Fault diagnosis of high-voltage pulse track circuit 2 based on IHHO-KELM

Yunshui  Zheng; Yuefan  Zhang

doi:10.6180/jase.202407_27(7).0002

Fault diagnosis of high-voltage pulse track circuit 2 based on IHHO-KELM

Yunshui Zheng and Yuefan ZhangThis email address is being protected from spambots. You need JavaScript enabled to view it.

School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China

Received: October 25, 2022
Accepted: May 25, 2023
Publication Date: November 4, 2023

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202407_27(7).0002

Aiming at the problem of low fault diagnosis accuracy of high-voltage pulse track circuit, a track circuit fault diagnosis method based on kernel extreme learning machine (KELM) optimized by improved Harris hawks optimization (IHHO) is proposed. Firstly, in order to improve the optimization performance, the logarithmic convergence factor is used in combination with the symbiotic organisms search (SOS) algorithm to improve the basic Harris hawks optimization (HHO) algorithm. The benchmark test function is used for the experiment, which proves that the IHHO algorithm performs better in convergence accuracy and convergence speed. Secondly, the IHHO algorithm is used to optimize the kernel function parameter and penalty coefficient of the KELM model and then improves the fault diagnosis accuracy of the KELM model. Finally, the IHHO-KELM model is used to diagnose fault types of the high-voltage pulse track circuit. The experimental results show that the diagnostic accuracy of the proposed IHHO-KELM model is 93.3%, which is 6.6%, 5%, and 3.3% higher than that of the KELM model, GA (Genetic algorithm)-KELM model, and HHO-KELM model respectively. Further experiments verify that the IHHO-KELM model is superior to BP neural network, deep confidence network (DBN), long short-term memory (LSTM) network, and gated recurrent unit (GRU) network in terms of diagnostic accuracy, training time, and diagnostic mean square error, which proves the rapidity and stability of the IHHO-KELM model in track circuit fault diagnosis.

Keywords: Harris hawks optimization; Kernel extreme learning machine; High-voltage pulse track circuit; Fault diagnosis

