Contrastive feature-based learning-guided elevated deep reinforcement learning: Developing an imbalanced fault quantitative diagnosis under variable working conditions

• Published in: Mechanical systems and signal processing Vol. 211; p. 111192
• Main Authors: He, Shuilong, Cui, Qianwen, Chen, Jinglong, Pan, Tongyang, Hu, Chaofan
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2024
• Subjects: Class imbalance; Contrastive Learning; Dueling Double Deep Q Network (D3QN); Fault quantitative diagnosis; Prioritized experience replay; Contrastive Learning; Fault quantitative diagnosis; Dueling Double Deep Q Network (D3QN); Class imbalance; Prioritized experience replay
• ISSN: 0888-3270; 1096-1216
• DOI: 10.1016/j.ymssp.2024.111192

Fault diagnosis is subject to the challenge of implementing model learning in the presence of small samples and imbalanced data (i.e., variable operating conditions), which is a fundamental and crucial problem that hinders their applications in real industrial scenarios. Herein, a novel deep reinfor...