To address the issues of incomplete, imbalanced, and partially missing condition monitoring data from railway switch machine, a fault diagnosis method of the plunger pump in switch machines with an improved Generative Adversarial Network (GAN) is proposed in this paper. First, a Conditional Deep Convolutional Generative Adversarial Network (C-DCGAN) model is established, with one-dimensional convolutional layers designed to capture the timing and frequency-domain features of the plunger pump vibration signal. The generator and discriminator are optimized through game confrontation mechanism to enhance the model's generalization and fault feature extraction capability. Then, Two Time-scale Update Rule (TTUR) is added to solve the slow learning issue in discriminator regularization, improving the stability of model training. Finally, a case study using measured data provided by the Electrical Equipment Materials Company of a railway bureau is conducted to validate the effectiveness of the method. The results show that the JSD obtained from the generated samples are 0.190, 0.235, 0.240 and 0.185 under the four working conditions. When the normal-to-fault sample ratios are 100∶1, 50∶1, 20∶1 and 10∶1, respectively, the fault classification accuracies reach 91.24%, 94.13%, 94.96% and 96.08%, consecutively. The proposed method achieves better performance in handling imbalanced data, achieving high fault classification accuracy, thereby providing robust support for ensuring the safe operation of railways.
HAMADACHEM, DUTTAS, OLABYO, et al. On the Fault Detection and Diagnosis of Railway Switch and Crossing Systems: an Overview [J]. Applied Sciences, 2019, 9 (23): 5129.
ZHAOPan, WANGXiaomin, FUMeijun. Few-Shot Switch Machine Fault Diagnosis Based on Bayesian Meta-Learning [J]. Journal of Railway Science and Engineering, 2023, 20 (10): 4008-4020. in Chinese
[4]
ZHANGT C, CHENJ L, LIF D, et al. Intelligent Fault Diagnosis of Machines with Small & Imbalanced Data: a State-of-the-Art Review and Possible Extensions [J]. ISA Transactions, 2022, 119: 152-171.
[5]
GOODFELLOWI J, POUGET-ABADIEJ, MIRZAM, et al. Generative Adversarial Nets [J]. Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014, 2: 2672-2680.
GUOXu, LUOYongpeng, WANGLinkun, et al. Fault Self-Diagnosis of Structural Vibration Monitoring Sensor and Monitoring Data Recovery Based on CNN and DCGAN [J]. Journal of Railway Science and Engineering, 2022, 19 (11): 3383-3395. in Chinese
LIDongdong, LIUYuhang, ZHAOYang, et al. Fault Diagnosis Method of Wind Turbine Planetary Gearbox Based on Improved Generative Adversarial Network [J]. Proceedings of the CSEE, 2021, 41 (21): 7496-7507. in Chinese
YANGQing, LUJianguang, TANGXianghong, et al. Bearing Small Sample Fault Diagnosis Based on infoGAN and CNN [J]. Journal of Ordnance Equipment Engineering, 2021, 42 (11): 235-240. in Chinese
GUOJunfeng, WANGMiaosheng, SUNLei, et al. New Method of Fault Diagnosis for Rolling Bearing Imbalance Data Set Based on Generative Adversarial Network [J]. Computer Integrated Manufacturing Systems, 2022, 28 (9): 2825-2835. in Chinese
ZHANGYonghong, ZHANGZhongyang, ZHAOXiaoping, et al. Bearing Fault Diagnosis Method Based on VAE - GAN and FLCNN Unbalanced Samples [J]. Journal of Vibration and Shock, 2022, 41 (9): 199-209. in Chinese
LUOJia, HUANGJinying, MAJiancheng. Stability Training Method of C‑DCGAN in Mechanical Fault Diagnosis Based on TTUR [J]. Journal of Vibration, Measurement & Diagnosis, 2022, 42 (4): 733-740, 827. in Chinese
[18]
SPRINGENBERGJ T. Unsupervised and Semi-Supervised Learning with Categorical Generative Adversarial Networks [EB/OL]. 2015: arXiv:1511.06390.
[19]
SHAOS Y, WANGP, YANR Q. Generative Adversarial Networks for Data Augmentation in Machine Fault Diagnosis [J]. Computers in Industry, 2019, 106 (4): 85-93.
LUOJ, VONGC M, WONGP K. Sparse Bayesian Extreme Learning Machine for Multi-Classification [J]. IEEE Transactions on Neural Networks & Learning Systems, 2017, 25 (4): 836-843.
[26]
HONGJ S. Microstrip Filters for RF/Microwave Applications [J]. IEEE Microwave Magazine, 2002, 3 (3): 62-65.
[27]
DINUZZOF, ONGC S, GEHLERP V, et al. Learning Output Kernels with Block Coordinate Descent [J]. Proceedings of the 28th International Conference on Machine Learning, 2011: 49-56.
[28]
MAOW T, TIANM, YANG R. Research of Load Identification Based on Multiple-Input Multiple-Output SVM Model Selection [J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2012, 226 (5): 1395-1409.
[29]
SHAOH D, JIANGH K, ZHANGH Z, et al. Rolling Bearing Fault Feature Learning Using Improved Convolutional Deep Belief Network with Compressed Sensing [J]. Mechanical Systems and Signal Processing, 2018, 100 (2): 743-765.
[30]
LUC, WANGZ Y, QINW L, et al. Fault Diagnosis of Rotary Machinery Components Using a Stacked Denoising Autoencoder-Based Health State Identification [J]. Signal Process, 2017, 130 (1): 377-388.