Research On Fault Diagnosis And Maintenance Decision Of High Voltage Circuit Breaker

In recent years,with the continuous development and improvement of China’s power industry and the continuous improvement of people’s economic level,the social demand for electricity continues to increase.As one of the core components to ensure the safe and stable operation of power system,high voltage circuit breaker has been widely valued.With the development of on-line monitoring technology,it is possible to analyze the state of high voltage circuit breakers based on on-line monitoring data.In order to realize the economic maximization of the operation and maintenance of high-voltage circuit breakers,it is necessary to conduct in-depth research on the fault diagnosis and maintenance decision of high-voltage circuit breakers.Therefore,the research on fault diagnosis and maintenance decision of high voltage circuit breakers has become a hot topic.This paper studies the fault diagnosis and maintenance decision of high voltage circuit breaker based on online monitoring data.The main work is as follows:This paper introduces the structure,working principle and fault type of high voltage circuit breaker,analyzes the principle and technical difficulties of various online monitoring technologies,discusses the principle and limitation of various fault diagnosis methods,and summarizes the common maintenance decision methods and their shortcomings.On on-line monitoring,characteristics of loop coil current is analyzed in detail,and the relationship between the circuit breaker state and the characteristic value of coil current is explored.Considering the noise signal produced during the monitoring process,the principle of wavelet threshold de-noising is introduced to eliminate the noise,on this basis,a method of extraction of characteristic value of coil current is proposed,and the effectiveness of the proposed method are verified through the simulation analysis.On fault diagnosis,aiming at the small sample fault diagnosis problem of high voltage circuit breaker,the fault diagnosis method of high voltage circuit breaker based on the improved Bayesian algorithm is proposed.The method discretizes the circuit breaker coil current eigenvalue based on the probabilistic distribution of standard state,and selects the standard state of circuit breaker coil current eigenvalue by invasive weed optimization algorithm,and diagnosed it by Bayesian classifier.The effectiveness and superiority of the algorithm are verified by simulation analysisOn maintenance decision,a maintenance decision based on risk assessment model is applied to the high voltage circuit breaker.Weibull distribution is used to calculate the breaker failure rate under the condition of the different operation time,at the same time the breaker severity evaluation model is established,and comprehensive failure rate and severity index is established based on the risk assessment of circuit breaker maintenance decision model,the effectiveness is analyzed by an example circuit breaker.