Research On Mechanical Fault Diagnosis Of High Voltage Circuit Breakers Based On Vibration Analysis

High voltage circuit breakers(HVCBs)play a very important role in power system,which is responsible for the control and protection of the system.Under normal conditions,HVCBs control the switching operation of the equipment and circuit.When the system fails,it quickly cut off the fault line to prevent further expansion of the fault.Therefore,once HVCBs in the event of failure,it will directly endanger the operation reliability of the system,and may cause significant outage cost.According to domestic and international investigation,most faults of circuit breakers are of mechanical origin.So it is of great practical significance to study the mechanical fault diagnosis of HVCBs.Vibration signals generated during the opening/closing operations of the HVCBs contain some important information associated with the mechanical state of the breaker.In this paper,the mechanical state of HVCB is obtained by processing and analyzing the vibration signal of circuit breaker.The main research contents include three parts:signal acquisition,feature extraction and condition recognition.Firstly,the vibration signal acquisition system platform is designed and built based on the reasonable vibration sensor and signal acquisition equipment.This system is used to collect the vibration signals of HVCBs under different mechanical states.Secondly,aiming at the non-stationary and nonlinear characteristics of the vibration signals of HVCBs,a variational mode decomposition(VMD)algorithm is used to decompose the vibration signals into several intrinsic mode functions(IMFs).Then,the IMFs matrix is divided into submatrices to compute the local singular values.The maximum singular values of each submatrix are selected as the feature vector for fault diagnosis.Finally,a multi-layer classifier composed by two one-class support vector machines(OCSVM)and a support vector machine(SVM)is constructed to identify the fault type.Two layers of independent OCSVM are adopted to distinguish normal or fault conditions with known or unknown fault types,respectively.On this basis,SVM is used to recognize the specific fault type.The real diagnostic experiments are carried on a real SF6 HVCB with normal and three kinds of typical fault states.The results show that the VMD and local singular value decomposition method can accurately extract the fault characteristics of the circuit breakers and the recognition accuracy increases significantly when one-class classifier is used to diagnose mechanical fault of HVCBs.As the reliability of fault diagnosis is improved,the new method in this paper is of certain engineering application value.