An intelligent PID controller based on variable structure radial basis function network

A sequential learning algorithm for constructing variable structure radial basis function (RBF) network is presented. The algorithm learns samples sequantially, with both network structure and connecting parameters are adjusted on-line. The resulting RBF network is used for system identification in PID control strategy. The RBF-network-based PID controller simplifies modeling procedure by learning input-output samples while keep the advantages of traditional PID controller simultaneously. Simulation results of ship course control simulation demonstrate the applicability and effectiveness of the intelligent PID control strategy.