A Novel Sequential Learning Algorithm for RBF Networks and Its Application to Dynamic System Identification

The paper presents a novel sequential learning algorithm for radial basis function (RBF) networks referred to as synamic orthogonal structure adapation (DOSA) algorithm. The algorithm enables the RBF network to on-line adjust its structure and weights to the identified dynamics with a compact network structure. It makes use of the well-known idea of error reduction ration in orthogonal least squares (OLS) method for network pruning, and takes advantage of a sliding data window for monitoring system dynamics. Simulation results of nonlinear dynamic system identification demonstrate the adapative tracking ability and high learning speed of the proposed algorithm.