Use Cases  •  Transport

Wear prediction for automotive parts: use cases

Context

The device under analysis consists of a moving part with a rubber element cleaning a fixed part.

The rubber element bears all the friction and is subject to wear after each movement.
As the level of wear increases, the quality of the cleaning process deteriorates.

Need

The customer wanted to automatically measure the wear of the rubber element, in order to display its wear level to the driver and help plan its replacement.

Solution

DiagFit was used to build a wear indicator based on acceleration data captured from the moving part and by rubber type. The wear indicator was obtained by using data from devices with a new rubber part, learning normal behavior and then detecting devices with wear conditions. The wear indicator can be further refined using historical data for new and old rubber parts.

Results

Using available data, including acceleration data for different parts and rubber types, DiagFit was able to classify worn parts with a 99.3% true-positive rate and 2.8% false-positive rate. 50% of the data was used to train the model.

Confusion matric and Roc Curve

Latest use cases