Identification of the Asynchronous Electric Motor Defects Based on Neural Networks

The article presents the method of increasing the efficiency of detection and evaluation of various types of faults of an asynchronous motor (AC motor) that is based on a complex consideration of the characteristic features of defects. Both electrical and mechanical causes of defects are considered. There are mentioned neural networks as a tool of developing a system of functional diagnostics. There are presented an analysis of the choice of the structure of neural network depending on the number of input variables and the amount of the experimental part for predicting AC motor's defects. The results of modeling of AC motor's predicted state are presented. The effectiveness of the proposed method of diagnostics after learning the network is confirmed by the convergence of results with the examples of test sample, which is not involved in the learning process and network setup.