城轨列车滚动轴承智能诊断的特征降维与随机森林方法

doi:10.13229/j.cnki.jdxbgxb20210312

摘要/Abstract

摘要：

针对城轨列车滚动轴承的智能故障诊断问题，提出了一种主成分分析（PCA）和随机森林（RF）相组合的新方法。应用滚动轴承振动信号的时域、频域特征指标构成21维特征原始向量，采用主成分分析方法对其进行降维处理，将降维后的有效特征数据输入随机森林模型，以此建立集成智能诊断模型。通过实验验证表明，相比于将原始特征向量直接输入支持向量机（SVMs）或RF的方法，对特征降维可以有效提高算法效率和准确率，PCA-RF方法具有更优的智能诊断能力，该方法可在诊断故障类型的基础上有效诊断出故障的程度，进一步反映滚动轴承故障类别的复杂度，对城轨列车滚动轴承故障诊断具有一定的价值。

关键词: 车辆工程, 主成分分析, 随机森林, 滚动轴承, 智能诊断

Abstract:

As for the fault diagnosis of rolling bearings for urban rail trains，an integrated intelligent diagnosis method was proposed based on principal component analysis （PCA） and random forest （RF）. Firstly， original feature vectors of 21 dimensions were extracted from time domain and frequency domain. Principal component analysis was then utilized to conduct dimension reduction accounting for the correlations within features. Finally， the size-reduced features act as the inputs of the RF. Consequently， an integrated intelligent diagnostic model called PCA-RF model was established. Experimental results demonstrate that the PCA-RF model is superior to other methods such as support vector machines and RF with original feature vectors as inputs， in terms of efficiency and effectiveness. In addition， the proposed method can obtain satisfied identifications among complicated bearing fault patterns which involve not only various fault locations but fault severity levels. In short， the PCA-RF model had a certain value in the diagnosis of rolling bearing faults of urban rail vehicles.

Key words: vehicle engineering, principal component analysis, random forest, rolling bearing, intelligent diagnosis

中图分类号:

U271

曹振,崔路瑶,雷斌,王婧旖,曹双胜. 城轨列车滚动轴承智能诊断的特征降维与随机森林方法[J]. 吉林大学学报(工学版), 2022, 52(10): 2287-2293.

Zhen CAO,Lu-yao CUI,Bin LEI,Jing-yi WANG,Shuang-sheng CAO. Feature dimensionality reduction and random forest method in intelligent diagnosis of rolling bearings for urban rail trains[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(10): 2287-2293.

