Study of the Induction Motor Faulted Diagnosis Based on Information Fusion Technology
Liping Shi · Journal of China University of Mining and Technology · 2010
To improve accuracy of fault diagnosis using integrated motor multi-fault characteristic information,a fault diagnosis method of multi-fault characteristic information fusion was proposed,which include stator current signal,axial vibration signal and radial vibration signal. The measured data were processed by wavelet analysis to obtain the energy eigenvalue at each frequency branch which were defined as the criterion to diagnose the rotor fault. Dempster-Shafer (D-S) evidence theory was used to realize information fusion. Because the D-S theory failed to combine conflict evidences,a modified combination rule based on field background knowledge was presented to improve the accuracy of fault diagnosis. The experimental results show that the reliability of fault diagnosis is improved evidently,the accuracy of this diagnosis method reaches 90%.