Our Paper on “Contrastive Learning for Fault Detection and Diagnostics in the Context of Changing Operating Conditions and Novel Fault Types” has been published

The emergence of novel faults as well as changing environmental or operating conditions can cause unknown variations in condition monitoring data. This poses a critical challenge to purely data-driven solutions for fault detection and diagnostics: A fault diagnostics model that is not sensitive to novel variation in the data might fail in detecting novel fault types but also misclassify data recorded under unknown operating conditions. And a fault detection model that is sensitive to any kind of variations in the data is prone to raise false alarms if the variation in the data are caused, e.g., by only changing operating conditions. We tackle this challenge in our newest research by applying contrastive learning.

Abstract:

Reliable {fault detection} and diagnostics are crucial in order to ensure efficient operations in industrial assets. Data-driven solutions have shown great potential in various fields but pose many challenges in Prognostics and Health Management (PHM) applications: Changing external in-service factors and operating conditions cause variations in the condition monitoring (CM) data resulting in false alarms. Furthermore, novel types of faults can also cause variations in CM data. Since faults occur rarely in complex safety critical systems, a training dataset typically does not cover all possible fault types. To enable the detection of novel fault types, the models need to be sensitive to novel variations. Simultaneously, to decrease the false alarm rate, invariance to variations in CM data caused by changing {operating conditions} is required. We propose contrastive learning for the task of {fault detection} and diagnostics in the context of changing operating conditions and novel fault types. In particular, we evaluate how a feature representation trained by the triplet loss is suited to {fault detection} and diagnostics under the aforementioned conditions. We showcase that classification and clustering based on the learned feature representations are (1) invariant to changing {operating conditions} while also being (2) suited to the detection of novel fault types. Our evaluation is conducted on the bearing benchmark dataset provided by the Case Western Reserve University (CWRU).

external page Paper