论文信息 - Neural Networks as a Tool for Gray Box Modelling in Reactive Distillation

Neural Networks as a Tool for Gray Box Modelling in Reactive Distillation

In this paper we discuss the use of neural networks as a tool for gray box modelling of the reactive distillation column. The basic idea is to replace certain correlations for the calculation of physical properties by neural networks. Different architectures as radial basis function networks and feedforward networks are compared and their approximation abilities are demonstrated.

[1] J. A. Leonard,et al. Radial basis function networks for classifying process faults , 1991, IEEE Control Systems.

[2] Design of a Combined Mixing Rule for the Prediction of Vapor−Liquid Equilibria Using Neural Networks , 1999 .

[3] Rajamani Krishna,et al. Modelling reactive distillation , 2000 .

[4] Sebastian Engell,et al. Optimal operation of a semi-batch reactive distillation column , 2000 .

[5] Jürgen Gmehling,et al. Einsatz von Katalysatorpackungen für die Herstellung von Methylacetat durch reaktive Rektifikation , 1994 .

[6] Aage Fredenslund,et al. Artificial neural networks as a predictive tool for vapor-liquid equilibrium , 1994 .

[7] Kurt Hornik,et al. Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[8] J. MacQueen. Some methods for classification and analysis of multivariate observations , 1967 .

[9] Ashish Dwivedi,et al. Potential applications of artificial neural networks to thermodynamics: vapor–liquid equilibrium predictions , 1999 .