Application of a radial basis function (RBF) neural network forfault diagnosis in a HVDC system

摘要

The application of a radial basis function (RBF) neural networkn(NN) for fault diagnosis in an HVDC power system is presented in thisnpaper. To provide a reliable pre-processed input to the RBF NN, a newnpre-classifier is proposed. This pre-classifier consists of an adaptivenfilter (to track the proportional values of the fundamental and averagencomponents of the sensed system variables), and a signal conditionernwhich uses an expert knowledge base (KB) to aid the pre-classificationnof the signal. The proposed method of fault diagnosis is evaluated usingnsimulations performed with the EMTP package