Optical fiber sensor system for monitoring leakage current of post insulators based on RBF neural network

With the construction and operation of China´s EHV and UHV power grid, the voltage level of transmission line has been increasing, and with the rapid development of industry and agriculture, and the increasing level of atmospheric contamination, pollution flashover has become a serious threat to the safe operation of the electric power system. Leakage current monitoring has been widely employed to estimate pollution level on high voltage insulators. Therefore, an optical fiber sensor system for monitoring leakage current of post insulators based on RBF neural network for pollution evaluation is introduced in this paper which contributes to design a practical used system for flashover predicting. This system is composed of a fiber optic sensor, humidity and temperature sensors, a signal processing module, a data collection module based on micro-controller, a wireless signal transmission module and power supply with solar panels and batteries. Measured data are analyzed by the RBF neutral work, which measures four parameters (amplitude, RMS, number of the impulse and relative humidity(RH)) reflecting the insulating property of an insulator and outputs the pollution level and risk level of pollution flashover. After enough of training, the outputs of the network show great agreement with the experiment results. And this system has been applied in actual operation.