Grounding Fault Diagnosis of Running Rails Based on a Multi-scale One-Dimensional Convolutional Neural Network in a DC Subway System

Abstract

Running rails are the return conductors of the traction current in DC subway systems, which should be insulated from the earth. Due to the large length of the line, as well as the humidity and metal dust in the tunnel, grounding fault of the running rails usually occurs, which will increase stray current (SC) leakage and endanger power supply safety. In this paper, a method of grounding fault diagnosis of running rails based on a multi-scale one-dimensional convolutional neural network (MS-1DCNN) is proposed. Firstly, a platform for the dynamic distribution of SC and rail potential (RP) with grounding faults existing in the running rails is established, which generates the dynamic RP data with various grounding faults. Secondly, a grounding fault diagnostic method of running rails based on MS-1DCNN is proposed, so as to realize the effective identification of ground fault types in subway systems. Thirdly, with the proposed diagnostic method, the datasets under two operating conditions of a single train and two trains are tested; a comparison test between MS-1DCNN and the 1D convolutional neural network (1DCNN) is carried out, and the effectiveness of the proposed method is verified. Results demonstrate that the proposed model can significantly improve the ground fault diagnostic accuracy of running rails. The dynamic RP simulation platform for trains established in this paper lays a theoretical foundation for the grounding fault research of running rail. Moreover, the deep learning method is proposed for the first time to diagnose the grounding fault of running rail, and the high diagnostic accuracy is obtained, which is of great significance for the safe and stable operation of the subway line.

Keywords

DC subway system / Ground fault diagnosis / Dynamic rail potential / MS-1DCNN

References

[1] Wang M, Yang XF, Zheng TQ, Ni MH. DC autotransformer-based traction power supply for urban transit rail potential and stray current mitigation. IEEE Trans Transp Electr, 2020, 6: 762-773

[2] Wang YD, Zhang G, Qiu RC, Liu ZG, Yao N. Distribution correction model of urban rail return system considering rail skin effect. IEEE Trans Transp Electrif, 2021, 7: 883-891

[3] Charalambous CA. Comprehensive modeling to allow informed calculation of DC traction systems’ stray current levels. IEEE Trans Veh Technol, 2017, 66: 9667-9677

[4] Jan S, Machczynski W, Budnik K. Modeling effects of stochastic stray currents from D.C. traction on corrosion hazard of buried pipelines. Energie, 2019, 12: 4524-4570

[5] Lin S, Yang HF, Zhou Q, Wang A. Evaluation and analysis model of stray current in the metro depot. IEEE Trans Transp Electrif, 2021, 7: 1780-1794

[6] Wang CT, Li W, Wang YQ, Xu SY, Fan MB. Stray current distributing model in the subway system: a review and outlook. Int J Electrochem Sci, 2018, 13: 1700-1727

[7] Enrico P, Riccardo T, Pietro C. Fault current detection and dangerous voltages in DC urban rail traction systems. IEEE Trans Ind Appl, 2017, 53: 4109-4115

[8] Jose MG, Daniel SJ, Kumar M, Carlos A. A ground fault location method for DC systems through multiple grounding connections. IEEE Trans Ind Appl, 2022, 58: 7022-7033

[9] Park JD. Ground fault detection and location for ungrounded DC traction power systems. IEEE Trans Veh Technol, 2015, 64: 5667-5676

[10] Li CY, Aniruddha MG, Zhao CY. A fast DC fault detection method using DC reactor voltages in HVdc grids. IEEE Trans Power Deliv, 2018, 33: 2254-2264

[11] Ricardo G, Jose G, Femando A, Carlos P. Ground fault directional protection method for HVDC multiterminal networks. IEEE Trans Ind Appl, 2022, 58: 1573-1580

[12] Leng Y, Wang ZQ, Yang HG. A novel approach based on EEMD sample entropy to fault current identification in DC traction network. Int Trans Electr Energy Syst, 2017, 27: e2371-e2379

[13] Du WL, Hu PJ, Wang HC, Gong XY, Wang SY. Fault diagnosis of rotating machinery based on 1D–2d joint convolution neural network. IEEE Trans Industr Electron, 2023, 70: 5277-5285

[14] Zhao GQ, Liu XY, Zhang B. A novel approach for analog circuit fault diagnosis based on deep belief network. Measurement, 2018, 121: 170-178

[15] Li GQ, Wu J, Deng C, Chen ZY, Shao XY. Convolutional neural network-based Bayesian Gaussian mixture for intelligent fault diagnosis of rotating machinery. IEEE Trans Instrum Meas, 2021, 70: 1-10

[16] Mo ZL, Zhang ZJ, Tsui KL. The variational kernel-based 1-D convolutional neural network for machinery fault diagnosis. IEEE Trans Instrum Meas, 2021, 70: 1-10

[17] Yang ZK, He B, Li G, Lu P, Cheng B, Zhang PP. Multigrained hybrid neural network for rotating machinery fault diagnosis using joint local and global information. IEEE Trans Instrum Meas, 2023, 72: 1-13

[18] Liao GP, Gao W, Yang GJ, Guo MF. Hydroelectric generating unit fault diagnosis using 1-D convolutional neural network and gated recurrent unit in small hydro. IEEE Sens J, 2019, 19: 9352-9363

[19] Gao W, Wai RJ. A novel fault identification method for photovoltaic array via convolutional neural network and residual gated recurrent unit. IEEE Access, 2020, 8: 159493-159510

[20] Yong C. Dynamic monitoring analysis of urban rail transit stray current and the application. Urban Mass Transit, 2020, 23: 166-169

[21] Yang JX, Cheng M, Li LP et al (2018) Railway applications—fixed installations—electrical safety, earthing and the return circuit—part 2: provisions against the effects of stray currents caused by d. c. traction systems. Standardization Administration of China (SAC). pp 1–26. GB/T 28026.2-2018

[22] Xu SY, Li W, Wang YQ. Effects of vehicle running mode on rail potential and stray current in DC mass transit systems. IEEE Trans Veh Technol, 2013, 62: 3569-3580

[23] Xiao S, Lai XN, Meng J et al (2021) A lightweight ground return device for rail transit grounded third rails. Southwest Jiaotong University. pp 1–9. CN202010046282.4

[24] Du GF, Wang J, Jiang XX, Zhang DL Evaluation of rail potential and stray current with dynamic traction networks in multitrain subway systems. IEEE Trans Transp Electrif, 2020, 6: 784-796

[25] Lu Q, Qi F, Chen Z et al (2022) A dynamic simulation method of return parameters with train grounding. CRRC NANJING PUZHEN CO. LTD. pp 1–13. CN202210206129.2

[26] Rodriguez JV, Feito JS. Calculation of remote effects of stray currents on rail voltages in DC railways systems. IET Electr Syst Transp, 2013, 3: 31-40

[27] Liu W, Li T, Zheng J, Pan WG, Yin YC. Evaluation of the effect of stray current collection system in DC-electrified railway system. IEEE Trans Veh Technol, 2021, 70: 6542-6553

[28] Gu JD, Yang XF, Zheng TQ, Xia X, Zhao ZJ, Chen ML. Rail potential and stray current mitigation for urban rail transit with multiple trains under multiple conditions. IEEE Trans Transp Electrif, 2022, 8: 1684-1694

Funding

National Natural Science Foundation of China(52007128)

Natural Science Foundation of the Jiangsu Higher Education Institution of China(22KJD510011)