Abstract:
Inspired by the idea of combining models to improve prediction accuracy and robustness,a new method for nonlinear soft sensing modeling of chemical processes is proposed.Fuzzy c means clustering (FCM) algorithm is used for separating a whole training data set into several clusters with different centers,each subset is trained by radial base function networks (RBFN) or partial least square algorithm (PLS). The degrees of membership is used for combining several models to obtain the finial result. The proposed method has been evaluated by a nonlinear function example and applied to a practical case of modeling product quality of hydrocracking fractionator. The obtained results demonstrate the promise of this approach for improving nonlinear soft sensing modeling.