Academic Journal of Engineering and Technology Science, 2022, 5(3); doi: 10.25236/AJETS.2022.050302.
College of Computer and Communication, Lanzhou University of Technology, Lanzhou, 730050, China
There is a huge difference in the number of operating samples and failure samples in industrial production. If the diagnostic model is trained through deep learning under an unbalanced data set, it will make the model recognize the faulty samples as normal samples. Aiming at this problem, an adaptive focus loss function mechanism is proposed. It can avoid over-learning large-scale samples during small-batch imbalance training. At the same time, to improve the generalization ability of fault samples, a pre-training data enhancement mechanism is proposed. By using the rolling element bearing fault diagnosis data set, the effectiveness of the two mechanisms is verified. The two mechanisms can not only complete training tasks under unbalanced data and improve generalization ability.
Bearing fault diagnosis, Class imbalance dataset, Adaptive focus loss function, Pre training data enhancement
Jialin Ma. Bearing fault diagnosis under class unbalanced data based on deep learning. Academic Journal of Engineering and Technology Science (2022) Vol. 5, Issue 3: 5-12. https://doi.org/10.25236/AJETS.2022.050302.
 L. Li, Y. Xie, L. Cen, and Z. Zeng, ‘A novel cause analysis approach of grey reasoning Petri net based on matrix operations’, Appl. Intell., 2021, doi: 10.1007/s10489-021-02377-4.
 F. Naseri, E. Schaltz, K. Lu, and E. Farjah, ‘Real-Time Open-Switch Fault Diagnosis in Automotive PMSM Drives Based on Kalman Filter’, IET Power Electron., vol. 13, 2020, doi: 10.1049/iet-pel.2019.1498.
 X. Zhang, C. Li, X.-B. Wang, and H. Wu, ‘A novel fault diagnosis procedure based on improved symplectic geometry mode decomposition and optimized SVM’, Measurement, vol. 173, p. 108644, 2020, doi: 10.1016/j.measurement.2020.108644.
 C. Keleolu, H. Küük, and M. Demetgül, ‘Fault Diagnosis of Bevel Gears Using Neural Pattern Recognition and MLP Neural Network Algorithms’, Int. J. Precis. Eng. Manuf., vol. 21, no. 5, 2020.
 Y. Han, W. Qi, N. Ding, and Z. Geng, ‘Short-Time Wavelet Entropy Integrating Improved LSTM for Fault Diagnosis of Modular Multilevel Converter’, IEEE Trans. Cybern., vol. PP, no. 99, pp. 1–9, 2021.
 Z. Tang, L. Bo, X. Liu, and D. Wei, ‘A semi-supervised transferable LSTM with feature evaluation for fault diagnosis of rotating machinery’, Appl. Intell., pp. 1–15, 2021.
 J. Zhang, B. Xu, Z. Wang, and J. Zhang, ‘An FSK-MBCNN based Method for Compound Fault Diagnosis in Wind Turbine Gearboxes’, Measurement, 2020.
 G. Vashishtha and R. Kumar, ‘Pelton Wheel Bucket Fault Diagnosis Using Improved Shannon Entropy and Expectation Maximization Principal Component Analysis’, J. Vib. Eng. Technol., 2021, doi: 10.1007/s42417-021-00379-7.
 I. Goodfellow, Y. Bengio, A. Courville, and Y. Bengio, Deep learning, vol. 1. MIT press Cambridge, 2016.
 Y. LeCun, Y. Bengio, and G. Hinton, ‘Deep learning’, nature, vol. 521, no. 7553, pp. 436–444, 2015.
 V. N. Ghate and S. V. Dudul, ‘Design of optimal MLP and RBF neural network classifier for fault diagnosis of three phase induction motor’, Int. J. Adv. Mechatron. Syst., vol. 2, no. 3, p. 204, 2010.
 T. Waqar and M. Demetgul, ‘Thermal analysis MLP neural network based fault diagnosis on worm gears’, Measurement, vol. 86, pp. 56–66, 2016.
 M. A. Hui, D. Che, Q. Niu, and S. Xia, ‘Research on Fault Diagnosis of Hoisting Bearing Based on Deep Neural Network’, Comput. Eng. Appl., 2019.
 A. Dibaj, M. M. Ettefagh, R. Hassannejad, and M. B. Ehghaghi, ‘A hybrid fine-tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults’, Expert Syst. Appl., vol. 167, no. January, 2020.
 L. Jing, M. Zhao, P. Li, and X. Xu, ‘A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox’, Measurement, vol. 111, pp. 1–10, 2017.
 X. Li, _J_ Li, C. Zhao, Y. Qu, and D. He, ‘Early Gear Pitting Fault Diagnosis Based on Bi-directional LSTM’, 2019.
 T. Huang, Q. Zhang, X. Tang, S. Zhao, and X. Lu, ‘A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems’, Artif. Intell. Rev., pp. 1–27, 2021.
 D. Wang, Q. Guo, Y. Song, S. Gao, and Y. Li, ‘Application of Multiscale Learning Neural Network Based on CNN in Bearing Fault Diagnosis’, J. Signal Process. Syst. Signal Image Video Technol., vol. 91, no. 10, pp. 1205–1217, 2019.
 Y. Pei, Z. Wang, H. Jiang, and Z. Liu, ‘Fault Diagnosis Method Based on CS-Boosting for Unbalanced Training Data’, J. Vib. Meas. Diagn., 2013.
 Q. Shi and H. Zhang, ‘Fault diagnosis of an autonomous vehicle with an improved SVM algorithm subject to unbalanced datasets’, IEEE Trans. Ind. Electron., vol. PP, no. 99, pp. 1–1, 2020.
 Xu, S. Li, Jiang, Z. An, and T. Yu, ‘A renewable fusion fault diagnosis network for the variable speed conditions under unbalanced samples’, Neurocomputing, vol. 379, 2019.
 E. Levent, I. Turker, and K. Serkan, ‘A Generic Intelligent Bearing Fault Diagnosis System Using Compact Adaptive 1D CNN Classifier’, J. Signal Process. Syst., 2018.
 H. Wu, S. Luo, H. Lin, D. Shuangda, Y. Guan, and J. Rojas, Recovering from External Disturbances in Online Manipulation through State-Dependent Revertive Recovery Policies. 2018. doi: 10.1109/ROMAN.2018.8525771.
 W. Smith and R. B. Randall, ‘Rolling Element Bearing Diagnostics Using the Case Western Reserve University Data: A Benchmark Study’, Mech. Syst. Signal Process., vol. 64–65, 2015, doi: 10.1016/j.ymssp.2015.04.021.
 J. Cao, J. Ma, D. Huang, and P. Yu, ‘Finding the optimal multilayer network structure through reinforcement learning in fault diagnosis’, Measurement, p. 110377, 2021, doi: https://doi.org/10.1016/j.measurement.2021.110377.