| Citation: | WANG Xiaomin, XIONG Xuzhou, YANG Yong, YANG Wudong, JIANG Lei. Identification of Shunt Malfunctions in Track Circuits Based on Transient Features of Rail Output Voltage[J]. Journal of Southwest Jiaotong University. doi: 10.3969/j.issn.0258-2724.20240490 |
To address the problem of shunt malfunctions in ZPW-2000A track circuits, an intelligent identification method based on the analysis of transient features of rail output voltage was proposed, taking into account the relationship between shunting resistance and shunt malfunctions. First, variational mode decomposition (VMD) was used to extract the transient signal of rail output voltage, and the marine predators algorithm was employed to adaptively optimize the VMD parameters to obtain the mode components. Second, mutual information was used to select and reconstruct the mode components, thus obtaining the transient feature vector of rail output voltage. Finally, an improved deep residual shrinkage network based on an efficient channel attention mechanism was proposed. The transient features of rail output voltage corresponding to different shunting resistances were collected and used for network training and shunting resistance identification. The identification results were combined with the track relay status to determine whether the shunting state was normal, required a shunt malfunction warning, or indicated a shunt malfunction. A physical simulation platform for the ZPW-2000A system was established, and transient response data were collected as a train entered and cleared the track section under conditions involving a disconnected compensation capacitor and different shunting resistances. The model performance was tested to verify the feasibility and effectiveness of the proposed method for shunt malfunction identification. The results show that the proposed method can effectively identify shunt malfunctions in track circuits and provide early warnings based on the transient features of rail output voltage, achieving an identification accuracy of 98% and a transient feature identification accuracy of 97.3%. Under interference from traction harmonics, adjacent track sections, transient traction currents, and Gaussian white noise, the model exhibits strong feature representation capability and good anti-noise performance. The findings provide an approach for identifying shunt malfunctions in track circuits and issuing early warnings in practical railway applications.
| [1] |
徐宗奇. ZPW-2000A轨道电路分路不良技术分析与处理研究[J]. 铁路通信信号工程技术, 2019, 16(增刊1): 53-58.
Xu Zongqi. Technical analysis and treatment of ZPW-2000A track circuit bad shunting[J]. Railway Signalling & Communication Engineering, 2019, 16(S1): 53-58.
|
| [2] |
王健. 站内轨道电路分路不良问题分析与优化[J]. 铁路通信信号工程技术, 2024, 21(7): 110-114. doi: 10.3969/j.issn.1673-4440.2024.07.017
Wang Jian. Analysis and optimization of poor shunting of station track circuit[J]. Railway Signalling & Communication Engineering, 2024, 21(7): 110-114. doi: 10.3969/j.issn.1673-4440.2024.07.017
|
| [3] |
冯栋, 赵林海. 基于机车信号远程监测系统的分路电阻在线估算方法[J]. 铁道学报, 2017, 39(4): 62-67. doi: 10.3969/j.issn.1001-8360.2017.04.009
Feng Dong, Zhao Linhai. Online estimation method of shunt resistance based on cab-signal remote monitoring system[J]. Journal of the China Railway Society, 2017, 39(4): 62-67. doi: 10.3969/j.issn.1001-8360.2017.04.009
|
| [4] |
苏丽娜, 张亚东, 王梓丞, 等. 基于变分模态分解和能量谱的轨道电路分路不良故障监测[J]. 铁道标准设计, 2019, 63(2): 155-160. doi: 10.13238/j.issn.1004-2954.201803220003
Su Lina, Zhang Yadong, Wang Zicheng, et al. Prediction of shunt malfunction of track circuit based on variational mode decomposition and energy spectrum[J]. Railway Standard Design, 2019, 63(2): 155-160. doi: 10.13238/j.issn.1004-2954.201803220003
|
| [5] |
李钰婕. ZPW-2000A型无绝缘轨道电路分路不良预测方法研究[D]. 兰州: 兰州交通大学, 2022.
