Prognostic of Electrical Motor Vibration Signals: a Hybrid Technique

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-transformFFBNN and DWT-RBFNN techniques. From the comparative analysis, it has been shown that the proposed method has better accuracy, sensitivity and specificity.