基于改进时域多尺度散布熵与支持向量机的转辙机故障诊断

doi:10.12263/DZXB.20210773

电子学报 ›› 2023, Vol. 51 ›› Issue (1): 117-127.DOI: 10.12263/DZXB.20210773

基于改进时域多尺度散布熵与支持向量机的转辙机故障诊断

曹源¹, 宋迪¹, 胡小溪², 孙永奎¹

^1.北京交通大学轨道交通运行控制系统国家工程研究中心, 北京 100044
^2.北京交通大学轨道交通控制与安全国家重点实验室, 北京 100044

收稿日期:2021-06-22 修回日期:2021-09-01 出版日期:2023-01-25
- 通讯作者:
- 宋迪
- 作者简介:
- ：曹源　男，1982年出生于河南省开封市.现为北京交通大学电子信息工程学院教授、博士生导师.主要研究方向为列车运行控制系统健康管理.E-mail: ycao@bjtu.edu.cn
  宋迪（通讯作者）　男，1992年出生于河北省衡水市.现为北京交通大学电子信息工程学院硕士研究生.主要研究方向为转辙机故障诊断.E-mail: 19120243@bjtu.edu.cn
  胡小溪　男，1995年出生于湖北省襄阳市.现为北京交通大学电子信息工程学院博士研究生.主要研究方向是道岔转换系统的状态监测与寿命预测.
  孙永奎　男，1993年出生于河南省永城市.2021年毕业于北京交通大学电子信息工程学院，获得交通信息工程及控制专业博士学位.现为北京交通大学电子信息工程学院副教授.主要研究方向为列车运行控制系统故障诊断.
- 基金资助:
- 国家自然科学基金重点项目 (U1934219); National Natural Science Foundation of China (U1934219); 国家自然科学基金优秀青年基金项目 (52022010)

Fault Diagnosis of Railway Point Machine Based on Improved Time- Domain Multiscale Dispersion Entropy and Support Vector Machine

CAO Yuan¹, SONG Di¹, HU Xiao-xi², SUN Yong-kui¹

^1.National Engineering Research Center of Rail Transportation Operation and Control System, Beijing Jiaotong University, Beijing 100044, China
^2.State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, China

Received:2021-06-22 Revised:2021-09-01 Online:2023-01-25 Published:2023-02-23
- Corresponding author:
- SONG Di

摘要/Abstract

摘要：

为充分挖掘转辙机振动信号的有效故障信息，提高故障诊断准确率，提出了一种基于集合经验模态分解（Ensemble Empirical Mode Decomposition，EEMD）、改进时域多尺度散布熵（Improved Time-domain Multiscale Dispersion Entropy，TMDE）与粒子群优化算法（Particle Swarm Optimization algorithm，PSO）优化支持向量机（Support Vector Machine，SVM）的故障诊断方法.首先，通过EEMD方法将不同故障类型的振动信号分解成若干个模态函数（Intrinsic Mode Functions，IMFs）；其次，采用相关系数与峭度的混合筛选准则筛选IMFs并重构信号；再次，应用所提ITMDE算法提取重构信号的多尺度故障特征；最后将得到的特征向量输入经PSO搜索最优参数后的SVM进行训练和测试.实验分类准确率为100%，分析表明所提方法优于传统的多尺度排列熵、多尺度散布熵的故障诊断方法，能精确地识别转辙机故障类型.

关键词: 故障诊断, 转辙机, 集合经验模态分解, 改进时域多尺度散布熵, 支持向量机

Abstract:

To fully mine the effective fault information and improve the fault diagnosis accuracy, a fault diagnosis approach for railway point machine is proposed by ensemble empirical mode decomposition (EEMD), improved time-domain multiscale dispersion entropy (ITMDE) and support vector machine (SVM) optimized by particle swarm optimization algorithm (PSO). Firstly, vibration signals with different fault types are decomposed into several intrinsic mode functions (IMFs) by EEMD. Subsequently, the hybrid screening criteria of correlation coefficient and kurtosis (CCKC) are used to screen IMFs and reconstruct the signal. Afterwards, the proposed ITMDE algorithm is employed to extract multiscale fault features from the reconstructed signal. Finally, the PSO is devoted to search the optimal parameters of SVM, with which the obtained feature vectors are trained and tested. The experimental classification accuracy reaches 100%. The results show that the proposed method is superior to the traditional multiscale permutation entropy and multiscale dispersive entropy fault diagnosis methods, and can accurately identify the fault type of the railway point machine.

