Generalized autoencoder-based fault detection method for traction systems with performance degradation

Abstract

Fault diagnosis of traction systems is important for the safety operation of high-speed trains. Long-term operation of the trains will degrade the performance of systems, which decreases the fault detection accuracy. To solve this problem, this paper proposes a fault detection method developed by a Generalized Autoencoder (GAE) for systems with performance degradation. The advantage of this method is that it can accurately detect faults when the traction system of high-speed trains is affected by performance degradation. Regardless of the probability distribution, it can handle any data, and the GAE has extremely high sensitivity in anomaly detection. Finally, the effectiveness of this method is verified through the Traction Drive Control System (TDCS) platform. At different performance degradation levels, our method’s experimental results are superior to traditional methods.

Keywords

Performance degradation / Generalized autoencoder / Fault detection / Traction control systems / High-speed trains

Declaration of Competing Interest

The authors declare that they have no conflicts of interest.

Acknowledgements

This work was supported by the National Natural Science Foundation of China (Grant Nos. U20A20186 and 62372063).

References

[1] S.S. Chopade, P.K. Sharma. High-speed trains. Int. J. Mod. Eng. Res., 3(2)(2013), pp. 1161-1166.

[2] H. Chen, B. Jiang, S.X. Ding, et al., Data-driven fault diagnosis for traction systems in high-speed trains: a survey, challenges, and perspectives. IEEE Trans. Intel. Transp. Syst., 23(3)(2020), pp. 1700-1716.

[3] H. Chen, B. Jiang. A review of fault detection and diagnosis for the traction system in high-speed trains. IEEE Trans. Intel. Transp. Syst., 21(2)(2019), pp. 450-465.

[4] Z. Chen, S.X. Ding, T. Peng, et al., Fault detection for non-Gaussian processes using generalized canonical correlation analysis and randomized algorithms. IEEE Trans. Ind. Electron., 65(2)(2017), pp. 1559-1567.

[5] H. Chen, B. Jiang, N. Lu, et al., Multi-mode kernel principal component analysis-based incipient fault detection for pulse width modulated inverter of China railway high-speed 5. Adv. Mech. Eng., 9(10)(2017), pp. 1-12.

[6] C. Yang, C. Yang, T. Peng, et al., A fault-injection strategy for traction drive control systems. IEEE Trans. Ind. Electron., 64(7)(2017), pp. 5719-5727.

[7] J. Feng, J. Xu, W. Liao, et al., Review on the traction system sensor technology of a rail transit train. Sensors, 17(6)(2017), p. 1535.

[8] H. Chen, B. Jiang, N. Lu. Data-driven incipient sensor fault estimation with application in inverter of high-speed railway. Math. Probl. Eng. (2017), pp. 1-13.

[9] D. Feng, S. Lin, Z. He, et al., A technical framework of PHM and active maintenance for modern high-speed railway traction power supply systems. Int. J. Rail Transp., 5(3)(2017), pp. 145-169.

[10] S. Yin, S.X. Ding, X. Xie, et al., A review on basic data-driven approaches for industrial process monitoring. IEEE Trans. Ind. Elec., 61(11)(2014), pp. 6418-6428.

[11] B. Gou, X. Ge, Y. Liu, et al., Load-current-based current sensor fault diagnosis and tolerant control scheme for traction inverters. Electron. Lett., 52(20)(2016), pp. 1717-1719.

[12] J. Liu, Y.F. Li, E. Zio. A SVM framework for fault detection of the braking system in a high-speed train. Mech. Syst. Signal Proc., 87 (2017), pp. 401-409.

[13] J.F. Martins, V.F. Pires, A.J. Pires. PCA-based on-line diagnosis of induction motor stator fault feed by PWM inverter. IEEE Int. Symp. Ind. Electron., 3 (2006), pp. 2401-2405.

[14] H. Chen, B. Jiang, N. Lu, et al., Deep PCA based real-time incipient fault detection and diagnosis methodology for electrical drive in high-speed trains. IEEE Trans. Veh. Technol., 67(6)(2018), pp. 4819-4830.

[15] H. Chen, B. Jiang, N. Lu, et al., Real-time incipient fault detection for electrical traction systems of CRH2. Neurocomputing, 306 (2018), pp. 119-129.

[16] H. Chen, Z. Chai, B. Jiang, et al., Data-driven fault detection for dynamic systems with performance degradation: a unified transfer learning framework. IEEE Trans. Instrum. Meas., 70 (2021), pp. 1-12.

[17] T. Chen, X. Liu, B. Xia, et al., Unsupervised anomaly detection of industrial robots using a sliding-window convolutional variational autoencoder. IEEE Access, (2020), pp. 47072-47081.

[18] H. Wang, J. Xu, R. Yan, et al., A new intelligent bearing fault diagnosis method using SDP representation and SECNN. IEEE Trans. Instrum. Meas., 69(5)(2020), pp. 2377-2389.

[19] H. Wang, J. Xu, R. Yan, Bearing fault diagnosis based on visual symmetrized dot pattern and CNNs, IEEE Int. Instrum. Measurem. Technol. Conf. (I2MTC), (2019) 1–6.

[20] W. Wang, Y. Huang, Y. Wang, et al., Generalized autoencoder: a neural network framework for dimensionality reduction. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, (2014) 490–497.