Leakage Current Sensor and Neural Network for  MOA Monitoring

Abstract

Metal-oxide arrester (MOA) has been widely used in electric power systems. The leakage current monitoring of MOA can not only detect the MOA’s running state continuously and intelligently but also reduce the unexpected outage of the equipment, which is also beneficial to the stability of the grid. The MOA loses its protection function due to various faults caused by excessive leakage current in actual running. This article studies the monitoring method of MOA based on leakage current sensor and back propagation (BP) neural network. At first, we design a novel leakage current sensor to acquire the leakage current of MOA. Then, the leakage current measurement of MOA based on harmonic analysis is proposed. Finally, the strong training ability of the BP neural network is used to train some key parameters that can reflect the aging of MOA so as to monitor the MOA state. The experimental results show that the leakage current acquired from the simulation is close to the actual leakage current that needs to be measured. It is also shown that the proposed method has good anti-interference and can effectively monitor the aging of MOA. Through the training of the BP neural network, the experiments prove that the training method in this article is superior to other neural network training methods obviously.