Improved fault location method for AT traction power network based on EMU load test

Abstract

The autotransformer (AT) neutral current ratio method is widely used for fault location in the AT traction power network. With the development of high-speed electrified railways, a large number of data show that the relation between the AT neutral current ratio and the distance from the beginning of the fault AT section to the fault point (Q–L relation) is mostly nonlinear. Therefore, the linear Q–L relation in the traditional fault location method always leads to large errors. To solve this problem, a large number of load-related current data that can be used to describe the Q–L relation are obtained through the load test of the electric multiple unit (EMU). Thus, an improved fault location method based on the back propagation (BP) neural network is proposed in this paper. On this basis, a comparison between the improved method and the traditional method shows that the maximum absolute error and the average absolute error of the improved method are 0.651 km and 0.334 km lower than those of the traditional method, respectively, which demonstrates that the improved method can effectively eliminate the influence of nonlinear factors and greatly improve the accuracy of fault location for the AT traction power network. Finally, combined with a short-circuit test, the accuracy of the improved method is verified.

Keywords

Fault location / EMU load test / BP neural network / AT traction power network / High-speed electrified railway

References

[1.] Zhou Y Xu G Chen Y. Fault location in power electrical traction line system. Energies, 2012 5 12 5002-5018

[2.] Xu G Zhou Y Chen Y. Model-based fault location with frequency domain for power traction system. Energies, 2013 6 7 3097-3114

[3.] Han Z Li S Liu S Gao S. A reactance-based fault location method for overhead lines of ac electrified railway. IEEE Trans Power Deliv, 2020 35 5 2558-2560

[4.] Lin G (2010) Study on novel protection and location schemes for traction power supply system. Dissertation, Southwest Jiaotong University (in Chinese)

[5.] Guo M Lin G Chen X. Fault locator of all-paralleling at traction power supply based on the theory of the current ratio of paralleling lines. Relay, 2006 34 22 36-39

[6.] Xiong L Wu G Wang Z. Study on fault location of multi measuring points traveling wave method based on IHHT in all parallel AT traction network. Trans China Electrotech Soc, 2019 35 3244-3252

[7.] Jiao Z Gao S. Study on the feasibility of using traveling wave in the fault location in the overhead contact network of electrified railway traction. Relay, 2003 07 33-36

[8.] Lu T Han Z Wang J. Fault location method for all-parallel autotransformer feeding systems. Proc CSU-EPSA, 2006 2 27-30

[9.] Lin G, Li Q (2010) Impedance calculations for AT power traction networks with parallel connections. In: 2010 Asia-Pacific Power and Energy Engineering Conference, Chengdu

[10.] Li G, Lin G (2012) Short circuit impedance analysis for novel AT power traction network. In: 2012 Asia-Pacific Power and Energy Engineering Conference, Chengdu

[11.] Wang C Yin X. Comprehensive revisions on fault-location algorithm suitable for dedicated passenger line of high-speed electrified railway. IEEE Trans Power Deliv, 2012 27 4 2415-2417

[12.] Serrano J Platero CA López-Toledo M Granizo R. A novel ground fault identification method for 2 $\times $ 5 kv railway power supply systems. Energies, 2015 8 7 7020-7039

[13.] Lin G Quan W Tong X. Fault location scheme for over-zone feeding operation condition on high-speed railway. J Electr Eng Technol, 2021 17 1459-1467

[14.] Cho G-J Kim C-H Kim M-S Kim D-H Heo S-H Kim H-D Min M-H An T-P. A novel fault-location algorithm for ac parallel autotransformer feeding system. IEEE Trans Power Deliv, 2019 34 2 475-485

[15.] Serrano J Platero C López-Toledo M Granizo R. A new method of ground fault location in 2 $\times $ 25 kV railway power supply systems. Energies, 2017 10 3 340

[16.] Platero CA Serrano J Guerrero JM Fernández-Horcajuelo A. Ground fault location in 2 $\times $ 25 kV high-speed train power systems by (auto)transformers currents ratio. IEEE Trans Power Deliv, 2021 36 5 3065-3073

[17.] Wang S Chen M Li Q Kou Z. A unified fault-location method of autotransformer traction network for high-speed railway. IEEE Trans Power Deliv, 2021 36 6 3925-3936

[18.] Chih-Ju C Ying-Tung H Jhane-Li W Yaw-Tzong H. Distribution of earth leakage currents in railway systems with drain auto-transformers. IEEE Trans Power Deliv, 2001 16 2 271-275

[19.] Chou C-J, Hsiao Y-T, Hsu C-C et al (1999) Distribution of earth leakage currents in railway systems with drain auto-transformers. In: 1999 IEEE Transmission and Distribution Conference, New Orleans

[20.] Wang J (2006) Research on fault location of all-parallel at traction system. Dissertation, Southwest Jiaotong University (in Chinese)

[21.] Yu G. Check distance measurement accuracy of at suck current ratio with locomotive load current. J Railw Eng Soc, 2014 31 07 95-98

[22.] Miu B Li R Ai G. Research and modification on fault location method for traction power supply system in high speed railway. Electr Railw, 2019 30 01 20-23

[23.] Mohanpurkar M Suryanarayanan S. Regression modeling for accommodating unscheduled flows in electric grids. IEEE Trans Power Syst, 2014 29 5 2569-2570

[24.] Zhengyou H Shibin G Xiaoqin C Jun Z Zhiqian B Qingquan Q. Study of a new method for power system transients classification based on wavelet entropy and neural network. Int J Electr Power Energy Syst, 2011 33 3 402-410

[25.] Chen B Wang Y. Short-term electric load forecasting of integrated energy system considering nonlinear synergy between different loads. IEEE Access, 2021 9 43562-43573

[26.] Zhou Z. Machine learning, 2016 Bei Jing Tsinghua University Press

[27.] Yao Z, Pan F, Shen Y, Wu J, Yu X (2015) Short-term prediction of photovoltaic power generation output based on GA-BP and POS-BP neural network. Power Syst Prot Control 43(20):83–89 (in Chinese)

[28.] Chen M. Principles and examples of MATLAB neural network, 2013 Bei Jing Tsinghua University Press

[29.] Yan Z Fan X Zhao W Xu X Fan J Wang Y. Improving the convergence of power flow calculation by a self-adaptive Levenberg–Marquardt method. Proc CSEE, 2015 35 8 1909-1918

[30.] Wang Y Wu C Zhou D Li Z-H . A survey of fault diagnosis for PV array based on BP neural network. Power Syst Prot Control, 2013 41 16 108-114

Funding

National Key Research and Development Program of China(2021YFB2601500)