基于支持向量机的轨道结构病害识别研究

doi:10.16180/j.cnki.issn1007-7820.2022.02.005

摘要/Abstract

摘要：

轨道结构作为承载列车载荷的关键部件,一旦出现病害将直接影响列车的行驶安全。针对这一问题,文中提出了一种基于支持向量机的轨道结构病害识别方法。该方法利用时域统计和离散小波变换对轨道结构不同工况,例如正常状态、轨枕空吊、道床板结下轨枕振动加速度数据进行联合特征提取,降低了数据的维度,为病害识别提供了可能。该方法还利用支持向量机算法对特征向量进行识别,并采用网格搜索方法对支持向量机参数进行选优,识别准确率在85%左右。实验结果表明,所提方法可以对不同程度的轨枕空吊及道床板结病害进行较好地识别,为轨道结构故障在线预警提供技术基础。

关键词: 轨枕空吊, 道床板结, 病害识别, 时域统计, 特征提取, 网格搜索, 支持向量机

Abstract:

The track structure is a key component that carries the load of the train. Once a disease occurs, it will directly affect the safety of the train. To solve this problem, a method for identifying the track structure disease based on a support vector machine is proposed. This method uses time-domain statistics and discrete wavelet transform to perform joint feature extraction on the vibration acceleration data of the sleeper under different working conditions of the track structure, such as normal state, unsupported sleeper and cement hardening, which reduces the dimensionality of data and provides the possibility for disease identification. The method also uses the support vector machine algorithm to identify the feature vector, and uses the grid search method to select the parameters of the support vector machine, so that the recognition accuracy rate reaches about 85%. The experimental results show that the proposed method can better identify different degrees of unsupported sleeper and cement hardening, and provide a technical basis for online early warning of track structure failure.

Key words: unsupported sleeper, cement hardening, disease identification, time-domain statistics, feature extraction, grid search, support vector machine

中图分类号:

TP391.4

伍伟嘉,杨俭,袁天辰,邵志慧. 基于支持向量机的轨道结构病害识别研究[J]. 电子科技, 2022, 35(2): 27-33.

WU Weijia,YANG Jian,YUAN Tianchen,SHAO Zhihui. Research on Track Structure Damage Identification Based on Support Vector Machine[J]. Electronic Science and Technology, 2022, 35(2): 27-33.

