Neural network-based identification of the SMB chromatographic process

Abstract

In this contribution, the identification problem for the control of nonlinear SMB chromatographic processes is addressed. For process control the flow rates of extract. desorbent, and recycle of the SMB-process, and the switching time are the natural choices for the manipulated variables. However, these variables influence the process in a strongly coupled manner. Therefore, a new set of input variables is introduced by a nonlinear transformation of physical inputs, such that the couplings are reduced considerably. The front positions of the axial concentration profile are taken as model outputs. Multilayer neural networks are utilized as approximate models of the nonlinear input-output behaviour. The correlation functions between the input and output signals and the gradient distribution of the model outputs with respect to the inputs are used to determine their structural parameters. To illustrate the effectiveness of the identification method, a laboratory scale SMB process is taken as an example. The simulation results of the identified model confirm a very good approximation of the first principles models and have a satisfactory long range prediction performance.