Research on R&D cost forecast of the life cycle based on wavelet neural network

Based on the analysis of the time frequency character of wavelet function and the learning capability of the artificial neural network, a method for R & D cost forecast of the life cycle is presented on the basis of wavelet neural network(WNN).The theoretical analysis and results of the MATLAB simulation show that the model and algorithm of the WNN are effective and superior to traditional BP neural network in its faster convergence and higher prediction accuracy.