图/表 6

图1

表1

图2

图3

图4

图5

参考文献 19

[1]	韦红亮, 练松良, 周宇. 轨面不平顺对高架支承块轨道结构振动特性影响试验研究[J]. 中国铁道科学, 2011, 32(6):22-27.
	Wei Hongliang, Lian Songliang, Zhou Yu. Experimental study on the influence of rail surface irregularities on the vibration characteristics of elevated block-supported track[J]. China Railway Science, 2011, 32(6):22-27.
[2]	张健. 基于ACSEEMD和模糊C均值聚类的风电机组齿轮箱故障预警[J]. 电子器件, 2019, 42(6):1410-1415.
	Zhang Jian. Fault warning of wind turbine gearbox based on ACSEEMD and fuzzy C means clustering[J]. Chinese Journal of Electron Devices, 2019, 42(6):1410-1415.
[3]	何宜鸿, 李彦锋, 黄树恺, 等. 基于深度卷积神经网络的自适应图像去雾算法[J]. 电子科技, 2020, 33(8):70-73.
	He Yihong, Li Yanfeng, Huang Shukai, et al. Adaptive image dehazingg algorithm based on deep convolutional neural network[J]. Electronic Science and Technology, 2020, 33(8):70-73.
[4]	蓝机满. 基于径向基神经网络的粒子群表面缺陷识别算法[J]. 电子科技, 2019, 32(5):92-95.
	Lan Jiman. Particle swarm optimization surface defect recognition algorithm based on radial basis neural network[J]. Electronic Science and Technology, 2019, 32(5):92-95.
[5]	Gordan M, Ismail Z, Razak H A, et al. Data mining-based damage identification of a slab-on-girder bridge using inverse analysis[J]. Measurement, 2020, 151(3):107-175.
[6]	高国磊, 李英娜, 段效琛, 等. 基于ACO优化LS-SVM的变压器故障诊断[J]. 电子科技, 2018, 31(6):59-62.
	Gao Guolei, Li Yingna, Duan Xiaochen, et al. A fault diagnosis method for transformer based on least squares support vector machine optimized by ant colony optimization[J]. Electronic Science and Technology, 2018, 31(6):59-62.
[7]	赵柄锡, 冀大伟, 袁奇, 等. 采用时域与时频域联合特征空间的转子系统碰磨故障诊断[J]. 西安交通大学学报, 2020, 54(1):75-84.
	Zhao Bingxi, Ji Dawei, Yuan Qi, et al. Rubbing fault diagnosis of rotor system based on combined feature space in time and time-frequency domains[J]. Journal of Xi'an Jiaotong University, 2020, 54(1):75-84.
[8]	梁治华, 曹江涛, 姬晓飞. 基于EEMD和CS-SVM的滚动轴承故障诊断研究[J]. 机电工程, 2019, 36(6):622-627.
	Liang Zhihua, Cao Jiangtao, Ji Xiaofei. Fault diagnosis of rolling bearing based on EEMD and CS-SVM[J]. Journal of Mechanical & Electrical Engineering, 2019, 36(6):622-627.
[9]	翟婉明. 车辆-轨道耦合动力学[M].4版. 北京: 科学出版社, 2015.
	Zhai Wanming. Vehicle-track coupled dynamics[M].4th ed. Beijing: Science Press, 2015.
[10]	Baydar N, Chen Q, Ball A, et al. Detection of incipient tooth defect in helical gears using multivariate statistics[J]. Mechanical Systems and Signal Processing, 2001, 15(2):303-321. doi: 10.1006/mssp.2000.1315
[11]	Ding H, Zhang G C, Chen L Q. Supercritical vibration of nonlinear coupled moving beams based on discrete Fourier transform[J]. International Journal of Non-Linear Mechanics, 2012, 47(10):1095-1104. doi: 10.1016/j.ijnonlinmec.2011.09.010
[12]	Cao H R, He D, Xi S T, et al. Vibration signal correction of unbalanced rotor due to angular speed fluctuation[J]. Mechanical Systems and Signal Processing, 2018, 107(1):202-220. doi: 10.1016/j.ymssp.2018.01.030
[13]	Parey A, Singh A. Gearbox fault diagnosis using acoustic signals, continuous wavelet transform and adaptive neuro-fuzzy inference system[J]. Applied Acoustics, 2019, 147(2):133-140. doi: 10.1016/j.apacoust.2018.10.013
[14]	高永强. 连续小波变换高光谱数据降维挖掘系统设计[J]. 激光杂志, 2020, 41(7):137-140.
	Gao Yongqiang. Design of continuous wavelet transform hyper-spectral data dimension reduction mining system[J]. Laser Journal, 2020, 41(7):137-140.
[15]	高秋菊, 张云银, 曲志鹏, 等. 基于ISTA算法的稀疏约束反演谱分解及应用[J]. 新疆石油地质, 2020, 41(4):471-476.
	Gao Qiuju, Zhang Yunyin, Qu Zhipeng, et al. Decomposition and application of constrained sparse inversion spectrum based on ISTA algorithm[J]. Xinjiang Petroleum Geology, 2020, 41(4):471-476.
[16]	Chen R X, Huang X, Yang L X, et al. Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform[J]. Computers in Industry, 2019, 106(3):48-59. doi: 10.1016/j.compind.2018.11.003
[17]	Wu F, Hao Y, Zhao J, et al. Current similarity based open-circuit fault diagnosis for induction motor drives with discrete wavelet transform[J]. Microelectronics Reliability, 2017, 75(7):309-316. doi: 10.1016/j.microrel.2017.05.036
[18]	屈召贵. 基于窗函数法的FIR数字滤波器设计[J]. 信息技术与网络安全, 2019, 38(9):85-89.
	Qu Zhaogui. Design of FIR digital filter based on window function method[J]. Information Technology and Network Security, 2019, 38(9):85-89.
[19]	Bacha K, Souahlia S, Gossa M. Power transformer fault diagnosis based on dissolved gas analysis by support vector machine[J]. Electric Power Systems Research, 2012, 83(1):73-79. doi: 10.1016/j.epsr.2011.09.012

工况编号	工况状态	刚度K_b	阻尼C_b
A1	正常	K_b	C_b
A2	轨枕空吊	0.5 K_b	0.5 C_b
A3	轨枕空吊	0	0
A4	道床板结	2 K_b	2 C_b
A5	道床板结	3 K_b	3 C_b