图/表 8

图1

图2

图3

表1

图4

图5

表2

图6

参考文献 20

1	刘建强, 赵治博, 章国平, 等. 地铁车辆转向架轴承故障诊断方法研究[J]. 铁道学报, 2015, 37(1):30-36.
	Liu Jian-qiang, Zhao Zhi-bo, Zhang Guo-ping. Research on fault diagnosis method for bogie bearings of metro vehicle[J]. Journal of the China Railway Society, 2015, 37(1): 30-36.
2	姚德臣. 面向城轨列车走行安全的轴承在途故障诊断研究[D]. 北京: 北京交通大学轨道交通安全与控制国家重点实验室, 2015.
	Yao De-chen. Research on the Fault Diagnosis Algorithm for the Bearing of Urban Rail Train Running Gear[D]. Beijing: State Key Laboratory of Rail Transit Safety and Control, Beijing Jiaotong University, 2015.
3	左万里, 武小悦. 电子设备智能故障诊断技术发展综述[J]. 系统工程与电子技术, 2003, 25 (12) :1572-1575.
	Zuo Wan-li, Wu Xiao-yue. The summary of equipment technology development on intelligent fault diagnosis[J]. Systems Engineering and Electronics, 2003, 25(12): 1572-1575.
4	Cheng Wei-dong, Wang Tian-yang, Wang Jin-jiang, et al. Effects and its elimination method of envelope deformation on order analysis[J].Journal of Vibration Engineering, 2015, 28(3): 470-477.
5	丁锋, 何正嘉, 陈雪峰. 考虑损伤程度的设备运行可靠性研究[J]. 西安交通大学学报, 2010, 44(1): 36-40.
	Ding Feng, He Zheng-jia, Chen Xue-feng. Operational reliability evaluation of machinery considering component damaged severity[J]. Journal of Xi'an Jiaotong University, 2010, 44(1): 36-40.
6	林伟炜, 朱金福, 徐丽, 等. 基于主成分分析的飞机租赁业务成长研究[J]. 华东交通大学学报, 2019, 36(2): 69-76, 91.
	Lin Wei-wei, Zhu Jin-fu, Xu Li, et al. Study on aircraft leasing business growth level index based on principal component analysis[J]. Journal of East China Jiaotong University, 2019, 36(2): 69-76, 91.
7	王依宁, 解大, 王西田, 等. 基于PCA-LSTM模型的风电机网相互作用预测[J]. 中国电机工程学报, 2019, 39(14): 4070-4081.
	Wang Yi-ning, Xie Da, Wang Xi-tian, et al. Prediction of Interaction between grid and wind farms based on PCA-LSTM model[J]. Proceedings of the CSEE, 2019, 39(14): 4070-4081.
8	魏伟, 刘鹏. 基于字典原子优化的滑动轴承摩擦状态识别[J]. 电子测量与仪器学报, 2018, 32(5): 202-207.
	Wei Wei, Liu Peng. Sliding bearing friction state recognition based on optimization of dictionary atoms[J]. Journal of Electronic Measurement and Instrumentation, 2018, 32(5): 202-207.
9	彭虹. 中国食用菌出口影响因素主成分分析与变化趋势预测[J]. 中国农机化学报, 2020, 41(10): 125-131.
	Peng Hong. Study on export forecast of edible fungi in China based on principal component-grey prediction model[J]. Journal of Chinese Agricultural Mechanization, 2020, 41(10): 125-131.
10	傅军栋, 邹欢, 康水华. PSO-SVM算法在智能建筑环境监控系统中的应用[J]. 华东交通大学学报, 2016, 147(1): 121-127.
	Fu Jun-dong, Zou Huan, Kang Shui-hua. Application of PSO-SVM algorithm in environmental monitoring system of intelligent building[J]. Journal of East China Jiaotong University, 2016, 147(1): 121-127.
11	谢丽蓉, 杨欢, 李进卫, 等. 基于GA-ENN特征选择和参数优化的双馈风电机组轴承故障诊断[J]. 太阳能学报, 2021, 42(1): 149-156.
	Xie Li-rong, Yang Huan, Li Jin-Wei, et al. Bearing fault diagnosis using GA-ENN based feature selection and parameters optimization for doubly-fed wind turbine[J]. Acta Energiae Solaris Sinica, 2021, 42(1): 149-156.
12	古莹奎, 承姿辛, 朱繁泷. 基于主成分分析和支持向量机的滚动轴承故障特征融合分析[J]. 中国机械工程, 2015, 26(20): 2778-2783.
	Gu Ying-kui, Cheng Zi-xin, Zhu Fan-long. Rolling bearing fault feature fusion based on PCA and SVM[J]. China Mechanical Engineering, 2015, 26(20): 2778-2783.
13	陈亮, 周国模, 杜华强, 等. 基于随机森林模型的毛竹林CO₂通量模拟及其影响因子[J]. 林业科学, 2018, 54(8): 1-12.
	Chen Liang, Zhou Guo-mo, Du Hua-qiang, et al. Simulation of CO2 Flux and Controlling Factors in Moso Bamboo Forest Using Random Forest Algorithm[J]. Scientia Silvae Sinicae, 2018, 54(8): 1-12.
14	冯文卿, 眭海刚, 涂继辉, 等. 高分辨率遥感影像的随机森林变化检测方法[J]. 测绘学报, 2017, 46(11): 1880-1890.
	Feng Wen-qing, Sui Hai-gang, Tu Ji-hui, et al. Change detection method for high resolution remote sensing images using random forest[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(11): 1880-1890.
15	徐卓飞, 刘凯, 张海燕. 基于经验模式分解和主元分析的滚动轴承故障诊断方法研究[J]. 振动与冲击, 2014, 33(23): 133-139.
	Xu Zhuo-fei, Liu Kai, Zhang Hai-yan. A fault diagnosis method for rolling bearings based on empirical mode decomposition and principal component analysis[J]. Journal of Vibration and Shock, 2014, 33(23) : 133-139.
16	来海锋, 韩斌, 厉力华. 基于集成类随机森林方法的神经胶质瘤特征基因选择的研究[J]. 生物物理学报, 2010, 26(9): 833-845.
	Lai Hai-feng, Han Bin, Li Li-hua. An intefrated semi-random forests based approach to gene selection for glioma classification[J]. Acta Biophysica Sinica, 2010, 26(9): 833-845.
17	Svetnik V, Liaw A, Tong C . et al. Random forest: a classification and regression tool for compound classification and QSAR modeling[J]. Journal of Chemical Information and Computer Sciences, 2003, 43 (6) : 1947-1958.
18	李文峰, 戴豪民, 许爱强. 时域新指标和PNN 在滚动轴承故障诊断中的应用[J]. 机械科学与技术, 2016, 35(9): 1382-1386.
	Li Wen-feng, Dai Hao-min, Xu Ai-qiang. New time domain index and probabilistic neural network and their application in fault diagnosis of rolling bearing[J]. Mechanical Science and Technology for Aerospace Engineering, 2016, 35(9): 1382-1386.
19	冯桓榰, 张来斌, 石帅. 等 . 基于小波包熵的轴承状态监测和早期故障诊断技术[J]. 科学技术与工程, 2013, 13(18): 5177-5181.
	Feng Heng-zhi, Zhang Lai-bin, Shi Shuai . et al. Fault diagnosis of rolling bearing based on wavelet energy entropy[J]. Science Technology and Engineering, 2013, 13(18): 5177-5181.
20	张永祥, 李军, 孙云岭. 基于遗传算法和峰度最佳的滚动轴承故障诊断[J]. 振动与冲击, 2007, 26(8): 122-124.
	Zhang Yong-xiang, Li Jun, Sun Yun-ling. Study on design method of resonant demodulation apparatus for rolling elements bearing fault diagnosis[J]. Journal of Vibration and Shock, 2007, 26(8): 122-124.

