To address the issue of over-reliance on manual inspections for diagnosing vehicle shaking states in traditional high-speed turnout areas, a novel diagnosis method based on generalized demodulation and Sparrow Search Algorithm optimized Support Vector Machine Model (SSA-SVM) is proposed. Firstly, the lateral acceleration of the vehicle body is decomposed using generalized demodulation, and the modal components of different frequencies are extracted. By integrating this component information with the track geometry information, the diagnostic characteristic indicators for vehicle shaking in the turnout area are further calculated. Secondly, the SSA-SVM model is used as the classification diagnosis model for vehicle shaking in the turnout area, and a corresponding diagnosis method is proposed. Finally, a case study using measured data from high-speed railway turnout area in China is conducted to validate the effectiveness of the method. The results show that compared with the diagnosis methods based on Back-Propagation algorithm model (BP), SVM model, Particle Swarm Optimization algorithm optimized Back-Propagation algorithm model (POS-BP) and Particle Swarm Optimization algorithm optimized Support Vector Machine model (POS-SVM), the proposed method achieves faster convergence speed, higher accuracy, and maintains a high diagnostic accuracy of 94.8% even with fewer features.
SIDaolin, YANGDongsheng, WANGShuguo, et al. Analysis on Dynamic Characteristics of High Speed Turnout Frog Structure in Irregularity State [J]. Railway Engineering, 2018, 58 (1): 67-69. in Chinese
WANGShuguo, SIDaolin, WANGMeng, et al. Influence of Value Reduced for Switch Rail of High Speed Railway on Riding Quality [J]. China Railway Science, 2014, 35 (3): 28-33. in Chinese
[6]
ZHOUF F, LIX, DONGW, et al. Fault Diagnosis of High-Speed Railway Turnout Based on Support Vector Machine [C]// 2016 IEEE International Conference on Industrial Technology (ICIT). Taipei, China. New York: IEEE Press, 2016: 1539-1544.
[7]
ZHANGY G, HUANGY. Research on Turnout Fault Classification Diagnosis Based on SOM Algorithm [C]// 2021 7th International Symposium on Mechatronics and Industrial Informatics (ISMII). Zhuhai, China. New York: IEEE Press, 2021: 296-299.
[8]
ZHANGK. The Railway Turnout Fault Diagnosis Algorithm Based on BP Neural Network [C]// 2014 IEEE International Conference on Control Science and Systems Engineering. Yantai, China. New York: IEEE Press, 2014: 135-138.
[9]
LIUC Y, GUOA H, CUIB S. Time-Frequency Characteristic Analysis of Track Irregularity of High-Speed Railway [J]. Electronic Measurement Technology, 2009, 32 (7): 29-32.
[10]
ZHAOL, HUANGD R, WANGH G, et al. Time-Frequency Analysis of Track Irregularity Based on Orthogonal Empirical Mode Decomposition [J]. Telkomnika Telecommunication Computing Electronics and Control, 2016, 14 (3A): 237-243.
[11]
HUH, SHIJ J, FUH X, et al. Impulse Detection of Welded Joints of High-Speed Railway Turnout Based on Time-Frequency and Correlation Analyses [C]// 2022 International Conference on Sensing, Measurement & Data Analytics in the Era of Artificial Intelligence (ICSMD). Harbin, China. New York: IEEE Press, 2022: 1-5.
[12]
HAVRYLIUKV. Fault Detecting of Turnouts Using DWT and ANN [C]// 2021 IEEE International Conference on Modern Electrical and Energy Systems (MEES). Kremenchuk, Ukraine. New York: IEEE Press, 2021: 1-6.
[13]
SHIJ J, HUAZ H, HUANGW G, et al. Instantaneous Frequency Synchronized Generalized Stepwise Demodulation Transform for Bearing Fault Diagnosis [J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 3509515.
[14]
XUEJ K, SHENB. A Novel Swarm Intelligence Optimization Approach: Sparrow Search Algorithm [J]. Systems Science and Control Engineering, 2020, 8 (1): 22-34.
BIEFengfeng, ZHUHongfei, PENGJian, et al. Fault Diagnosis of Reciprocating Compressor Air Valve Based on VMD-MSE and SSA-SVM [J]. Journal of Vibration and Shock, 2022, 41 (19): 289-295. in Chinese
ZHAOWenbo, YANGFei, TANShehui, et al. Feature Representation and Identification of Periodic Irregularity of High-Speed Railway Track [J]. China Railway Science, 2023, 44 (3): 43-52. in Chinese
[20]
KHANK, ASHOKS. A Comparison of BA, GA, PSO, BP and LM for Training Feed Forward Neural Networks in E-Learning Context [J]. International Journal of Intelligent Systems and Applications, 2012, 4 (7): 23-29.
LIUJinzhao, CHENDongsheng, ZHAOGang, et al.Track Impact Index Method for Evaluating Track Short Wave Irregularity of High Speed Railway [J]. China Railway Science, 2016, 37 (4): 34-41. in Chinese
YongwangKAI, CAIXiaopei. Analysis of Lateral Offset of Ballastless Turnout Structure and Its Disease Treatment [J]. Railway Engineering, 2017, 57 (3): 129-133. in Chinese
Suzhou University. Fault Diagnosis Method of Rotating Machinery Based on Matched Enhanced Time-Frequency Representation: China, CN202010271309.X [P]. 2020-07-28. in Chinese)
SHIJuanjuan, HUAZehui, SHENChangqing, et al. A Generalized Instantaneous-Frequency-Estimation-Free Stepwise Demodulation Transform and Its Application in Vibration Signal Analysis of Rotating Machinery [J]. Journal of Vibration and Shock, 2021, 40 (24): 1-11, 21. in Chinese
[29]
TRUEH. Recent Advances in the Fundamental Understanding of Railway Vehicle Dynamics [J]. International Journal of Vehicle Design, 2006, 40 (1/2/3): 251-264.
[30]
刘金朝.轨道周期性几何不平顺诊断和评价方法[J].铁道建筑,2016,56(7):1-5.
[31]
LIUJinzhao. Diagnosis and Evaluation Method of Track Periodic Geometric Irregularity [J]. Railway Engineering, 2016, 56 (7): 1-5. in Chinese
LINXinhai, DONGTing, XUHang. Fault Detection of Electric Multiple Unit Gearbox Based on Vibration Eigenvalue [J]. Failure Analysis and Prevention, 2022, 17 (3): 189-194. in Chinese
ZHANGChao, CHENJianjun, GUOXun. A Gear Fault Diagnosis Method Based on EMD Energy Entropy and SVM [J]. Journal of Vibration and Shock, 2010, 29 (10): 216-220, 261. in Chinese
[36]
SUNW, LIUM H, LIANGY. Wind Speed Forecasting Based on FEEMD and LSSVM Optimized by the Bat Algorithm [J]. Energies, 2015, 8 (7): 6585-6607.