Nonlinear Predictive Control Based on Wavelet Neural Network Applied to Polypropylene Process

Abstract

A nonlinear adaptive predictive control strategy using orthogonal wavelet network model is presented. Based on a set of orthogonal wavelet functions, wavelet neural network performs a nonlinear mapping from the network input space to the wavelons output space in hidden layer. Its weight coefficients can be simply estimated by a linear least-square estimation algorithm. The excellent statistic properties of the weight parameters of wavelet network also can be obtained. A single input single output (SISO) nonlinear predictive control strategy is implemented in the simulation of a Polypropylene process.