Fault diagnosis of induction motor based on information entropy fusion
A Han li, Shi Li-ping · 2010
A fault diagnosis method based on information entropy fusion of motor is presented in this paper. Fault feature are extracted though calculating information entropy of collected signal. To improve accuracy of diagnosis, stator current signal, axial vibration signal and radial vibration signal are collected. Based on these eigenvalue of each signal type, primary conclusion is obtained using Neural network. The Dempster combination rule is used to realize information fusion to achieve finally conclusion. The result of experiment shows that information entropy acts well as fault feature and when using multi sensor signal, the reliability of the fault diagnosis method is more accurate and certainty. As a result, the proposed method can improve the accuracy and reliability of fault diagnosis remarkably.