相关文章 15

[1]	王克勇,鲍大同,周苏. 基于数据驱动的车用燃料电池故障在线自适应诊断算法[J]. 吉林大学学报(工学版), 2022, 52(9): 2107-2118.
[2]	曹起铭,闵海涛,孙维毅,于远彬,蒋俊宇. 质子交换膜燃料电池低温启动水热平衡特性[J]. 吉林大学学报(工学版), 2022, 52(9): 2139-2146.
[3]	隗海林,王泽钊,张家祯,刘洋. 基于Avl-Cruise的燃料电池汽车传动比及能量管理策略[J]. 吉林大学学报(工学版), 2022, 52(9): 2119-2129.
[4]	刘岩,丁天威,王宇鹏,都京,赵洪辉. 基于自适应控制的燃料电池发动机热管理策略[J]. 吉林大学学报(工学版), 2022, 52(9): 2168-2174.
[5]	李丞,景浩,胡广地,刘晓东,冯彪. 适用于质子交换膜燃料电池系统的高阶滑模观测器[J]. 吉林大学学报(工学版), 2022, 52(9): 2203-2212.
[6]	张佩,王志伟,杜常清,颜伏伍,卢炽华. 车用质子交换膜燃料电池空气系统过氧比控制方法[J]. 吉林大学学报(工学版), 2022, 52(9): 1996-2003.
[7]	池训逞,侯中军,魏伟,夏增刚,庄琳琳,郭荣. 基于模型的质子交换膜燃料电池系统阳极气体浓度估计技术综述[J]. 吉林大学学报(工学版), 2022, 52(9): 1957-1970.
[8]	裴尧旺,陈凤祥,胡哲,翟双,裴冯来,张卫东,焦杰然. 基于自适应LQR控制的质子交换膜燃料电池热管理系统温度控制[J]. 吉林大学学报(工学版), 2022, 52(9): 2014-2024.
[9]	胡广地,景浩,李丞,冯彪,刘晓东. 基于高阶燃料电池模型的多目标滑模控制[J]. 吉林大学学报(工学版), 2022, 52(9): 2182-2191.
[10]	陈凤祥,伍琪,李元松,莫天德,李煜,黄李平,苏建红,张卫东. 2.5吨燃料电池混合动力叉车匹配、仿真及优化[J]. 吉林大学学报(工学版), 2022, 52(9): 2044-2054.
[11]	武小花,余忠伟,朱张玲,高新梅. 燃料电池公交车模糊能量管理策略[J]. 吉林大学学报(工学版), 2022, 52(9): 2077-2084.
[12]	高青,王浩东,刘玉彬,金石,陈宇. 动力电池应急冷却喷射模式实验分析[J]. 吉林大学学报(工学版), 2022, 52(8): 1733-1740.
[13]	王奎洋,何仁. 基于支持向量机的制动意图识别方法[J]. 吉林大学学报(工学版), 2022, 52(8): 1770-1776.
[14]	王骏骋,吕林峰,李剑敏,任洁雨. 分布驱动电动汽车电液复合制动最优滑模ABS控制[J]. 吉林大学学报(工学版), 2022, 52(8): 1751-1758.
[15]	国强,李明松,周凯. 基于势距图与改进云模型的多模雷达分选[J]. 吉林大学学报(工学版), 2022, 52(8): 1904-1911.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

轴承状态	故障程度	故障尺寸 /（mm×mm）	样本数量/个	训练集/个	测试集/个	类别
正常	正常	0	300	250	50	1
内圈故障	轻度	0.5×0.3	300	250	50	2
	中度	1.0×0.3	300	250	50	3
	重度	2.0×0.3	300	250	50	4
外圈故障	轻度	0.5×0.3	300	250	50	5
	中度	1.0×0.3	300	250	50	6
	重度	2.0×0.3	300	250	50	7
滚动体故障	轻度	0.5×0.3	300	250	50	8
	中度	1.0×0.3	300	250	50	9
	重度	2.0×0.3	300	250	50	10

模型	SVM	PCA?SVM	RF	PCA?RF
故障类别	正确率/%
1	74.6	87.7	98	100
2	96.7	100	98	94.2
3	61.7	71.4	95.8	94
4	83.3	86.2	100	100
5	94.6	92.5	96	92
6	98	100	88.9	100
7	100	100	98	100
8	100	100	100	100
9	100	100	81	100
10	100	100	100	100
整体准确率/%	89.2	93.2	95.2	98
耗时/s	1.56	0.99	3.11	2.53