For the current SF6 circuit breaker monitoring system takes a long time

and cannot accurately determine whether the SF6 circuit breaker operating mechanism failure occurs

affecting the safe and stable operation of the power grid.This article proposes for the first time that the BAS（beetle Antennae search

BAS） algorithm combing with the BP neural network to optimize the circuit breaker monitoring system.A beetle in the BAS algorithm was improved into a beetle population

and established this improved Beetle Antennae search-BP neural network（IBASBP） diagnosis algorithm.The experimental results show that

compared with the PSO-BP prediction model

GA-BP prediction model and the original BAS-BP model

the IBAS-BP model effectively avoids the possibility of the BP network falling into a local minimum and has a high prediction accuracy

better robustness.The number of iterations in this algorithm is only 38

and the average error is only 0.1%.According to this

six kinds of fault states

including jamming of the iron core of SF6 circuit breaker

low operating voltage

poor contact of auxiliary switch action

jamming of operating mechanism

malfunction of SF6 air pressure gauge.These six fault states can be accurately diagnosed in real time

effectively optimizing the circuit breaker detection system

which can provide a reference for realizing the intelligent online diagnosis of the grid switch state.