Key words: fault diagnosis, railway point machine, ensemble empirical mode decomposition, improved time-domain multiscale dispersion entropy, support vector machine

中图分类号:

U284.92

曹源, 宋迪, 胡小溪, 等. 基于改进时域多尺度散布熵与支持向量机的转辙机故障诊断[J]. 电子学报, 2023, 51(1): 117-127.

Yuan CAO, Di SONG, Xiao-xi HU, et al. Fault Diagnosis of Railway Point Machine Based on Improved Time- Domain Multiscale Dispersion Entropy and Support Vector Machine[J]. Acta Electronica Sinica, 2023, 51(1): 117-127.

图/表 18

参考文献 23

1	杜洁. 基于故障树技术的铁路信号设备故障诊断专家系统的实现方法研究[D]. 北京: 北京交通大学, 2009.
	DU J. Research on Expert System Implementation of Railway Signal Equipment Fault Diagnosis Based on Fault Tree Analysis[D]. Beijing: Beijing Jiaotong University, 2009. (in Chinese)
2	CAO Y, LI P, ZHANG Y Z. Parallel processing algorithm for railway signal fault diagnosis data based on cloud computing[J]. Future Generation Computer Systems, 2018, 88: 279-283.
3	LI Z, YIN Z, TANG T, et al. Fault diagnosis of railway point machines using the locally connected autoencoder[J]. Applied Sciences, 2019, 9(23): 5139.
4	SHAO K X, FU W L, TAN J W, et al. Coordinated approach fusing time-shift multiscale dispersion entropy and vibrational Harris Hawks optimization-based SVM for fault diagnosis of rolling bearing[J]. Measurement, 2021, 173: 108580.
5	HUANG N, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-998.
6	CAO Y, ZHANG Y Z, WEN T, et al. Research on dynamic nonlinear input prediction of fault diagnosis based on fractional differential operator equation in high-speed train control system[J]. Robotics & Maching Learning, 2019, 29(1): 340-346.
7	WU Z H, HUANG N E. Ensemble empirical mode decomposition: A noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41.
8	张安安, 黄晋英, 冀树伟, 等. 基于卷积神经网络图像分类的轴承故障模式识别[J]. 振动与冲击, 2020, 39(4): 165-171.
	ZHANG A A, HUANG J Y, JI S W, et al. Bearing fault pattern recognition based on image classification with CNN[J]. Journal of Vibration and Shock, 2020, 39(4): 165-171. (in Chinese)
9	高军峰, 司慧芳, 余彬, 等. 基于脑电样本熵的测谎分析[J]. 电子学报, 2017, 45(8): 1836-1841.
	GAO J F, SI H F, YU B, et al. Lie detection analysis based on the sample entropy of EEG[J]. Acta Electronica Sinica, 2017, 45(8): 1836-1841. (in Chinese)
10	王志坚, 常雪, 王俊元, 等. 排列熵优化改进变模态分解算法诊断齿轮箱故障[J]. 农业工程学报, 2018, 34(23): 59-66.
	WANG Z J, CHANG X, WANG J Y, et al. Gearbox fault diagnosis based on permutation entropy optimized variational mode decomposition[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(23): 59-66. (in Chinese)
11	ROSTAGHI M, AZAMI H. Dispersion entropy: A measure for time-series analysis[J]. IEEE Signal Processing Letters, 2016, 23(5): 610-614.
12	张学军, 景鹏, 何涛, 等. 基于变分模态分解的癫痫脑电信号分类方法[J]. 电子学报, 2020, 48(12): 2469-2475.
	ZHANG X J, JING P, HE T, et al. An epileptic electroencephalogram signal classification method based on variational mode decomposition[J]. Acta Electronica Sinica, 2020, 48(12): 2469-2475. (in Chinese)
13	YAN X A, JIA M P. Intelligent fault diagnosis of rotating machinery using improved multiscale dispersion entropy and mRMR feature selection[J]. Knowledge-Based Systems, 2019, 163: 450-471.
14	COSTA M, GOLDBERGER A L, PENG C K. Multiscale entropy analysis of complex physiologic time series[J]. Physical Review Letters, 2002, 89(6): 068102.
15	AZAMI H, ESCUDERO J. Coarse-graining approaches in univariate multiscale sample and dispersion entropy[J]. Entropy (Basel, Switzerland), 2018, 20(2): 138.
16	LIU R N, YANG B Y, ZIO E, et al. Artificial intelligence for fault diagnosis of rotating machinery: A review[J]. Mechanical Systems and Signal Processing, 2018, 108: 33-47.
17	ZHANG X Y, LIANG Y T, ZHOU J Z, et al. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM[J]. Measurement, 2015, 69: 164-179.
18	KRAMAR V A, ALCHAKOV V V, DUSHKO V R, et al. Application of support vector machine for prediction and classification[J]. Journal of Physics: Conference Series, 2018, 1015: 032070.
19	DWIVEDI R, DIKSHIT O. A comparison of particle swarm optimization (PSO) and genetic algorithm (GA) in second order design (SOD) of GPS networks[J]. Journal of Applied Geodesy, 2013, 7(2): 135-145.
20	张敏, 蔡振宇, 包珊珊. 基于EEMD-Hilbert和FWA-SVM的滚动轴承故障诊断方法[J]. 西南交通大学学报, 2019, 54(3): 633-639, 662.
	ZHANG M, CAI Z Y, BAO S S. Fault diagnosis of rolling bearing based on EEMD-Hilbert and FWA-SVM[J]. Journal of Southwest Jiaotong University, 2019, 54(3): 633-639, 662. (in Chinese)
21	车一鸣, 王冬梅, 王国兴, 等. 基于IMDE和ORF模型的断路器工况识别[J]. 组合机床与自动化加工技术, 2019(12): 85-90.
	CHE Y M, WANG D M, WANG G X, et al. Working condition identification of circuit breaker based on IMDE and ORF model[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2019(12): 85-90. (in Chinese)
22	LIU B, WANG R M, PENG Z Q, et al. Identification of denatured biological tissues based on compressed sensing and improved multiscale dispersion entropy during HIFU treatment[J]. Entropy (Basel, Switzerland), 2020, 22(9): 944.
23	任强, 官晟, 王凤军, 等. 基于EEMD和PSO-SVM的电机气隙偏心故障诊断[J]. 组合机床与自动化加工技术, 2021(2): 73-76, 85.
	REN Q, GUAN S, WANG F J, et al. Motor air-gap eccentricity fault diagnosis based on EEMD and PSO-SVM[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2021(2): 73-76, 85. (in Chinese)

