[其它]Gear fault detection using artificial neural networks and support vector machines

Abstract 1>_$O|dE  
A study is presented to compare the performance of gear fault detection using artificial neural networks 7|Qb}[s  
(ANNs) and support vector machines (SMVs). The time-domain vibration signals of a rotating machine $IKN7  
with normal and defective gears are processed for feature extraction. The extracted features from original +Kmxo4p  
and preprocessed signals are used as inputs to both classifiers based on ANNs and SVMs for two-class u 'ng'j'  
(normal or fault) recognition. The number of nodes in the hidden layer, in case of ANNs, and the radial i(u zb<  
basis function kernel parameter, in case of SVMs, along with the selection of input features are optimised qvsfU*wo?  
using genetic algorithms (GAs). For each trial, the ANNs and SVMs are trained with a subset of the r
I)&.5^  
experimental data for known machine conditions. The trained ANNs and SVMs are tested using the w6 Y+Y;,'f  
remaining set of data. The procedure is illustrated using the experimental vibration data of a gearbox. The 9(&$Gwi  
roles of different vibration signals, obtained under both normal and light loads, and at low and high ,0L< w
a  
sampling rates, are investigated. The results compare the effectiveness of both types of classifiers without L7II>^"B  
and with GA-based selection of features and the classifier parameters. For most of the cases considered, the %[,^2s  
classification accuracy of SVM is better than ANN, without GA. With GA-based selection, the (^=kV?<  
performance of both classifiers are comparable, in most cases, with three selected features. However, for q9(O=7O]-  
SVMs with six features, 100% classification success is achieved in all test cases. The training time of SVMs 7Aw <:  
is substantially less compared to ANNs in all cases considered. The present classification accuracy 4pDZ +}p  
compares well with .. /|Gz<nSc  
*nM.`7g*[  

未注册仅能浏览部分内容，查看全部内容及附件请先 登录 或 注册