Quality Modeling of Chemical Product Based on a New Chaotic Elman Neural Network

An improved Elman neural network, the hybrid feedback Elman neural network is presented for the modeling of unknown delay and high-order nonlinear system. The stability of the improved Elman network is proved in the sense of Lyapunov stability theory, and then chaos searching is imported to train it, make BP algorithm can skip the local minimum and find the global minimum easily. Modeling and prediction for the product quality of a certain propylene rectifying column with the new Elman network and algorithm, Simulation results show that the new network and the strategy can improve the network´s training speed and the predictive precision of the product quality index effectively.