基于排列熵和支持向量机的轨枕病害诊断

doi:10.16180/j.cnki.issn1007-7820.2022.02.009

摘要/Abstract

摘要：

文中提出了一种基于排列熵和支持向量机的轨枕病害诊断方法。该方法通过建立车辆-轨道耦合振动模型获取轨枕的振动加速度,利用排列熵算法提取轨枕不同病害下的振动响应特征指标,并以归一化后的排列熵特征指标集为输入。该方法基于遗传算法优化的支持向量机对轨枕服役状态进行诊断和分类,实现了对轨枕不同病害的诊断。数据仿真结果表明,该方法对轨枕病害识别准确率均能达到90%以上,对于部分轨道不平顺谱激励和列车速度下的服役状态,识别准确率能达到97.5%。该结果表明,文中所提方法能够有效地对轨枕病害进行诊断,为轨道结构服役状态的在线监测与智能预警提供了方法依据。

关键词: 振动响应, 轨枕病害, 特征提取, 排列熵, 归一化, 遗传算法, 支持向量机, 病害诊断

Abstract:

This study proposes a sleeper diseases diagnosis method based on permutation entropy and support vector machine. This method obtains the vibration acceleration of the sleeper by establishing a vehicle-track coupled vibration model, uses the permutation entropy algorithm to extract the vibration response characteristic indexes under different diseases of the sleeper, and takes the normalized permutation entropy characteristic index set as input. Based on the support vector machine optimized by genetic algorithm, this method diagnoses and classifies the service status of sleepers, and realizes the diagnosis of different diseases of sleepers. The simulation results show that the accuracy of the method for the identification of sleeper diseases can reach more than 90%, and the recognition accuracy can reach 97.5% for the part of track irregularity spectrum excitation and the service state of the train speed. Therefore, the proposed method can effectively diagnose sleeper diseases and provide a certain method basis for online monitoring and intelligent early warning of track structure service status.

Key words: vibration response, sleeper faults, feature extraction, permutation entropy, normalized, genetic algorithm, support vector machine, disease diagnosis

中图分类号:

TP391.4

邵志慧,杨俭,袁天辰,伍伟嘉. 基于排列熵和支持向量机的轨枕病害诊断[J]. 电子科技, 2022, 35(2): 52-58.

SHAO Zhihui,YANG Jian,YUAN Tianchen,WU Weijia. Sleeper Diseases Diagnosis Based on Permutation Entropy and Support Vector Machine[J]. Electronic Science and Technology, 2022, 35(2): 52-58.

