Prediction of Substance Concentration in Simulated Moving Bed by Ultraviolet Sensor and Neural Network

Abstract

In chromatographic separation, the simulated moving bed (SMB) has been recognized as an important and the cleanest technology. Basically, the SMB is constructed of several columns in series, and can be operated continuously with a fixed switching time. Owing to the adsorption of different substances by the adsorbent, the concentration of the separated substance flowing in the columns changes with time. The success of chromatographic separation will be determined by the time change, substance flow rate, and other possible influencing factors. Therefore, if the concentration of the flowing substance in SMB columns can be sensed immediately, then the accurate control of the SMB can be executed. In this paper, the prediction of substance concentration in SMB chromatographic separation by using an ultraviolet (UV) sensor and a neural network (NN) is presented. In this study, a UV sensor was used to monitor the concentration of the substance, and the NN model was used to predict the substance concentration in real time. The predicted concentration can be used for the real-time control of the moving bed. From the research results shown, it is found that the real-time prediction of substance concentration by the NN based on the sensed UV light intensity can indeed reach a very high accuracy. This result is very promising for the future development of an SMB automatic control mechanism.