编号	工况描述	数量	时间长度/s
a	正常工作状态(负载力4 kN)	58	7.1~8.1
b	负载力过小(约3 kN)	60	6.8~7.9
c	负载力过大,一级程度(约5 kN)	60	6.7~8.2
d	负载力过大,二级程度(约6 kN)	40	7.1~8.3
e	尖轨卡异物,出现摩擦振动现象	40	7.6~8.5
f	卡缺口,表示电路未接通	60	6.5~7.8
g	空载(杆件断裂)	58	7.5~8.3
h	摩擦连接器摩擦力不足,打滑振动	60	6.7~7.7
共计		436

编号	工况描述	数量	时间长度/s
a	正常工作状态(负载力4 kN)	58	7.1~8.1
b	负载力过小(约3 kN)	60	6.8~7.9
c	负载力过大,一级程度(约5 kN)	60	6.7~8.2
d	负载力过大,二级程度(约6 kN)	40	7.1~8.3
e	尖轨卡异物,出现摩擦振动现象	40	7.6~8.5
f	卡缺口,表示电路未接通	60	6.5~7.8
g	空载(杆件断裂)	58	7.5~8.3
h	摩擦连接器摩擦力不足,打滑振动	60	6.7~7.7
共计		436

分类器	预处理与特征提取方法	分类准确率/%
BP	EEMD+CCKC+ITMDE	90.2
k-NN	EEMD+CCKC+ITMDE	91.4
SVM	EEMD+CCKC+ITMDE	93.1

