有监督不相关局部Fisher判别分析故障诊断
|
摘要
针对现有流形学习理论用于旋转机械故障诊断存在识别精度不高的问题,提出基于有监督不相关局部Fisher判别分析(Supervised Uncorrelated Local Fisher Discriminant Analysis,SULFDA)的新型故障诊断方法。首先构造全面表征不同故障特征的时频域特征集,再利用有监督不相关局部Fisher判别分析将高维时频域故障特征集化简为区分度更好的低维特征矢量,并输入到K-近邻分类器中进行故障模式辨识。有监督不相关局部Fisher判别分析在类标签指导下最小化同类流形的离散度并最大化异类流形的离散度来实现类判别,还施加了不相关约束条件使所提取的特征统计不相关,提高了针对旋转机械的故障诊断精度。深沟球轴承故障诊断实验验证了该方法的有效性。
Facing on the crucial problem that the fault diagnosis accuracy of current manifold learning theories for rotating machinery is not high enough,a novel fault diagnosis method based on Supervised Uncorrelated Local Fisher Discriminant Analysis(SULFDA)is proposed in this paper.The time-frequency domain feature set is first constructed to completely characterize the property of each fault.Then,SULFDA is introduced to automatically compress the high-dimensional time-frequency domain fault feature sets of training and test samples into the low-dimensional eigenvectors with better discrimination.Finally,the low-dimensional eigenvectors of training and test samples are input into K-nearest neighbors classifier(KNNC)to carry out fault identification.SULFDA achieves good discrimination ability by minimizing the within-manifold scatter and maximizing the between-manifold scatter under the supervision of class labels.Also,an uncorrelated constraint is put on SULFDA to make the extracted features statistically uncorrelated.Therefore,SULFDA improves the fault diagnosis accuracy for rotating machine.The fault diagnosis experiment on deep groove ball bearings demonstrated the effectivity of proposed fault diagnosis method.
Facing on the crucial problem that the fault diagnosis accuracy of current manifold learning theories for rotating machinery is not high enough,a novel fault diagnosis method based on Supervised Uncorrelated Local Fisher Discriminant Analysis(SULFDA)is proposed in this paper.The time-frequency domain feature set is first constructed to completely characterize the property of each fault.Then,SULFDA is introduced to automatically compress the high-dimensional time-frequency domain fault feature sets of training and test samples into the low-dimensional eigenvectors with better discrimination.Finally,the low-dimensional eigenvectors of training and test samples are input into K-nearest neighbors classifier(KNNC)to carry out fault identification.SULFDA achieves good discrimination ability by minimizing the within-manifold scatter and maximizing the between-manifold scatter under the supervision of class labels.Also,an uncorrelated constraint is put on SULFDA to make the extracted features statistically uncorrelated.Therefore,SULFDA improves the fault diagnosis accuracy for rotating machine.The fault diagnosis experiment on deep groove ball bearings demonstrated the effectivity of proposed fault diagnosis method.
引文
[1]Tianhao Zhang,Jie Yang,Deli Zhao,et al.Linear local tangent space alignment and application to face recognition[J].Neurocomputing,2007,70(7-9):1 547—1 553.
[2]Feng Li,Jiaxu Wang,Baoping Tang,et al.Life grade recognition method based on supervised uncorrelated orthogonal locality preserving Projection and K-nearest neighbor classifier[J].Neurocomputing,2014,138:271—282.
[3]Hong Huang,Jiamin Liu,Hailiang Feng,et al.Ear recognition based on uncorrelated local Fisher discriminant analysis[J].Neurocomputing,2011,74(17):3 103—3 113.
[4]Xiaofei He,Shuicheng Yan,Yuxiao Hu,et al.Face recognition using Laplacianfaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(3):328—340.
[5]李锋,汤宝平,董绍江.基于正交邻域保持嵌入特征约简的故障诊断模型[J].仪器仪表学报,2011,32(3):621—627.Li Feng,Tang Baoping,Dong Shaojiang.Fault diagnosis model based on feature compression with orthogonal neighborhood preserving embedding[J].Chinese Journal of Scientific Instrument,2011,32(3):621—627.
[6]Sugiyama Masashi.Dimensionality reduction of multimodal labeled data by local Fisher discriminant analysis[J].Journal on Machine Learning Research,2007,8:1 027—1 061.
