Early fault diagnosis based on reinforcement learning optimized-SVM model with vibration-monitored signals

Abstract

Effective fault diagnosis maximizes economic benefits by ensuring the stability of machinery systems. Detecting the faults of the key components in machinery, such as rolling bearings, at an early stage, helps to avoid accidents to optimize the maintenance efficiency. It is well known that faulty bearings always deliver a message through their abnormal vibration variation, which can be captured by vibration acceleration sensors in order to facilitate the deteriorating status assessment. However, a clue for an early fault is so ambiguous and sometimes masked by ambient noise, which makes the early fault diagnosis a challenging problem. To tackle the problem, we propose a vibration signal-based data-driven early fault diagnosis approach based on the reinforcement learning (RL) optimized support vector machine (SVM) model. The exploration of the hyperparameter optimization using RL to improve SVM performance motivates this research. Firstly, the corresponding features in the time domain, frequency domain and time-frequency domain are extracted from the obtained vibration signals of the key components under certain working conditions. Subsequently, to better recognize the pattern of an early fault, linear discriminant analysis (LDA) is employed in fuzing the multi-domain early fault features. Finally, the fused features are fed into the RL optimized-SVM model for fault diagnosis. Experimental validation was performed with a public dataset of rolling bearings, and the results confirmed the effectiveness and superiority of the approach compared with other methods.

Keywords:

• Early fault diagnosis
• linear discriminant analysis
• reinforcement learning
• SVM
• vibration signals

Author statement

The authors confirm that there is no conflict of interest in the manuscript.

Additional information

Funding

The work was supported in part by the National Natural Science Foundation of China (NSFC) under grant No. 72101194 and in part by the Humanities and Social Science Foundation of Ministry of Education of China Grant No. 20YJC630096 and the National Key R&D Program of China (Project No. 2022YFE0125200), as well as supported by Laboratory of Science and Technology on Marine Navigation and Control, China State Shipbuilding Corporation (2022010301).

Notes on contributors

Wenqin Zhao

Wenqin Zhao received the B.eng degree in Logistics Engineering from Wuhan University of Technology, Wuhan, China, in 2020. She is now pursuing her master degree with the School of Transportation and Logistics Engineering, Wuhan University of Technology, Wuhan. Her research interests include equipment health monitoring, fault diagnosis, and remaining useful life prediction.

Yaqiong Lv

Yaqiong LV received the B.Eng. degree in industrial engineering from Huazhong University of Science and Technology, Wuhan, China, 2008. the Ph.D. degree in system engineering and engineering management, School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, 2013. She is currently an Associate Professor with school of Transportation and Logistics engineering, Wuhan University of Technology. Her research interests include system reliability/resilience analysis, big data analytics, and intelligent scheduling.

Jialun Liu

Jianlun Liu received the M.S. in traffic information engineering and control from Wuhan University of Technology, Wuhan, China, in 2013. Then he received a Ph.D. degree in Ship Design, Production and Operation from Delft University of Technology, Delft, The Netherlands in 2017. He is currently working at the Intelligent Transportation Systems Research Center, Wuhan University of Technology as an associate professor. His research interest is the motion control and functional testing of smart ships.

Carman K. M. Lee

Carman K. M. Lee is currently an associate professor in the Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong. Prior to her current appointment in Hong Kong, Dr. Lee served as Assistant Professor of School of Mechanical and Aerospace Engineering in Nanyang Technological University, Singapore. She obtained her PhD and B. Eng degree from The Hong Kong Polytechnic University. She was awarded Bronze Award of 16th China National Invention Exhibition Award in 2006 and Outstanding Professional Service and Innovation Award, The Hong Kong Polytechnic University in 2006. Dr Lee has authored or coauthored more than 100 journal and conferences papers. Her current research areas include logistics information management, manufacturing information systems, product development and data mining techniques.

Lei Tu

Lei Tu received the B.Eng. degree in Electronics and Information Engineering from Huazhong University of Science and Technology, Wuhan, China, 2008. the Ph.D. degree in Electrical Engineering, School of Electrical & Electronics Engineering, Nanyang Technological University, Singapore, 2016. He is currently R&D director of Hangzhou Huier Hearing Instrument & Technique Co.,Ltd. And Associate Dean of Hangzhou Ren-ai Hearing Rehabilitation Research Center, China. His research interests include Audio Signal Processing, Artificial Intelligence and Deep Learning.