针对滚动轴承故障分类中全局信息损失和模态识别精度低的问题，提出一种中心修正投影算法（Center Modified Projection, CMP）结合改进的灰狼算法（Improved Grey Wolf Optimization, IGWO）优化支持向量机（Support Vector Machine, SVM）的滚动轴承故障分类方法。首先，融合样本高维空间全局分布信息和样本局部信息提出CMP降维算法，利用CMP的信息保留能力，实现轴承信号特征矩阵降维；其次借助钟形收敛曲线不同阶段下降速度的差异性特点以及前进式搜索和包围式搜索模式优化灰狼算法收敛性能，并利用改进后的灰狼算法实现SVM参数的自主寻优；最后采用优化后的SVM进行轴承故障分类识别。该方法充分结合了CMP的特征信息保留能力和SVM的小样本分类性能，有效减弱了特征冗余成分对诊断结果的影响。多组对比实验表明，本文所提方法能够能有效的去除冗余成分，较好的保留样本空间分布信息，具有较好的分类性能。
Abstract
Aiming at the problems of global information loss and low mode recognition accuracy in rolling bearing fault classification, a rolling bearing fault classification method based on center modified projection (CMP) dimensionality reduction algorithm and support vector machine (SVM) optimized by improved Gray Wolf algorithm (IGWO) was proposed. Firstly, The dimension reduction algorithm of CMP was proposed by combining the global distribution information of the high-dimensional space and the local information of the sample. The dimension reduction of bearing signal feature matrix was realized by using the information retention ability of CMP. Secondly, the bell-shaped convergence curve of normal distribution and the forward search and bounding search modes were introduced to optimize the performance of the gray Wolf algorithm. The independent optimization of SVM parameters was realized by using the improved gray Wolf algorithm. Finally, the optimized SVM is used for bearing fault classification and recognition. This method fully combines the feature information retention ability of CMP with the small sample classification performance of SVM. The influence of multiple sets of comparative experiments show that this proposed method can effectively remove redundant components, better retain sample space distribution information, has a good classification performance.
关键词
滚动轴承 /
特征降维 /
灰狼算法 /
支持向量机 /
故障分类
{{custom_keyword}} /
Key words
Rolling bearing /
Feature dimension reduction /
Gray Wolf algorithm /
Support vector machine /
Fault classification
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1]周亚波，池茂儒，蔡吴斌，等.铁道车辆异常振动噪声的原因分析[J].机械工程学报,2021,57(04):148-155.
ZHOU Ya-bo, CHI Mao-ru, CAI Wu-bin,et al. Causes Analysis of Abnormal Vibration and Noise in Railway Vehicles[J]. Journal of Mechanical Engineering, 2021,57(04):148-155.
[2]常书源，赵荣珍，陈 博，等.基于边界判别多流形分析的故障数据集降维方法[J].振动与冲击,2021,40(23):120-126.
CHANG Shu-yuan, ZHAO Rong-zhen, CHEN Bo,et al. Dimension reduction method of fault data set based on BDMA[J].Journal of Vibration and Shock,2021,40(23):20-126.
[3]李月仙，韩振南，黄宏臣，等.基于拉普拉斯特征映射的旋转机械故障识别[J].振动与冲击,2014,33(18):21-25+35.
LI Yue-xian, HAN Zhen-nan, HUANG Hong-chen,et al. Fault diagnosis of rotating machineries based on Laplacian eigenmaps[J].Journal of Vibration and Shock, 2014,33(18):21-25+35.
[4]HE X, Partha N. Locality preserving projection[C]//Proceedings of the 17th Annual Conference on Neural Information Processing Systems.Vancouver:NIPS,2003.
[5]Belkin M, Niyogi P. Laplacian Eigenmaps for Dimensionality Reduction and Data Representation[J].Neural Computation, 2003,15(6):1373-1396.
[6]Tenenbaum J B, Silva V, Langford J C. A global geometric framework for nonlinear dimensionality reduction[J]. Science,2000,290(5500):2319-2323.