|
| [6] |
戚呈辉, 任志俊, 杜小虎. 基于模糊熵和非对称贴近度的轨道电路分路不良故障预警系统[J]. 计算机与数字工程, 2023, 51(6): 1260-1265. doi: 10.3969/j.issn.1672-9722.2023.06.009
Qi Chenghui, Ren Zhijun, Du Xiaohu. Early warning system for track circuit shunt failure based on fuzzy entropy and asymmetric closeness[J]. Computer and Digital Engineering, 2023, 51(6): 1260-1265. doi: 10.3969/j.issn.1672-9722.2023.06.009
|
| [7] |
杨璟, 王小敏, 张文芳, 等. 基于PMFCC-DTW的轨道电路暂态故障诊断[J]. 铁道学报, 2021, 43(5): 104-111. doi: 10.3969/j.issn.1001-8360.2021.05.012
Yang Jing, Wang Xiaomin, Zhang Wenfang, et al. Transient fault diagnosis of track circuit based on PMFCC-DTW[J]. Journal of the China Railway Society, 2021, 43(5): 104-111. doi: 10.3969/j.issn.1001-8360.2021.05.012
|
| [8] |
林俊亭, 牛鹏远. 基于DCNN的ZPW-2000A无绝缘轨道电路故障诊断研究[J]. 电子测量与仪器学报, 2024, 38(6): 171-180. doi: 10.13382/j.jemi.B2306946
Lin Junting, Niu Pengyuan. Research on fault diagnosis of ZPW-2000A jointless track circuit based on DCNN[J]. Journal of Electronic Measurement and Instrumentation, 2024, 38(6): 171-180. doi: 10.13382/j.jemi.B2306946
|
| [9] |
王梓丞, 郭进, 张亚东, 等. 基于FDTD接口方法的ZPW-2000轨道电路暂态分析[J]. 西南交通大学学报, 2019, 54(1): 196-201, 218. doi: 10.3969/j.issn.0258-2724.20180020
Wang Zicheng, Guo Jin, Zhang Yadong, et al. Transient analysis of ZPW-2000 track circuit based on FDTD interface method[J]. Journal of Southwest Jiaotong University, 2019, 54(1): 196-201,218. doi: 10.3969/j.issn.0258-2724.20180020
|
| [10] |
祁欢, 张友鹏. 基于精细时程积分法的轨道电路暂态分析[J]. 控制工程, 2018, 25(12): 2232-2238. doi: 10.14107/j.cnki.kzgc.150802
Qi Huan, Zhang Youpeng. Transient analysis for track circuit based on precise time-integration[J]. Control Engineering of China, 2018, 25(12): 2232-2238. doi: 10.14107/j.cnki.kzgc.150802
|
| [11] |
中华人民共和国铁道部. 铁路信号维护规则技术标准-Ⅰ[M]. 2版. 北京: 中国铁道出版社, 2008: 92-93.
|
| [12] |
杨璟, 郑启明, 姚新文, 等. 基于深度网络的轨道电路暂态特征多补偿电容故障定位[J]. 铁道科学与工程学报, 2023, 20(7): 2653-2663. doi: 10.19713/j.cnki.43-1423/u.T20221535
Yang Jing, Zheng Qiming, Yao Xinwen, et al. Multiple compensation capacitance fault location based on deep network transient characteristics of track circuit[J]. Journal of Railway Science and Engineering, 2023, 20(7): 2653-2663. doi: 10.19713/j.cnki.43-1423/u.T20221535
|
| [13] |
易彩, 林建辉, 汪浩, 等. VMD引导的轮对与轴承复合故障诊断方法[J]. 西南交通大学学报, 2024, 59(1): 151-159. doi: 10.3969/j.issn.0258-2724.20211088
Yi Cai, Lin Jianhui, Wang Hao, et al. Compound fault diagnosis method guided by variational mode decomposition for wheelsets and bearings[J]. Journal of Southwest Jiaotong University, 2024, 59(1): 151-159. doi: 10.3969/j.issn.0258-2724.20211088
|
| [14] |
魏子钧, 杨世武, 李文涛, 等. 基于优化变分模态分解的轨道电路信号分析方法[J]. 中国铁道科学, 2024, 45(5): 198-208. doi: 10.3969/j.issn.1001-4632.2024.05.19
Wei Zijun, Yang Shiwu, Li Wentao, et al. Track circuit signal analysis method based on optimized variational mode decomposition[J]. China Railway Science, 2024, 45(5): 198-208. doi: 10.3969/j.issn.1001-4632.2024.05.19
|
| [15] |
Faramarzi A, Heidarinejad M, Mirjalili S, et al. Marine predators algorithm: a nature-inspired metaheuristic[J]. Expert Systems with Applications, 2020, 152: 113377. doi: 10.1016/j.eswa.2020.113377
|
| [16] |
