Keywords
Bearing failure
Diagnostic methods
Submitted : 2025-01-19
Accepted : 2025-02-03
Published : 2025-02-18
Abstract
Bearing is an indispensable key component in mechanical equipment, and its working state is directly related to the stability and safety of the whole equipment. In recent years, with the rapid development of artificial intelligence technology, especially the breakthrough of deep learning technology, it provides a new idea for bearing fault diagnosis. Deep learning can automatically learn features from a large amount of data, has a strong nonlinear modeling ability, and can effectively solve the problems existing in traditional methods. Aiming at the key problems in bearing fault diagnosis, this paper studies the fault diagnosis method based on deep learning, which not only provides a new solution for bearing fault diagnosis but also provides a reference for the application of deep learning in other mechanical fault diagnosis fields.
References
Ren H, Qu J, Chai Y, et al., 2017, Research Status and Challenges of Deep Learning in Fault Diagnosis. Control and Decision, 2017(8): 1345–1358.
Hu N, Chen HP, Cheng Z, et al., 2019, Fault Diagnosis Method of Planetary Gearbox Based on Empirical Mode Decomposition and Deep Convolutional Neural Network. Chinese Journal of Mechanical Engineering, 2019(7): 9–18.
Li M, Li J, Liu Y, 2023, Application of CEEMDAN-TFPF Noise Reduction Method Based on Autocorrelation in Gear Fault Diagnosis. Science of Digital Manufacturing, 2023(3): 199–204.
Yan B, Li X, 2023, Research on Ultrasonic Location System and Algorithm for Cracks in Stone Relics. Chinese Journal of Scientific Instrument, 2023(8): 155–163.
Kang S, Yang J, Wang Y, et al., 2023, Fault Diagnosis Method of Rolling Bearing Under Different Working Conditions Based on Federated Multiple Representation Domain Adaptation. Chinese Journal of Scientific Instrument, 2023(6): 165–176.
Song Z, Xu L, Hu X, et al., 2021, Research on Axle Box Bearing Fault Diagnosis Method of EMU Based on Improved Shapelets Algorithm. Chinese Journal of Scientific Instrument, 2021(2): 66–74.
Chen R, Zhang Y, Yang L, et al., 2020, Health State Evaluation of Harmonic Retarder Based on Whole Cycle Data and Convolutional Neural Network. Chinese Journal of Scientific Instrument, 2020(2): 245–252.
Gong W, Chen H, Zhang M, et al., 2020, Intelligent Diagnosis Method of Motor Bearing Minor Fault Based on Deep Learning. Chinese Journal of Scientific Instrument, 2020(1): 195–205.
Dong X, Guo L, Gao H, et al., 2019, Cost Sensitive Convolutional Neural Networks: An Unbalanced Classification Method for Mechanical Fault Data. Chinese Journal of Scientific Instrument, 2019(12): 205–213.
Wen Z, Chen J, Liu L, et al., 2022, Fault Diagnosis of Wind Power Gearbox Based on Wavelet Transform and Optimal CNN. Journal of Zhejiang University (Engineering and Technology), 2022(6): 1212–1219.
Meng Z, Guan Y, Pan Z, et al., 2021, Research on Fault Diagnosis of Rolling Bearing Based on Secondary Data Enhancement and Deep Convolution. Chinese Journal of Mechanical Engineering, 2021(23): 106–115.
Xin R, Miao F, Wang T, et al., 2022, Intelligent Fault Diagnosis of Mechanical Bearing Based on Deep Learning. Journal of Jilin University of Chemical Technology, 2022(11): 25–29.
Xu Y, 2020, Deep Learning Algorithm for Working State Detection of Electromechanical Equipment. Electronic Measurement Technology, 2020(11): 34–38.
Li C, Wu Y, Yang S, 2023, Research Progress of Data-Driven Fault Diagnosis with Unbalanced Distribution. Chinese Journal of Scientific Instrument, 2023(8): 181–197.
Hu Y, Liu S, Li Q, et al., 2019, Fault Diagnosis of Rolling Bearing Based on EMD Amplitude Entropy and Support Vector Machine. Mechanical Research and Application, 2019(2): 166–169.