Positive-Unlabeled Learning-Based Hybrid Deep Network for Intelligent Fault Detection

• Published in: IEEE transactions on industrial informatics Vol. 18; no. 7; pp. 4510 - 4519
• Main Authors: Qian, Min, Li, Yan-Fu, Han, Te
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.07.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Clustering; Deep learning; Fault detection; Feature extraction; Hybrid systems; Informatics; Labels; Machine learning; Modules; Optimization; positive-unlabeled (PU) learning; Supervised learning; Training; wind turbine; Wind turbines

Intelligent fault detection methods based on deep learning have been developed rapidly in recent years. However, most of these methods are based on supervised learning which requires a fully labeled training set. It is difficult to obtain massive labeled samples in real applications incredibly accur...