王稳, 易家彪. 柔性自适应海洋捕食者算法及其在风电机组故障诊断中的应用研究[J]. 控制与信息技术, 2024(6): 51-59. doi: 10.13889/j.issn.2096-5427.2024.06.600
Wang Wen, Yi Jiabiao. Flexible adaptive marine predator algorithm and its application in fault detection for wind turbines[J]. Control and Information Technology, 2024(6): 51-59. doi: 10.13889/j.issn.2096-5427.2024.06.600
|
| [17] |
Xing Z K, He Y G, Wang X, et al. VMD-IARIMA-based time-series forecasting model and its application in dissolved gas analysis[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2023, 30(2): 802-811. doi: 10.1109/TDEI.2022.3228222
|
| [18] |
焦梅梅, 石磊, 刘雅芝. 基于GA-VMD的无绝缘轨道电路调谐区和补偿电容故障特征提取[J]. 北京交通大学学报, 2023, 47(3): 149-158. doi: 10.11860/j.issn.1673-0291.20220101
Jiao Meimei, Shi Lei, Liu Yazhi. Fault feature extraction of jointless track circuit tuning area and compensation capacitor based on GA-VMD[J]. Journal of Beijing Jiaotong University, 2023, 47(3): 149-158. doi: 10.11860/j.issn.1673-0291.20220101
|
| [19] |
Zhao M H, Zhong S S, Fu X Y, et al. Deep residual shrinkage networks for fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7): 4681-4690. doi: 10.1109/tii.2019.2943898
|
| [20] |
刘小峰, 徐全桂, 金燕, 等. 噪声干扰环境下的深度强化学习故障诊断方法[J]. 电子测量与仪器学报, 2024, 38(12): 145-154. doi: 10.13382/j.jemi.B2407557
Liu Xiaofeng, Xu Quangui, Jin Yan, et al. Deep reinforcement learning fault diagnosis method under noisy interference environment[J]. Journal of Electronic Measurement and Instrumentation, 2024, 38(12): 145-154. doi: 10.13382/j.jemi.B2407557
|
| [21] |
Wang Q L, Wu B G, Zhu P F, et al. ECA-net: efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2020: 11531-11539.
|
| [22] |
Pei X W, Dong S J, Tang B P, et al. Bearing running state recognition method based on feature-to-noise energy ratio and improved deep residual shrinkage network[J]. IEEE/ASME Transactions on Mechatronics, 2022, 27(5): 3660-3671. doi: 10.1109/TMECH.2021.3120755
|
| [23] |
Si L, Li J H, Wang Z B, et al. A novel coal-gangue recognition method for top coal caving face based on IALO-VMD and improved MobileNetV2 network[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 2529216. doi: 10.1109/tim.2023.3316250
|
| [24] |
杨世武, 楚少童, 刘淑贤, 等. 基于改进DnCNN的机车信号抗干扰算法[J]. 北京交通大学学报, 2022, 46(2): 73-81. doi: 10.11860/j.issn.1673-0291.20210062
Yang Shiwu, Chu Shaotong, Liu Shuxian, et al. Anti-interference algorithm for cab signalling based on improved DnCNN[J]. Journal of Beijing Jiaotong University, 2022, 46(2): 73-81. doi: 10.11860/j.issn.1673-0291.20210062
|
| [25] |
崔勇, 唐乾坤, 杨世武. 基于调整表优化的轨道电路牵引电流干扰防护研究[J]. 铁道学报, 2018, 40(12): 71-80. doi: 10.3969/j.issn.1001-8360.2018.12.010
Cui Yong, Tang Qiankun, Yang Shiwu. Research on anti-interference of track circuit against traction current based on adjustment table optimization[J]. Journal of the China Railway Society, 2018, 40(12): 71-80. doi: 10.3969/j.issn.1001-8360.2018.12.010
|
| [26] |
邢玉龙, 王剑, 赵会兵, 等. 基于全卷积神经网络的机车信号降噪[J]. 西南交通大学学报, 2021, 56(2): 444-450. doi: 10.3969/j.issn.0258-2724.20191111
Xing Yulong, Wang Jian, Zhao Huibing, et al. Cab signal denoising process based on fully convolutional networks[J]. Journal of Southwest Jiaotong University, 2021, 56(2): 444-450. doi: 10.3969/j.issn.0258-2724.20191111
|