Improved Dynamic Wavelet Process Neural Network and Its Application

To solve the problems of slow convergence speed and low accuracy of the process neural networks, this paper presents the tuning of the structure and parameters of a dynamic wavelet process neural network (DWPNN) using an improved particle swarm optimization (IPSO). A DWPNN with switches introduce to links is proposed. By tuning the structure and improving the connection weights of PNN simultaneously, it eliminates some ill effects introduced by redundant in features of DWPNN. The effectiveness of this method is proved by dynamic optimal design of RV (rot-vector) reducer.