Research On Fault Diagnosis In Rotor Bar Breaking Of Asynchronous Motor Based On Artificial Immune System

Induction motors are widely used in the industrial and agricultural production because of its simple structure, low price, high reliability and convenient maintenance. Once the system fails, it may cause other parts or even the whole system damaged, sometimes even causing serious accidents, resulting in huge losses of persons and property. Therefore, the reliability of the motor protection is of great significance.This paper discusses Artificial Immune Algorithm (AIS) based on the negative selection algorithm principle, a new type of fault diagnosis in rotor bar breaking of asynchronous motor is proposed.The main research work is as follows:First of all, this paper discuss the principle of fault diagnosis of broken rotor bars and describes that there are some characteristics appear in the steady-state stator current when it has broken bars faults. The steady-state stator current as a study object, mainly uses the stator current analysis, establish the simulation model of the operational status of wound induction motor under normal circumstances and under rotor fault by the software of MATLAB(SIMULINK). To collect asynchronous motor data, to establish appropriate broken for fault criterion, as the simulation data of the fourth chapter.Secondly, this paper studies the negative selection algorithm of the artificial immune algorithm in detail, based on the fundamental short comings of negative selection algorithm, researched and improved constant radius algorithm NSA, V-detector NS A and MO Algorithm NSA. Through the comparison of three algorithms, we know the MO Algorithm was developed with the aim to promote better coverage of nonself space with greater efficiency, meaning in this context:lowest number of detectors with the largest radius possible. The detectors should be arranged in the most appropriate manner to minimize the overlap between them.Finally, this article designs asynchronous motor fault diagnosis simulation experiment based on improved negative selection algorithm. Experimental results show that compared to traditional algorithms, MO Algorithm NSA in fault detection and diagnosis efficiency of diagnosis has greatly improved and better fault diagnosis.This paper studies wound rotor of induction motor fault by the improved negative selection algorithm, then digital simulation and experimental results show that the MO algorithm has a good effect on failure, and prove that the method applied is feasible.