[7]李锋,汤宝平,宋涛,等.归一Laplacian矩阵有监督最优局部保持映射故障辨识[J].机械工程学报,2013,49(13):100—107.Li Feng,Tang Baoping,Song Tao,et al.Fault identification method based on normalized Laplacian-based supervised optimal locality preserving projection[J].Chinese Journal of Mechanical Engineering,2013,49(13):100—107.
[8]Songbo Tan.An effective refinement strategy for KNN text classifier[J].Expert Systems with Applications,2006,30(2):290—298.
[9]Wong W K,Zhao H T.Supervised optimal locality preserving projection[J].Pattern Recognition,2012,45(1):186—197.
[10]李城梁,王仲生,姜洪开,等.自适应Hessian LLE在机械故障特征提取中的应用[J].振动工程学报,2013,26(5):758—763.Li Chengliang,Wang Zhongsheng,Jiang Hongkai,et al.Adaptive Hessian LLE in mechanical fault feature extraction[J].Journal of Vibration Engineering,2013,26(5):758—763[EB/OL].
[11]Xiaofei He,Deng Cai,Shuicheng Yan,et al.Neighborhood preserving embedding[A].Proceedings of10th International Conference on Computer Vision[C].Beijing,China,2005:1 208—1 213.
[12]http://csegroups.case.edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearing-datacenter-website[EB/OL].
[13]王国彪,何正嘉,陈雪峰,等.机械故障诊断基础研究“何去何从”[J].机械工程学报,2013,49(1):63—72.Wang Guobiao,He Zhengjia,Chen Xuefeng,et al.Review of life prediction for mechanical major equipments[J].Chinese Journal of Mechanical Engineering,2013,49(1):63—72.
[2]Feng Li,Jiaxu Wang,Baoping Tang,et al.Life grade recognition method based on supervised uncorrelated orthogonal locality preserving Projection and K-nearest neighbor classifier[J].Neurocomputing,2014,138:271—282.
[3]Hong Huang,Jiamin Liu,Hailiang Feng,et al.Ear recognition based on uncorrelated local Fisher discriminant analysis[J].Neurocomputing,2011,74(17):3 103—3 113.
[4]Xiaofei He,Shuicheng Yan,Yuxiao Hu,et al.Face recognition using Laplacianfaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(3):328—340.
[5]李锋,汤宝平,董绍江.基于正交邻域保持嵌入特征约简的故障诊断模型[J].仪器仪表学报,2011,32(3):621—627.Li Feng,Tang Baoping,Dong Shaojiang.Fault diagnosis model based on feature compression with orthogonal neighborhood preserving embedding[J].Chinese Journal of Scientific Instrument,2011,32(3):621—627.
[6]Sugiyama Masashi.Dimensionality reduction of multimodal labeled data by local Fisher discriminant analysis[J].Journal on Machine Learning Research,2007,8:1 027—1 061.
[7]李锋,汤宝平,宋涛,等.归一Laplacian矩阵有监督最优局部保持映射故障辨识[J].机械工程学报,2013,49(13):100—107.Li Feng,Tang Baoping,Song Tao,et al.Fault identification method based on normalized Laplacian-based supervised optimal locality preserving projection[J].Chinese Journal of Mechanical Engineering,2013,49(13):100—107.
[8]Songbo Tan.An effective refinement strategy for KNN text classifier[J].Expert Systems with Applications,2006,30(2):290—298.
[9]Wong W K,Zhao H T.Supervised optimal locality preserving projection[J].Pattern Recognition,2012,45(1):186—197.
[10]李城梁,王仲生,姜洪开,等.自适应Hessian LLE在机械故障特征提取中的应用[J].振动工程学报,2013,26(5):758—763.Li Chengliang,Wang Zhongsheng,Jiang Hongkai,et al.Adaptive Hessian LLE in mechanical fault feature extraction[J].Journal of Vibration Engineering,2013,26(5):758—763[EB/OL].
[11]Xiaofei He,Deng Cai,Shuicheng Yan,et al.Neighborhood preserving embedding[A].Proceedings of10th International Conference on Computer Vision[C].Beijing,China,2005:1 208—1 213.
[12]http://csegroups.case.edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearing-datacenter-website[EB/OL].
[13]王国彪,何正嘉,陈雪峰,等.机械故障诊断基础研究“何去何从”[J].机械工程学报,2013,49(1):63—72.Wang Guobiao,He Zhengjia,Chen Xuefeng,et al.Review of life prediction for mechanical major equipments[J].Chinese Journal of Mechanical Engineering,2013,49(1):63—72.