[7]刘 锐，邹俊荣，任 超，等.采用规范化局部保持投影的轴承故障诊断方法[J].西安交通大学学报,2019,53(06):54-61.
LIU Rui, ZOU Jun-rong, REN Chao,et al. A Novel Diagnostic Approach for Bearing Faults Using Regularized Locally Maintaining Projections[J].Journal of Xi’an Jiaotong University,2019,53(06):54-61.
[8]王亚萍，李士松，葛江华，等.等距离映射和模糊C均值的滚动轴承故障识别[J].哈尔滨理工大学学报,2019,24(03):41-47.
WANG Ya-ping, LI Shi-song, GE Jiang-hua,et al. Rolling Bearing with Isometric Feature Mapping and Fuzzy C-means Fault Identification Method[J].Journal of Harbin University of Science and Technology,2019,24(03):41-47.
[9]赵孝礼，赵荣珍.全局与局部判别信息融合的转子故障数据集降维方法研究[J].自动化学报,2017,43(04):560-567.
ZHAO Xiao-li, ZHAO Rong-zhen. A Method of Dimension Reduction of Rotor Faults Data Set Based on Fusion of Global and Local Discriminant Information[J].Acta Automatica Sinica,2017,43(04):560-567.
[10]苏祖强，汤宝平，赵明航，等.基于多故障流形的旋转机械故障诊断[J].振动工程学报,2015,28(02):309-315.
SU Zu-qiang, TANG Bao-ping, ZHAO Ming-hang,et al. Rotating machinery fault diagnosis based on multiple fault manifolds[J].Journal of Vibration Engineering, 2015,28(02):309-315.
[11]王贡献，张 淼，胡志辉，等.基于多尺度均值排列熵和参数优化支持向量机的轴承故障诊断[J].振动与冲击,2022,41(01):221-228.
WANG Gong-xian, ZHANG Miao, HU Zhi-hui,et al. Bearing fault diagnosis based on multi-scale mean permutation entropy and parametric optimization SVM[J].Journal of Vibration and Shock,2022,41(01):221-228.
[12]袁宪锋，颜子琛，周风余，等.SSAE和IGWO-SVM的滚动轴承故障诊断[J].振动.测试与诊断,2020,40(02):405-413+424.
YUAN Xian-feng, YAN Zi-chen, ZHOU Feng-yu,et al. Rolling Bearing Fault Diagnosis Based on Stacked Sparse Auto-encoding Network and IGWO-SVM[J].Journal of Vibration, Measurement and Diagnosis, 2020,40(02): 405-413+424.
[13]Mirjalili S, Mirjalili S M, Lewis A. Grey Wolf Optimizer[J].Advances in Engineering Software, 2014,69: 46-61.
[14]WANG Z Y, YAO L G, CHEN G,et al. Modified multiscale weighted permutation entropy and optimized support vector machine method for rolling bearing fault diagnosis with complex signals[J].ISA Transactions,2021,114:470-484.
[15]Faramarzi A, Heidarinejad M, Mirjalili S,et al. Marine Predators Algorithm: A Nature-inspired Metaheuristic[J].Expert Systems With Applications,2020,152:113377-113377.
[16]路小娟，石成基.一种基于概率盒—HGWO优化SVM的滚动轴承故障诊断方法[J].振动与冲击,2021,40(22):234-241.
LU Xiao-juan, SHI Cheng-ji. Application of the P-box theory and HGWO-SVM in the fault diagnosis of rolling bearings[J].Journal of Vibration and Shock, 2021,40(22): 234-241.
[17]王望望，邓林峰，赵荣珍，等.集成KPCA与t-SNE的滚动轴承故障特征提取方法[J].振动工程学报,2021,34(02):431-440.
WANG Wang-wang, DEND Lin-feng, ZHAO Rong--zhen, et al. Fault feature extraction of rolling bearing integrating KPCA and t-SNE[J].Journal of Vibration Engineering, 2021,34(02): 431-440.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1571 KB)
