Regularization-based Continual Learning for Anomaly Detection in Discrete Manufacturing
This research addresses the problem of adapting anomaly detection models to changing manufacturing processes for operators, which is an incremental improvement.
This paper investigates regularization-based continual learning methods for anomaly detection in discrete manufacturing, aiming to address the lack of adaptability in current data-driven approaches to changes like new products. The authors implement, evaluate, and compare different regularization strategies using a real industrial metal forming dataset.
The early and robust detection of anomalies occurring in discrete manufacturing processes allows operators to prevent harm, e.g. defects in production machinery or products. While current approaches for data-driven anomaly detection provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to changes, e.g. in products. Continual learning promises such flexibility, allowing for an automatic adaption of previously learnt knowledge to new tasks. Therefore, this article discusses different continual learning approaches from the group of regularization strategies, which are implemented, evaluated and compared based on a real industrial metal forming dataset.