Research on Modeling of Improved Process Neural Network Based on KPCA and Discrete Walsh Transform

Process Neural Network (PNN) has an important significance in solving industry modeling problems which are related to time, but long time is cost on high dimension inputs nonlinear modeling problems. A new Improved Process Neural Networks based on KPCA and Walsh (IPNN-KPW) are proposed in this paper. KPCA method and discrete Walsh transform are used to reduce process neural network's time cost. Momentum factor and self-adapting learning rate are adopted to accelerate the astringency of the network and keep down network's oscillation. The IPNN-KPW is applied to modeling of Polyacrylonitrile (PAN) average molecular weight in polymerization. The effectiveness of the algorithm is verified by the results. A higher accuracy of model is obtained with less time.