论文部分内容阅读
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 / 20compared 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 5classes 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.
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 the classification accuracy almost invariable. Accreditedly, the training time was shortened to 1 / 20compared 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 effectivel y.A simulation example to classify 5classes 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.