On-line Monitoring And Fault Diagnosis Of Circuit Breaker Based On IBREMD And Multi-kernel RVW

As the largest number of power equipment in the power system,the circuit breaker plays an important role in the protection of the power grid and the safe operation of the power system.In order to maintain the stable operation of the power grid,online monitoring and fault diagnosis of circuit breakers is particularly important.In the maintenance process of power equipment such as circuit breakers,most of the electric power industry in China adopts a planned maintenance method in advance prevention,or repairs after failure,which is not economical.If online monitoring is applied to the circuit breaker equipment,and continuous monitoring is carried out for important parametersand and alarmed in advance,this will help the equipment to run better,and the type of fault will be judged according to the changes of various important parameters.The data analysis formed can be used as the basis of condition judgment,thereby expanding the maintenance and repair cycle of equipment,reducing maintenance costs,extending service life,and achieving economical maintenance,which is very important for improving the reliability of the power system.In order to obtain the fault information from the vibration signals of circuit breakers accurately and quickly,a fault feature extraction method based on improved bandwidth restricted empirical mode decomposition is proposed,and the fault diagnosis of circuit breakers is realized by combining with the multiple kernel relevance vector machine.For the limitation of the bandwidth restricted empirical mode decomposition in selecting the optimal bandwidth frequency,this method first establishes an optimization function to determine the optimal bandwidth restricted signal frequency,and then introduces the signal frequency in the process of empirical mode decomposition.The proposed method improves the frequency resolution by selecting the optimal bandwidth frequency of bandwidth restricted empirical mode decomposition,and can effectively analyze the vibration signals of normal and faults extracted from the circuit breaker.Then the quantum-behaved particle swarm optimization algorithm is used to determine the most suitable kernel coefficient of the multiple kernel relevance vector machine.The multiple kernel relevance vector machine is used to diagnose the fault of the circuit breaker.The test accuracy can achieve better results,which has good generalization ability and can be used to diagnose the mechanical fault of the circuit breaker.