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

Process neural network could handle the modeling problems of time related industry, but it needs a long time when the input dimension is high. In this paper, a new improved process neural network based on KPCA and Walsh (IPNNKPW) is proposed. Both KPCA method and discrete Walsh transform are used to reduce the time cost of process neural network. Meanwhile, both momentum factor and selfadapting learning rate are introduced to accelerate the astringency of the network and keep down network′s oscillation. IPNNKPW is applied to model polyacrylonitrile (PAN) average molecular weight in polymerization, whose results verify the effectiveness of the proposed algorithm.