WSVR-based fuzzy neural network with annealing robust algorithm for system identification

► Proposes fuzzy neural network (FNN) based on wavelet support vector regression (WSVR) approach for system identification. ► WSVR method with a wavelet kernel function is used to determine the number of fuzzy rules and the initial parameters of FNN. ► Apply an annealing robust learning algorithm (ARLA) to adjust the parameters of the WSVR-based FNN (WSVR-FNN). ► Demonstrate the performance of the WSVR-FNN for system identification using two nonlinear dynamic plants and a chaotic system. ► Illustrate the proposed WSVR-FNN has superiority over several offered FNNs even number of training parameters is much small.