Customer use case: use of predictive quality analytics in shell construction

The topic of predictive quality analytics is playing an increasingly important role in the planning of many companies. When it comes to the concrete implementation of a solution in the customer environment, not only the technology but also a deep understanding of the processes by all those involved is required.

We present a typical use case as an example:

Initial situation

In the past, individual inspection orders were generated on the basis of predefined static inspection plans. In SPC data acquisition, either parts are acknowledged as “OK” or “NOK” in relation to the respective inspection order. In order to obtain an overview of the reported defects, all defect information including images is recorded and displayed. In the specific customer case, more than 10 employees are permanently involved in ultrasonic testing.

Solution – AI-based process optimization

In a joint project from 2019, the basis for the implementation of an AI-based process optimization was set up. One of the aims was to support anomaly detection with a defined algorithm and reduce the scope of inspections. The process data is compared with other welding information already in the system for this purpose. This makes it possible to decide in real time whether the welded spot that has been classified as “n.I.O.” is relevant for a manual re-inspection and needs to be re-inspected by an inspector. In this case, the body is directed to a designated inspection station and the inspector can use an overview to check all the anomaly points collected.

The number and effort of manual ultrasonic inspections has been reduced by more than half thanks to the “Predictive Quality Analytics” approach.

Results and benefits

  • By integrating “Predictive Quality Analytics” into the existing inspection strategy, the quality of the ultrasonic inspection is significantly increased, as only conspicuous spot welds (anomaly points) are inspected in addition to the existing equipment inspection.
  • The integration of “Predictive Quality Analytics” increases the inspection rate to 100% of all welded spots.
  • The image database enables a visual representation of the spot welds to be inspected and feedback on the anomaly points.
  • As a result, the customer has achieved a significant reduction in manual ultrasonic inspections.

Get in touch!

Would you like to know more about our solutions? Then please write me using the contact form. I will get back to you as soon as possible.

Ludmila Lebedev
Sales Team Germanedge

Quick Search. Find more, search less.
Top results
Show all results
No results