Note: Application of neural network modelling for the control of dewatering and impregnation soaking process (osmotic dehydration) Nota: Aplicación del sistema de simulación de redes neurales para el control de la deshidratación osmótica

Abstract

The aim of this work was to elaborate a predictive model of the mass transfer (water loss and solute gain) that occurs during dewatering and soaking by using neural network modelling. Two separate feedforward networks with one hidden layer were used (for water loss and solute gain respectively). Model validation was carried out on results obtained previously, which dealt with agar gel soaked in sucrose solution over a wide experimental range (temperature, 30-70 °C; solu tion concentration, 30-70 g sucrose/100 g solution; time 0-500 min; agar concentration, 2-8%). The best results were obtained with three hidden neurons, which made it possible to predict mass transfer, with an accuracy at least as good as the experimental error, over the whole experimental range. The technological interest of such a model is related to a rapidity in simulation compa rable to that of a traditional transfer function, a limited number of parameters and experimental data, and the fact that no preliminary assumption on the underlying mechanisms was needed.

Keywords

modelling neural network soaking osmotic dehydration

References

Bishop C.M. (1994). Neural networks and their applications. Reviews on Scientific Instrumentation 65 (6): 1803-1832.

Dornier M. , Rocha Meir T. , Bardot I. , Decloux M. and Trystram G. (1993). Applications of neural computation for dynamic modelling of food processes; drying and microfiltration. In: Artificial Intelligence for Agriculture and food. Paris : EC2 ed. pp. 223-240.

Demuth H. and Beale M. ( 1993). Neural Network Toolbox for Matlab - User's Guide. Natrick, MA: The MathWorks Inc.

Hornik K. (1993). Some new results on Neural Network Approximation . Neural Network 6: 1069-1072.

Hornik K. , Stinchcombe M. and White H. (1989). Multilayer feedforward networks are universal approximators. Neural Network 2: 359-366.

Huang B. and Mujumdar A. (1993). Use of neural networks to predict industrial dryers performances. Drying Technology 11: 525-541.

Freeman J.A. and Skapura D.M. (1992). Neural Networks. New York: Addison Wesley.

Latrille E. , Corrieu G. and Thibault J. (1993). pH prediction and final fermentation time determination in lactic acid batch fermentations. Escape 2, Computer Chemical Engineering 17: 423-428.

Le Maguer M. (1988). Osmotic dehydration: review and future directions . In: Proceedings of Symposium on Progress in Food Preservation Processes. Vol 1. Brussels. pp. 283-309.

10.

Linko P. and Zhu Y.H. (1992). Neural networks for real time variable estimation and prediction in the control of glucoamylase fermentation, Progress in Biochemistry 27: 275-283.

11.

Narendra K.S. and Parthasaraty K. (1990). Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks 1 (1): 4-27.

12.

Raoult-Wack A.L. (1994). Recent advances in the osmotic dehydration of foods. Trends in Food Science and Technology 5 (8): 255-260.

13.

Raoult-Wack A.L. , Guilbert S. , Le Maguer M. and Rios G. (1991). Simultaneous water and solute transport in shrinking media. Part 1: application to dewatering and impregnation soaking analysis (osmotic dehydration). Drying Technology 9 (3): 589-612.

14.

Rosenblatt F. (1958). The perceptron: a probabilistic model for information storage and organisation in the brain. Psychology Review 65: 386-408.

15.

Rumelhart D. and Zipner D. (1985). Feature discovering by competitive learning. Cognitive Science 9: 75-112.

16.

Saurel R. , Raoult-Wack A.L. , Guilbert S. and Rios G. (1994). Mass transfer during osmotic dehydration of apples. part 1: fresh plant tissue. International Journal of Food Science and Technology 29: 531-542.

17.

Torreggianni D. (1993). Osmotic dehydration in fruit and vegetable processing . Food Research International 26: 59-68.