Nonlinear adaptive predictive control based on orthogonal wavelet networks

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