针对旋转机械故障诊断中故障样本获取困难的现状，提出一种基于正则化核最大边界投影（Regularized Kernel Maximum Margin Projection, RKMMP）维数约简的滚动轴承故障诊断方法。该方法首先利用RKMMP对小样本、少标记信息的混合故障样本集进行训练降维，然后将降维后的低维敏感特征子集输入到核极限学习机（ Kernel Extreme Learning Machine, KLEM）分类器中进行故障识别。上述方法的特点是所提出的RKMMP能充分利用少量标记样本信息与大量无标记样本的故障信息，避免过学习的缺陷，同时通过添加正则化项克服小样本问题。滚动轴承故障模拟实验表明：该方法结合了RKMMP在维数约简和KLEM在模式识别上的优势，在一定程度上能提升故障诊断的泛化能力与识别精度。该研究可为解决好故障诊断中样本获取困难的问题，提供理论参考依据。
Abstract
Aiming at the present situation of fault samples’ acquisition which is difficult in the fault diagnosis of rotating machinery, a novel fault diagnosis method of the rolling bearing based on dimension reduction with Regularized Kernel Maximum Margin Projection (Regularized Kernel Maximum Margin Projection, RKMMP) is proposed. Firstly, in the method, using RKMMP to reduce the dimension of mixed fault data set of small samples and less labeled information. Then, after the dimension reduction, sensitive feature subset of low-dimensional is input into Kernel Extreme Learning Machine (Kernel Extreme Learning Machine, KLEM) classifier for training and fault identification. The characteristics of method is that the proposed RKMMP can make full use of labeled information of small samples and fault information of numerous unlabeled samples, and avoid over-fitted problem. At the same time, it add a regularization term to overcome the small sample problem. The experiments of rolling bearing fault simulation show that the method is a combination of RKMMP in dimension reduction and KLEM advantages in pattern recognition, and to a certain extent, it can improve the generalization ability of fault diagnosis and recognition accuracy. This study is able to solve the problem of samples’ acquisition which is difficult in the fault diagnosis, and it provides a theoretical based reference.
关键词
故障诊断 /
正则化核最大边界投影 /
核极限学习机分类器 /
维数约简
{{custom_keyword}} /
Key words
fault diagnosis /
Regularized Kernel Maximum Margin Projection(RKMMP) /
Kernel Extreme Learning Machine (KELM)classifier /
dimensionality reduction
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 张文义，于德介，陈向民. 基于信号共振稀疏分解与能量算子解调的轴承故障诊断方法[J]. 中国电机工程学报，2013, 33(20):111-118.
ZHANG Wen-yi, YU De-jie, CHEN Xiang-min. Fault diagnosis of rolling bearings based on resonance-based sparse signal decomposition and energy operator demodulating[J]. Proceedings of the CSEE, 2013, 33( 20): 111-118.
[2] 黄宏臣，韩振南，张倩倩，等. 基于拉普拉斯特征映射的滚动轴承故障识别[J]. 振动与冲击，2015(5): 128-134.
HUANG Hong-chen, HAN Zhen-nan, ZHANG Qian-qian，et al. Method of fault diagnosis for rolling bearings based on Laplacian eigenmap[J]. Journal of Vibration and Shock, 2015(5): 128-134.
[3] 李锋，汤宝平，陈法法. 基于线性局部切空间排列维数化简的故障诊断[J]. 振动与冲击，2012, 31(13): 36-40.
Li Feng, Tang Baoping, Chen Fafa. Fault diagnosis model based on dimension reduction using linear local tangent space alignment[J]. Journal of Vibration and Shock, 2012, 31(13): 36-40.
[4] 韦佳，杨创新，马千里，余国先. 基于局部重构与全局保持的半监督判别分析方法[J]. 华南理工大学学报(自然科学版)，2010, 38(7):45-49.
Wei Jia, Yang Chuangxin, Ma Qianli, et al. Semi-supervised discriminant analysis method based on local reconstruction and global preserving[J]. Journal of South China University of technology : Nature Science Edition, 2010, 38(7):44-49.
[5] Zhu X. Semi-Supervised Learning Literature Survey[J]. Computer Science, 2008, 37(1):63-77.
[6] He X, Cai D, Han J. Learning a Maximum Margin Subspace for Image Retrieval[J]. IEEE Transactions on Knowledge & Data Engineering, 2008, 20(2):189-201.
[7] Jiang L, Shi T, Xuan J. An intelligent fault diagnosis method of rolling bearings based on regularized kernel Marginal Fisher analysis[C]// Journal of Physics: Conference Series. 2012:597-604.
[8] Pima I, Aladjem M. Regularized discriminant analysis for face recognition[J]. Pattern Recognition, 2004, 37(9):1945-1948.
[9] Huang G B, Zhou H, Ding X, et al. Extreme learning machine for regression and multiclass classification.[J]. IEEE Transactions on Systems Man & Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man & Cybernetics Society, 2012, 42(42):513-29.
[10] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1-3):489-501.
[11] 陈绍炜，柳光峰，冶帅. 基于核极限学习机的模拟电路故障诊断研究[J]. 西北工业大学学报，2015, 33(02):290-294.
Chen Shaowei, Liu Guangfeng, Ye Shuai. A Method of Fault Diagnosis for Analog Circuit Based on KELM[J]. Journal of Northwestern Polytechnical University, 2015,33(02):290-294.
[12] Cai D, He X, Zhou K, et al. Locality Sensitive Discriminant Analysis.[C]// IJCAI. 2007:708-713.
[13] 杨望灿，张培林，吴定海，陈彦龙. 基于改进半监督局部保持投影算法的故障诊断[J]. 中南大学学报(自然科学版)，2015, 47(06):2059-2064.
YANG Wangcan, ZHANG Peilin, WU Dinghai, et al. Fault diagnosis based on improved semi-supervised locality preserving projections.[J] Journal of Central South University(Science and Technology), 2015, 47(06): 2059-2064.
[14] The Case Western Reserve University Bearing Data Center. http://csegroups.case.edu/bearingdata center/home.
[15] Chen F, Tang B, Chen R. A novel fault diagnosis model for gearbox based on wavelet support vector machine with immune genetic algorithm[J]. Measurement, 2013, 46(1):220-232.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(1497 KB)
