Diagnosis of bearing fault of brushless DC motor based on dynamic neural network and orthogonal fuzzy neighborhood discriminant analysis

This paper presents a new approach for predicting the element rolling bearing defects. A set of fault scenarios (Outer race, inner race and ball rolling element) are designed and tested under different load and speed conditions. The experimental data set consists of the stator current and vibration spectrums are considered as fault indicators. Discrete wavelet transform (DWT) are used for feature extraction. To overcome feature redundancy, which affects diagnosis accuracy, the orthogonal fuzzy neighbourhood discriminative analysis approach is found to be the most effective and is implemented to reduce the dimensionality of original features. The selected features are used to train and test the dynamic neural network for fault classification. The results obtained from the real time simulation demonstrate the effectiveness and reliability of the proposed methodology in classifying the different faults faster and accurately.