Insulator fault diagnosis apparatus and method based on fuzzy cerebellar model neural network

The invention provides an insulator fault diagnosis apparatus and method based on a fuzzy cerebellar model neural network. The insulator fault diagnosis apparatus is composed of an MCU, a first pre-processing circuit, a second pre-processing circuit, a third pre-processing circuit, an electric field sensor, a leakage current sensor, and a temperature sensor, a remote transceiver module and a remote computer. The electric field sensor, the leakage current sensor and the temperature sensor collect signals; denoising processing is carried out based on a Kalman filter algorithm to obtain a featuresample with fault information; an insulator fault information training sample library is established; classification training is carried out on samples based on FCMAC; training is carried out by using a BP algorithm to obtain a weight value and a threshold value that enable network optimization to be realized; and when a new information sample is inputted into the network, a fault type of an insulator is determined rapid