- Reduce warranty claims through enhanced End-of-Line Testing with machine learning
- Accelerate root cause analysis for faulty transmissions
- Training data was drawn from only 100 units, none of which failed EOL tests
- Client required real-time results as part of a new end of line test
Reduced number of signals requiring manual investigation for RCA by
Costs from warranty claims reduced up to
Acerta’s team began by gathering information about the client’s manufacturing and data collection processes, which formed the basis for our intelligent feature engineering. Our resident industry experts identified non-polynomial features as potentially useful based on similarities between this application and past use cases. Acerta’s data scientists conducted a feature reduction, deploying LinePulse to prune out features that had little or no value to the final scoring algorithm.
Using unsupervised ensembled machine learning methods, LinePulse generated an abnormality score for each transmission at the end of the line. The score simultaneously evaluated single signals and multi-signal relationships, along with their expected behavior in each test step, and across several steps. It was calculated using the reconstruction error of different models in the ensemble.
Transmissions from the test dataset were sorted based on their abnormality scores, with LinePulse identifying the “least explainable” portions of the data.
Despite working from a small, unlabelled dataset, LinePulse was able to generate a valid abnormality score for each transmission at the end of the line. The platform uses data from multiple tests simultaneously to identify the signals with the greatest impact on abnormality score.
In one instance, LinePulse identified a causal link between pressure delays and rotation delays. Detecting these specific signal relationships accelerated root cause analysis of transmission issues by reducing the number of signals requiring manual investigation from approximately 4,000 per transmission to ten.
Using Smart Line Analytics, LinePulse was able to conduct multi-signal failure detection, something that was not possible with the client’s existing SPC program. As indicated in the accompanying charts, there was no clear threshold crossed (i.e., no extreme value) that would have triggered an alert from the existing SPC program. However, LinePulse identified these subtle deviations automatically and cross-correlated the abnormal region with other signals from the same transmission unit to ensure a high confidence score on its reporting.
According to the client, the new EOL test deployed via Acerta’s LinePulse platform would save the company up to 30% of the costs from warranty claims.