分类器	预处理与特征提取方法	分类准确率/%
BP	EEMD+CCKC+ITMDE	90.2
k-NN	EEMD+CCKC+ITMDE	91.4
SVM	EEMD+CCKC+ITMDE	93.1

分类器	分类准确率/%	运行时间/s
Grid-SVM	98.3	15.3
GA-SVM	98.85	12.5
PSO-SVM	100	9.9

基于改进时域多尺度散布熵与支持向量机的转辙机故障诊断

Fault Diagnosis of Railway Point Machine Based on Improved Time- Domain Multiscale Dispersion Entropy and Support Vector Machine

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 18

参考文献 23

相关文章 15

编辑推荐

Metrics

预处理方法	IMFs筛选方法	特征提取与分类方法	整体准确率/%
原始信号	—	ITMDE+PSO-SVM	86.78
EMD	CCKC	ITMDE+PSO-SVM	95.98
EEMD	CC	ITMDE+PSO-SVM	97.12
EEMD	CCKC	ITMDE+PSO-SVM	100

[1]	于建立, 吴传斌, 冷赫, 鲁志伟. 基于磁场分布特性的接地网故障诊断研究[J]. 电子学报, 2022, 50(3): 598-607.
[2]	吴国庆, 王罗胜斌, 庞晨, 李永祯, 王雪松. 雷达极化域变焦角反组合体对抗方法：抗冲淡式干扰[J]. 电子学报, 2022, 50(12): 2969-2983.
[3]	孙晨峰, 吕卫民, 戴洪德, 张浩晨. 一种基于TimeGAN和OCSVM的多元退化设备小子样数据增广方法[J]. 电子学报, 2022, 50(11): 2678-2687.
[4]	欧阳丹彤, 刘扬, 宋金彩, 王浩然, 张立明. 结合结构特征基于测试集重排序的故障诊断方法[J]. 电子学报, 2022, 50(1): 63-71.
[5]	杨国为, 万鸣华, 赖志辉, 张凡龙, 黄伟强. 具有合适拒识机制的高正确识别率分类器设计[J]. 电子学报, 2021, 49(8): 1569-1576.
[6]	罗忠涛, 夏杭, 卢琨, 何子述. 超视距雷达中距离-多普勒图的瞬态干扰自动识别方法[J]. 电子学报, 2021, 49(7): 1279-1285.
[7]	钱忠胜, 俞情媛, 宋涛, 朱懿敏, 祝洁, 赵畅. 基于支持向量机回归模型的测试用例生成与重用[J]. 电子学报, 2021, 49(7): 1386-1391.
[8]	张芳鑫, 王法松, 李睿, 左婷. GSSK‑VLC系统中基于SVM的LED选择算法[J]. 电子学报, 2021, 49(7): 1400-1405.
[9]	刘芳, 韩笑. 基于小波变换和深度网络的着陆地貌图像分类[J]. 电子学报, 2021, 49(11): 2171-2176.
[10]	鲍中新, 文成林, 马雪. 一种基于数据变化率的预处理及主元分析故障诊断方法[J]. 电子学报, 2021, 49(11): 2234-2240.
[11]	张彩霞, 王子涵, 文成林, 刘国文, 余伟. 样本空间基于多级高维特征表示的微小故障诊断[J]. 电子学报, 2020, 48(8): 1647-1654.
[12]	史聪伟, 赵杰煜, 陈瑜. 利用网格卷积特征的三维形变目标分类[J]. 电子学报, 2020, 48(4): 648-653.
[13]	张学军, 景鹏, 何涛, 孙知信. 基于变分模态分解的癫痫脑电信号分类方法[J]. 电子学报, 2020, 48(12): 2469-2475.
[14]	郑近德, 潘海洋, 童靳于, 刘庆运, 丁克勤. 自适应掩膜信号集成局部特征尺度分解及其应用[J]. 电子学报, 2020, 48(10): 2060-2070.
[15]	方佳艳, 刘峤. 具有同步化特征选择的迭代紧凑非平行支持向量聚类算法[J]. 电子学报, 2020, 48(1): 44-58.