Research on fault warning of AC filter in converter station based on RBF neural network

Abstract

AC filter in converter station is an important part of HVDC transmission system, and the tripping accident of AC filter will directly affect the transmission power of the DC transmission system. This paper presents a method for on-line identification of AC filter's health status based on the opening/closing current of AC filter's breaker. Firstly, a series of time domain feature and frequency domain feature of the opening/closing current of AC filter's breaker are defined. On this basis, radial basis function (RBF) neural network-based artificial intelligence method is used to identify the fault warning of AC filter. The results of an actual converter station show that the proposed method has high fault warning accuracy. It can alert staff to check and maintain AC filter before the abnormal status enlarges or causes adverse effects, and the occurrence of AC filter's tripping phenomenon can be reduced a lot.