to identify a growing trend from a large volume of dissimilar data. This kind of information intelligence can be used proactively to identify and mitigate issues and risk.

Learn how to put Project Intelligence to work for your company. Explore EXALEAD PLM Analytics

Related articles : 

 

 

 

 

Read our eBook PERFORMANCE-DRIVEN PROJECT MANAGEMENT WITH PLM ANALYTICS

 

 

 

 

 

Karin

Karin is a brand content creator on the NETVIBES-EXALEAD Marketing team. Previously in Corporate Communications, she has been at Dassault Systèmes for over 14 years.