Electrical Operation Test And Electrical Life Analysis Of AC Contactor

AC contactor is widely used in the electric power industry.It is mainly used to connect and disconnect the electrical equipment frequently.The reliability of the AC contactor is directly related to the safety of the equipment.With the increase of the number of operations,the life of AC contactor is decreasing and the failure is inevitable,due to the loss caused by the electrical stress and mechanical stress.If the judgment and replacement are made before the end of life,the reliability of the electric control system can be improved,and the safety of the electric equipment can be guaranteed.In this paper,the CJX2-9 AC contactor is the object,and the prediction of the residual electric life of the AC contactor is studied.Firstly,the electrical operation of AC contactor test device is introduced briefly.Focuses on the releasing time,the catching time,the arcing time,the accumulation of arc energy and three-phase contact resistance.Secondly,BP neural network and the mean impact value are descriped detailed.The accumulation of arc energy and the catching time are selected as inputs of the model by the method of MIV which are two main factors affecting the electrical life of the contactor.A neural network model is established to predict the residual life of AC contactor.Thirdly,initial weights and thresholds of BP neural network optimized by adaptive genetic algorithm s solve the local minima problem,and predict the electrical life of AC contactor.Finally,BP neural network model optimized by adaptive genetic algorithm(AGA-BP)has the highest prediction accuracy.The prediction errors of the models with unprocessed inputs,inputs processed by factor analysis and inputs processed by MIV are analyzed.The results show that MIV is suitable for predicting the electrical life of AC contactor.The test data of each sample is used as training sample and testing sample,and the maximum prediction error is less than 11%,so the model is acceptable in actual use.