A new condition monitoring and fault diagnosis system of induction motors using artificial intelligence algorithms

In this paper, a condition monitoring and fault diagnosis system for induction motors is proposed by integrating artificial intelligence algorithms: principal component analysis (PCA), genetic algorithm (GA) and an artificial neural network (ANN). As main diagnosis media of fault motor, three-direction vibration signals and three-phase stator current signals are selected to measure. Multi-sensor measurement results in lots of data transfer that makes on-line or continuous condition monitoring and fault diagnosis difficult. Data transform into feature information provides a solution. Features are calculated from many domains to keep original data information at the highest level. In order to avoid the curse of dimensionality phenomenon and improve fault identification accuracy rate, PCA and GA are employed to reduce the feature dimensionality of the measured data. PCA removes the relative features, and extracts the principal components (PCs) from the original features. Then the significant features are selected from the extracted features by GA as inputs to the neural network. GA is also used to optimize the ANN parameters. The efficiency of the proposed system is validated through monitoring and diagnosing induction motor conditions, and comparing with other systems. The results show good performance of the proposed system and promising application