Vertical quench furnace Hammerstein fault predicting model based on least squares support vector machine and its application

Abstract

Since large-scale vertical quench furnace is voluminous, whose working condition is a typically complex process with distributed parameter, nonlinear, multi-inputs/multi-outputs, close coupled variables, etc, Hammerstein model of the furnace is presented. Firstly, the nonlinear function of Hammerstein model is constructed by least squares support vector machines regression. A numerical algorithm for subspace system (singular value decomposition, SVD) is utilized to identify the Hammerstein model. Finally, the model is used to predict the furnace temperature. The simulation research shows this model provides accurate prediction and is with desirable application value.