图/表 10

图1

表1

表2

图2

图3

图4

表3

图5

图6

表4

参考文献 18

[1]	訾谦. 3.5万km:中国高铁的新跨度[J]. 城市轨道交通研究, 2019, 22(12):6-7.
	Zi Qian. 35 000 km: the new span of China's high-speed rail[J]. Urban Mass Transit, 2019, 22(12):6-7.
[2]	钟鹏飞, 车爱兰, 冯少孔, 等. 高速铁路线下结构典型病害分析及快速无损检测方法研究[J]. 振动与冲击, 2017, 36(11):154-160.
	Zhong Pengfei, Che Ailan, Feng Shaokong, et al. Typical defects' analysis and nondestructive detection method for undertrack structures of high speed railways[J]. Journal of Vibration and Shock, 2017, 36(11):154-160.
[3]	钟志旺, 唐涛, 王峰. 基于PLSA和SVM的道岔故障特征提取与诊断方法研究[J]. 铁道学报, 2018, 40(7):80-87.
	Zhong Zhiwang, Tang Tao, Wang Feng. Research on fault feature extraction and diagnosis of railway switches based on PLSA and SVM[J]. Journal of the China Railway Society, 2018, 40(7):80-87.
[4]	Wirtz S F, Beganovic N, Soffker D. Investigation of damage detectability in composites using frequency-based classification of acoustic emission measurements[J]. Structural Health Monitoring-AN International Journal, 2019, 18(4):1207-1218. doi: 10.1177/1475921718791894
[5]	张涵, 万振刚. 基于压缩感知与VMD的船舶推进轴系轴承振动故障分析[J]. 舰船电子工程, 2020, 40(1):157-161.
	Zhang Han, Wan Zhengang. Vibration fault analysis of ship propulsion shaft bearings based on compressed sensing and VMD[J]. Ship Electronic Engineering, 2020, 40(1):157-161.
[6]	赵柄锡, 冀大伟, 袁奇, 等. 基于时域与时频域联合特征提取和可分度分析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 extraction and distinguishing analysis in time and time-frequency domain[J]. Journal of Xi'an Jiaotong University, 2020, 54(1):75-84.
[7]	Tayfur S, Alver N, Abdi S, et al. Characterization of concrete matrix/steel fber de-bonding in an SFRC beam: Principal component analysis and k-mean algorithm for clustering AE data[J]. Engineering Fracture Mechanics, 2018, 194(3):73-85. doi: 10.1016/j.engfracmech.2018.03.007
[8]	曲星宇, 曾鹏, 李俊鹏. 基于RNN-LSTM的磨矿系统故障诊断技术[J]. 信息与控制, 2019, 48(2):179-186. doi: 10.13976/j.cnki.xk.2019.8365
	Qu Xingyu, Zeng Peng, Li Junpeng. Fault diagnosis technology of grinding system based on RNN-LSTM[J]. Information and Control, 2019, 48(2):179-186. doi: 10.13976/j.cnki.xk.2019.8365
[9]	苏烨, 李筠, 杨海马, 等. 基于Faster R-CNN的钢轨表面缺陷识别研究[J]. 电子科技, 2020, 33(9):63-68.
	Su Ye, Li Jun, Yang Haima, et al. Research on rail surface defect recognition based on faster R-CNN[J]. Electronic Science and Technology, 2020, 33(9):63-68.
[10]	万东燕, 许桢英, 杨卿, 等. 基于PCA与SVM的焊缝缺陷信号分类方法[J]. 电子科技, 2020, 33(5):9-14.
	Wan Dongyan, Xu Zhenying, Yang Qing, et al. A method of weld defect classification based on PCA and SVM[J]. Electronic Science and Technology, 2020, 33(5):9-14.
[11]	Shah S A A, Habib N, Nadeem M S A, et al. Extraction of dynamical information and classification of heart rate variability signals using scale based permutation entropy measures[J]. Traitement du Signal, 2020, 37(3):355-365. doi: 10.18280/ts
[12]	Keshmiri S. Comparative analysis of the permutation and multiscale entropies for quantification of the brain signal variability in naturalistic scenarios[J]. Brain Sciences, 2020, 10(8):1-38. doi: 10.3390/brainsci10010001
[13]	Borovsky J E, Osmane A. Compacting the description of a time-dependent multivariable system and its multivariable driver by reducing the state vectors to aggregate scalars: the Earth's solar-wind-driven magnetosphere[J]. Nonlinear Processes in Geophysics, 2019, 26(4):429-443. doi: 10.5194/npg-26-429-2019
[14]	Bandt C, Pompe B. Permutation entropy: A natural complexity measure for time series[J]. Physical Review Letters, 2002, 88(17):1741021-1741024.
[15]	翟婉明. 车辆-轨道耦合动力学[M]. 北京: 科学出版社, 2007.
	Zhai Wanming. Vehicle-track coupled dynamics[M]. Beijing: Science Press, 2007.
[16]	武薇, 申永军, 杨绍普. 基于排列熵理论的非线性系统特征提取研究[J]. 振动与冲击, 2020, 39(7):67-73.
	Wu Wei, Shen Yongjun, Yang Shaopu. Feature extraction for nonlinear systems based on permutation entropy theory[J]. Journal of Vibration and Shock, 2020, 39(7):67-73.
[17]	Jiao J Y, Zhao M, Lin J. Unsupervised adversarial adaptation network for intelligent fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2020, 67(11):9904-9913. doi: 10.1109/TIE.41
[18]	魏禹. 基于熵值的齿轮箱故障特征提取与早期故障诊断方法研究[D]. 哈尔滨:哈尔滨工业大学, 2019.
	Wei Yu. Investigation of fault feature extraction based on entropy and early fault diagnosis for gearbox[D]. Haibin:Harbin Institute of Technology, 2019.

列车速度 /(km·h^-1)	轨枕编号	轨枕服役状态
100	51~150	S₁	S₂	S₃	S₄
110	51~150	S₁	S₂	S₃	S₄
120	51~150	S₁	S₂	S₃	S₄
130	51~150	S₁	S₂	S₃	S₄
140	51~150	S₁	S₂	S₃	S₄
150	51~150	S₁	S₂	S₃	S₄
160	51~150	S₁	S₂	S₃	S₄
180	51~150	S₁	S₂	S₃	S₄
200	51~150	S₁	S₂	S₃	S₄

轨枕号服役状态	111	112	113	114	115	116	117	118	119	120
S₁	1.389	1.412	1.369	1.436	1.356	1.419	1.373	1.391	1.377	1.371
S₂	1.379	1.399	1.352	1.411	1.351	1.406	1.362	1.377	1.359	1.358
S₃	1.325	1.359	1.301	1.365	1.308	1.384	1.305	1.338	1.315	1.311
S₄	1.269	1.304	1.252	1.291	1.271	1.314	1.267	1.286	1.268	1.261