Fault diagnosis based on intelligent information processing technology

This paper proposes a fault diagnosis method based on intelligent information processing technology. It first extracts the characteristics of the primary sample signals with wavelet transforms, then optimizes the key characteristics to be the input parameters of the neural network using the genetic algorithm, and finally recognizes the state and classifies the characteristics with the neural network. This method not only effectively decreases the neural training time and neural calculation, but also enhances the correctness and reliability of the characteristic classification and fault diagnosis. The performance of the proposed method is proven by the bearing fault diagnosis experiment.