Intelligent Fault Diagnosis for Planetary Gearbox Using Time-Frequency Representation and Deep Reinforcement Learning

• Published in: IEEE/ASME transactions on mechatronics Vol. 27; no. 2; pp. 985 - 998
• Main Authors: Wang, Hui, Xu, Jiawen, Sun, Chuang, Yan, Ruqiang, Chen, Xuefeng
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-04-2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Classification; Classification policy; Decision making; Deep learning; deep learning (DL); deep reinforcement learning (DRL); Fault detection; Fault diagnosis; Feature extraction; Games; Gearboxes; Knowledge acquisition; Machine learning; Markov processes; Mechanical drives; Mechatronics; planetary gearbox; Representations; Signal processing; Time-frequency analysis; Vibrations
• ISSN: 1083-4435; 1941-014X
• DOI: 10.1109/TMECH.2021.3076775

Accurately and intelligently identifying faults of the planetary gearbox is essential in the safe and reliable operation and maintenance of the mechanical drive system. Recently, fault diagnosis of planetary gearbox has acquired tremendous progress, especially with the rising popularity of deep learning (DL). However, most methods are standard supervised learning where the input is directly mapped to a fault type, and with strong feedback. Also, their learning ways are static and unlike human learning that gradually acquires knowledge by interaction with the environment. To a certain extent, these deficiencies reduce the generalization and intelligence level of DL-based fault diagnosis methods. Besides, due to harsh working conditions, signals acquired often have strong noise and nonlinear features, leading to relatively low accuracy if raw signals are used as the input directly. Thus, this article proposes a new fault diagnosis method based on time-frequency representation and deep reinforcement learning (DRL). We first define fault diagnosis as a sequential decision-making problem in the classification Markov decision process. Next, the vibration signals are converted to uniform-sized TF maps by synchro-extracting transform to enhance the robustness of feature representation. Finally, a diagnosis agent is built and trained in the framework of DRL to learn the optimal classification policy automatically. Experimental results show that this method not only achieves better generalization and stability with an overall accuracy of over 99.5% in single-speed load cases but also outperforms others in multiwork conditions.