期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：63
期号：2
出版社：Journal of Theoretical and Applied
摘要：In this paper, a hybrid technique is proposed for detecting the vibration signal of electric motor. The proposed hybrid technique is the combination of S-transformation algorithm and radial basis function neural network (RBFNN) technique. Initially, the pre-processing is applied in the electric motor signal such as normal and vibration. Then, the features of the signal are extracted by using S-transformation algorithm. With the help of the extracted features, the network is trained by back propagation training algorithm and the respective classes. The proposed hybrid technique is implemented in MATLAB working platform. The performance of the proposed hybrid technique is evaluated with three types of vibration signals. Performance of proposed method is analyzed by statistically measured and compared with S-transform-FFBNN and DWT-RBFNN techniques. From the comparative analysis, it has been shown that the proposed method has better accuracy, sensitivity and specificity.
关键词：Fault detection; pre processing; fault classification; S-transformation; FFBNN and RBFNN
