This paper describes neural network models for the prediction of the concentration profile of a hydrochloric acid recovery process consisting of double fixed-bed ion exchange columns. The process is used to remove the Fe2+ and Fe3+ ion from the pickling liquor, resulting in increasing the acid concentration for reusing in the pickling process. Due to the complexity and highly nonlinearity of the process, the modeling of the process based on the first principle is difficult and involve too many unknown parameters. Therefore, an attractive alternative technique, neural network modeling, has been applied to model this system because of its ability to model a complex nonlinear process, even when process understanding is limited. The process data sets are gathered from a real hydrochloric acid recovery pilot plant and used for neural network training and validation. Backpropagation and Lenvenberg-Marquardt techniques are used to train various neural network architectures, and the accuracy of the obtained models have been examined by using test data set. The optimal neural network architectures of this process can be determined by MSE minimization technique. The simulation results have shown that multilayer feedforward neural network models with two hidden layers provide sufficiently accurate prediction of the concentration profile of the process.
Ahmad I, Berzins M, Mathematics and Computers in Simulation, 56, 115, 2001
Anderson D, McNeill G, Artificial Neural Networks Technology, A DACS State-of-the Art Report Kaman Sciences Corporation, 258 Genesse Street Utica, NY (Aug. 1992), 1992
Basu S, Henshaw PF, Biswas N, Kwan HK, "Prediction of Gas-Phase Adsorption Isotherms Using Neural Nets", The Canadian Journal Chemical Engineering, 80(August 2002)., 2002
BrianIII BF, Zwiebel I, "Numerical Simulation of a Fixed-bed Adsorption Dynamics by the Method of Line", Recent Progress in Adsorpion and Ion Exchange", AIChE Symposium Series., 83, 80 (Number 259).
Bureau of Industrial Environment Technology. Deparment of Industrial Works. Ministry of Industrial Works, Environment Management Gudeline for The Steel Processing Industry Pickling Process (April)/, 1999
Davis, Mark E., Numerical Methods and MOdeling for Chemical Engineers, John Wiley & Sons., 1984
Duong HM, Shallcross DC, "Ion Exchange Column Performance Model Incorporating Intra-Particle and Solution Phase Mass Transfer Phenomena", Department of Chemical Engineering, University of Melbourne.
Henry T, "Chromic Acid Recovery from Chrome Plating Rinse Water by Ion Exchange", Journal of The Chinese Institute of Chemical Engineers, 26(4), 253 (Jul. 1995).
Henry T, J. Chin. Inst. Chem. Eng., 25(2), 77, 1994
Kittisupakorn P, Polruksa N, Daosud W, Neural Networks Model for the Estimation of Melt Flow Rate and Density of Polymers, 9th APCChE Congress and CHEMECA, 2002
Petcherdsak J, Use of Multilayer Feedforward Networks for System Identification, Function Approximation, and Advanced Control, Thesis (M. Eng.), Department of Chemical Engineering, Faculty of Engineering, Chulalongkorn University, 1999
Ruthven DM, Douglas M, Principles of Adsorption and Adsorption Process, John Wiley & Sons., 1984
Sohn SH, Oh SC, Yeo YK, Korean J. Chem. Eng., 16, 368, 1999
Tien C, Adsorption Calculations and Modeling, Butterworth-Heinemann, 1994
Wong YW, Niedzwiecki JL, Recent Advance in Adsorption and Ion Exchange, AIChE Symposium Series, 78(219), 120, 1982
Worasinchai A, Adsorption Kinetics of An Ion Exchange Column in Fixed-Bed Operation : A Simple Model Approach, Thesis (M.Sci.), the Petroleum and Petrochemical College, Chulalongkorn University, 2001
Wutisatwongkul A, Improvement of Hydrochloric acid Recovery from Steel Pickling Liquor using ion Exchange Method, Thesis (M. Eng.), Department of Chemical Engineering, Faculty of Engineering, Chulalongkorn University, 2002
Yu DL, Gomn JB, Control Eng. Practice, 11, 1315, 2003