Scalable anomaly detection in manufacturing systems using an interpretable deep learning approach

摘要

Anomaly detection in manufacturing systems has great potential for the prevention of critical quality faults. In recent years, unsupervised deep learning has shown to frequently outperform conventional methods for anomaly detection. However, tuning, deploying and debugging deep learning models is a time-consuming task, limiting their practical applicability in manufacturing systems. We approach this problem by developing a deep learning model that learns interpretable shapes that can be used for anomaly detection in temporal process data. Application of the model to assembly tightening processes in the automotive industry shows a significant improvement in model interpretability and scalability.