Aero-engine fault diagnosis applying new fast support vector algorithm
Aero-engine fault diagnosis applying new fast support vector algorithm
-
摘要: A new fast learning algorithm was presented to solve the large-scale support vector machine (SVM) training problem of aero-engine fault diagnosis.The relative boundary vectors (RBVs) instead of all the original training samples were used for the training of the binary SVM fault classifiers.This pruning strategy decreased the number of final training sample significantly and can keep classification accuracy almost invariable.Accordingly,the training time was shortened to 1/20 compared with basic SVM classifier.Meanwhile,owing to the reduction of support vector number,the classification time was also reduced.When sample aliasing existed,the aliasing sample points which were not of the same class were eliminated before the relative boundary vectors were computed.Besides,the samples near the relative boundary vectors were selected for SVM training in order to prevent the loss of some key sample points resulted from aliasing.This can improve classification accuracy effectively.A simulation example to classify 5 classes of combination fault of aero-engine gas path components was finished and the total fault classification accuracy reached 96.1%.Simulation results show that this fast learning algorithm is effective,reliable and easy to be implemented for engineering application.Abstract: A new fast learning algorithm was presented to solve the large-scale support vector machine (SVM) training problem of aero-engine fault diagnosis.The relative boundary vectors (RBVs) instead of all the original training samples were used for the training of the binary SVM fault classifiers.This pruning strategy decreased the number of final training sample significantly and can keep classification accuracy almost invariable.Accordingly,the training time was shortened to 1/20 compared with basic SVM classifier.Meanwhile,owing to the reduction of support vector number,the classification time was also reduced.When sample aliasing existed,the aliasing sample points which were not of the same class were eliminated before the relative boundary vectors were computed.Besides,the samples near the relative boundary vectors were selected for SVM training in order to prevent the loss of some key sample points resulted from aliasing.This can improve classification accuracy effectively.A simulation example to classify 5 classes of combination fault of aero-engine gas path components was finished and the total fault classification accuracy reached 96.1%.Simulation results show that this fast learning algorithm is effective,reliable and easy to be implemented for engineering application.
-
[1] XU Qihua,SHI Jun.Fault diagnosis for aero-engine applying a new multi-class support vector algorithm[J].Chinese Journal of Aeronautics,2006,19(3):175-18. [2] XU Qihua,SHI Jun.Some studies in aero-engine fault diagnosis using support vector machines[J].Acta Aeronautica et Astronautica Sinica,2005,26(6):687-690.(in Chinese) [3] XU Qihua,SHI Jun.Aero-engine fault diagnosis based on support vector machine[J].Journal of Aerospace Power,2005,20(2):298-302.(in Chinese) [4] XU Qihua,SHI Jun.New multi-class support vector algorithm and its application in fault diagnosis[J].Acta Simulata Systematica Sinica,2005,17(11):2766-2768,2784.(in Chinese) [5] WEI Xunkai,LU Cheng,WANG Cheng.Applications of support vector machines to aeroengine fault diagnosis[J].Journal of Aerospace Power,2004,19(6):844-848.(in Chinese) [6] HAO Ying,SUN Jianguo,YANG Guoqing,et al.The application of support vector machines to gas turbine performance diagnosis[J].Chinese Journal of Aeronautics,2005,18(1):15-19. [7] WANG Xuhui,HUANG Shengguo,SHU Ping.Remote diagnosis of aeroengine's fault using LS-SVM[J].Mechanical Science and Technology,2007,26(5):595-599.(in Chinese) [8] YANG Jun,XIE Shousheng,YU Dongjun.Aero-engine fault diagnosis based on support vector machine[J].Mechanical Science and Technology,2005,24(1):123-126.(in Chinese) [9] Haykin S,YE Shiwei,SHI Zhongzhi.Neural networks:a comprehensive found,second edition[M].Beijing:China Machine Press,2004.(in Chinese) [10] Cristianini N,Shawe-Taylor J,LI Guozheng et al.An introduction to support vector machines and other kernel-based learning methods[M].Beijing:Publishing House of Electronic Industry,2004.(in Chinese) [11] Almeida M B,Braga A,Braga J P.SVM-KM:Speeding SVMs learning with a priori cluster selection and k-means //Proceedings of the Sixth Brazilian Symposium on Neural Networks.Washington,DC,USA:IEEE Computer Society,2000:162-167. [12] XU Hongmin,WANG Ruopeng,ZHANG Huainian.Fast classification algorithm for support vector machine[J].Journal of Beijing Institute of Petro-Chemical Technology,2009,17(4):55-58.(in Chinese) [13] AN Jinlong,WANG Zhengou.Pre-extracting support vectors for support vector machine[J].Computer Engineering,2004,30(10):10-11,48. [14] HE Qiang,XIE Zongxia,HU Qinghua.Neighborhood based sample and feature selection for SVM classification learning[J].Neurocomputing,2011,74(10):1585-1594. [15] LI Honglian,WANG Chunhua,YUAN Baozong.An improved SVM:NN-SVM[J].Chinese Journal of Computers,2003,26(8):1015-1020.(in Chinese) [16] LI Honglian,WANG Chunhua,YUAN Baozong.A learning strategy of SVM used to large training set[J].Chinese Journal of Computers,2004,27(5):715-719.(in Chinese) [17] YANG Weihua.Aero-engine modelling and fault diagnosis .Nanjing:Nanjing University of Aeronautics and Astronautics,2000.(in Chinese)
点击查看大图
计量
- 文章访问数: 1621
- HTML浏览量: 1
- PDF量: 582
- 被引次数: 0