[1] Y. Xing, J. Wang, G. Shang, C. Peng, and L. Zhu, (2022) “Fault diagnosis method of track circuit for massive unbalanced data" China Safety Science Journal 32(5): 112–118. DOI: 10.16265/j.cnki.issn1003-3033.2022.05.2389.
[2] C. Li and L. Zhao, (2022) “Optimization of 25Hz phase sensitive track circuit fault diagnosis method based on LightGBM algorithm" Journal of the China Railway Society 44(8): 68–77. DOI: 10.3969/j.issn.1001-8360.2022.08.008.
[3] A. R. Abbasi, (2022) “Fault detection and diagnosis in power transformers: A comprehensive review and classification of publications and methods" Electric Power Systems Research 209: 107990. DOI: 10.1016/j.epsr.2022.107990.
[4] L. Hong and X. Wu, (2022) “Fault feature analysis of compensation capacitor of jointless track circuit based on wavelet packet" Journal of Railway Science and Engineering 19(4): 1111–1120. DOI: 10.19713/j.cnki.43-1423/u.t20210399.
[5] A. R. Abbasi and M. R. Mahmoudi, (2021) “Application of statistical control charts to discriminate transformer winding defects" Electric Power Systems Research 191: 106890. DOI: 10.1016/j.epsr.2020.106890.
[6] A. R. Abbasi, M. R. Mahmoudi, and M. M. Arefi, (2021) “Transformer winding faults detection based on time series analysis" IEEE Transactions on Instrumentation and Measurement 70: 1–10. DOI: 10.1109/TIM.2021.3076835.
[7] A. R. Abbasi and C. P. Gandhi, (2022) “A Novel Hyperbolic Fuzzy Entropy Measure for Discrimination and Taxonomy of Transformer Winding Faults" IEEE Transactions on Instrumentation and Measurement 71: 1–8. DOI: 10.1109/TIM.2022.3212522.
[8] Y. Cao, B. Bian, and T. Zhang, (2018) “Track circuit fault diagnosis based on BP neural network" Journal of North China University of Science and Technology(Natural Science Edition) 40(1): 78–82. DOI: 10.3969/j.issn.2095-2716.2018.01.012.
[9] X. Xie and S. Dai, (2020) “Research on fault diagnosis of jointless track circuit based on deep learning" Journal of the China Railway Society 42(6): 79–85. DOI: 10.3969/j.issn.1001-8360.2020.06.011.
[10] J. Yang, Q. Zheng, X. Yao, G. Chen, and X. Wang, (2022) “Multi-compensation capacitor fault location of track circuit transient characteristics based on deep network" Journal of Railway Science and Engineering: DOI: 10.19713/j.cnki.43-1423/u.T20221535.
[11] S. Lu, W. Gao, C. Hong, and Y. Sun, (2021) “A newlydesigned fault diagnostic method for transformers via improved empirical wavelet transform and kernel extreme learning machine" Advanced Engineering Informatics 49: 101320. DOI: 10.1016/j.aei.2021.101320.
[12] X. Li, (2022) “Research on fault prediction of ZPW-2000A track circuit based on GA-KELM" Journal of Dalian Jiaotong University 43(115-119): DOI: 10.13291/j.cnki.djdxac.2022.02.021.
[13] K. Shao, W. Fu, J. Tan, and K. Wang, (2021) “Coordinated approach fusing time-shift multiscale dispersion entropy and vibrational Harris hawks optimization-based SVM for fault diagnosis of rolling bearing" Measurement 173: 108580. DOI: 10.1016/j.measurement.2020.108580.
[14] S. Li, X. Luo, and L. Wu, (2021) “An improved whale optimization algorithm for locating critical slip surface of slopes" Advances in Engineering Software 157: 103009. DOI: 10.1016/j.advengsoft.2021.103009.
[15] B. Zhu, S. Wang, Z. Zhang, P. Wang, and F. Dong, (2021) “Tunnel deformation prediction method based on time series and DEGWO-SVR model" Journal of Zhejiang University (Engineering Edition) 55(12): 2275– 2285. DOI: 10.3785/j.issn.1008-973X.2021.12.007.
[16] G.-B. Huang, (2014) “An insight into extreme learning machines: random neurons, random features and kernels" Cognitive Computation 6: 376–390. DOI: 10.1007/s12559-014-9255-2.
[17] X. Long, P. Yang, H. Guo, Z. Zhao, and Z. Zhao, (2019) “Fault diagnosis of wind power gearbox based on KELM and multi-sensor information fusion" Automation of Electric Power Systems 43(17): 132–139. DOI: 10.7500/AEPS20181126005.
[18] A. A. Heidari, S. Mirjalili, H. Faris, I. Aljarah, M. Mafarja, and H. Chen, (2019) “Harris hawks optimization: Algorithm and applications" Future generation computer systems 97: 849–872. DOI: 10.1016/j.future.2019.02.028.
[19] A. A. Dehkordi, A. S. Sadiq, S. Mirjalili, and K. Z. Ghafoor, (2021) “Nonlinear-based chaotic harris hawks optimizer: algorithm and internet of vehicles application" Applied Soft Computing 109: 107574. DOI: 10.1016/j.asoc.2021.107574.
[20] O. A. Alzubi, J. A. Alzubi, A. M. Al-Zoubi, M. A. Hassonah, and U. Kose, (2022) “An efficient malware detection approach with feature weighting based on Harris Hawks optimization" Cluster Computing 25: 2369–2387. DOI: 10.1007/s10586-021-03459-1.
[21] Y. Guo, S. Liu, W. Gao, and L. Zhang, (2021) “Multi strategy improved Harris Hawk optimization algorithm" Microelectronics & Computer 38(7): 18–24. DOI: 10.19304/j.cnki.issn1000-7180.2021.07.004.
[22] M.-Y. Cheng and D. Prayogo, (2014) “Symbiotic organisms search: a new metaheuristic optimization algorithm" Computers & Structures 139: 98–112. DOI: 10.1016/j.compstruc.2014.03.007.
[23] A. Tang, T. Han, D. Xu, and L. Xie, (2021) “Chaotic elite harris hawks optimization algorithm" Computer Application 41(8): 2265–2272. DOI: 10.11772/j.issn.1001-9081.2020101610.
[24] A. Liu and S. Wang, (2021) “Analysis and discussion on typical cases of asymmetric high-voltage pulse track circuit" Railway Communication Signal Engineering Technology 18: 99–102. DOI: 10.3969/j.issn.1673-4440.2021.Z1.022.
[25] Z. Huang. “Research on key technologies of track circuit fault prediction and health management". (phdthesis). Beijing: Beijing Jiaotong University, 2013.