Food and Bioprocess Technology

, Volume 5, Issue 5, pp 1694–1705 | Cite as

Advanced Modeling of Food Convective Drying: A Comparison Between Artificial Neural Networks and Hybrid Approaches

  • Alessandra Saraceno
  • Maria Aversa
  • Stefano Curcio
Original Paper


In the present paper, three different approaches are proposed to model the convective drying of food. The performance of thin-layer, pure neural network and hybrid neural model is compared in a wide range of operating conditions, with two different vegetables, available either as cylinders or as slabs with different characteristic dimensions. It was found that the thin-layer model was adequate to describe food drying behavior, but it could be applied only as a fitting procedure. Pure neural models gave accurate predictions in some situations, but exhibited poor performance when tested outside the range of operating conditions exploited during their development. Finally, it was shown that hybrid neural models, formulated as a combination of both theoretical and neural network models, are capable of offering the most accurate predictions of system behavior with average relative errors never exceeding 10%, even in operating conditions unexploited during the definition of the neural part of the model. The results obtained proved that the hybrid neural paradigm is a novel and efficient modeling technique that could be used successfully in food processing, thus allowing drying process optimization to be achieved, and efficient and fast on-line controllers to be implemented.


Vegetables drying Models formulation Computational tools 



This work was supported by the Food Science & Engineering Interdepartmental Center of the University of Calabria and L.I.P.A.C., Calabrian Laboratory of Food Process Engineering (Regione Calabria APQ-Ricerca Scientica e Innovazione Tecnologica-I atto Integrativo, Azione 2-Laboratori Pubblici di Ricerca “Mission oriented” Interfiliera).


  1. Agarwal, M. (1997). Combining neural and conventional paradigms for modelling, prediction and control. International Journal of Systems Science, 28, 65–81.CrossRefGoogle Scholar
  2. Akpinar, E. K., Bicer, Y., & Yildiz, C. (2003). Thin layer drying of red pepper. Journal of Food Engineering, 59, 99–104.CrossRefGoogle Scholar
  3. Arrieche, L. S., & Sartori, D. J. M. (2008). Fluid flow effect and mechanical interactions during drying of a deformable food model. Drying Technology, 26, 54–63.CrossRefGoogle Scholar
  4. Bird, R. B., Stewart, W., & Lightfoot, E. N. (1979). Fenomeni di trasporto. Milano: Ambrosiana.Google Scholar
  5. Bon, J., Rossello, C., Femenia, A., Eim, V., & Simal, S. (2007). Mathematical modeling of drying kinetics for apricots: Influence of the external resistance to mass transfer. Drying Technology, 25, 1829–1835.CrossRefGoogle Scholar
  6. Boyaci, I. H., Sumnu, G., & Sakiyan, O. (2009). Estimation of dielectric properties of cakes based on porosity, moisture content, and formulations using statistical methods and artificial neural networks. Food and Bioprocess Technology, 2, 353–360.CrossRefGoogle Scholar
  7. Chin, S. K., Law, C. L., Supramaniam, C. V., & Cheng, P. G. (2009). Thin-layer drying characteristics and quality evaluation of air-dried Ganoderma tsugae Murrill. Drying Technology, 27, 975–984.CrossRefGoogle Scholar
  8. Curcio, S. (2010). A multiphase model to analyze transport phenomena in food drying processes. Drying Technology, 28(6), 773–785.CrossRefGoogle Scholar
  9. Curcio, S., Scilingo, G., Calabrò, V., & Iorio, G. (2005). Ultrafiltration of BSA in pulsating conditions: An artificial neural networks approach. Journal of Membrane Science, 246(2), 235–247.CrossRefGoogle Scholar
  10. Curcio, S., Calabrò, V., & Iorio, G. (2006). Reduction and control of flux decline in cross-flow membrane processes modeled by artificial neural networks. Journal of Membrane Science, 286(1–2), 125–132.CrossRefGoogle Scholar
  11. Curcio, S., Aversa, M., Calabro`, V., & Iorio, G. (2008). Simulation of food drying: FEM analysis and experimental validation. Journal of Food Engineering, 87, 541–553.CrossRefGoogle Scholar
  12. Curcio, S., Calabrò, V., & Iorio, G. (2009). Reduction and control of flux decline in cross-flow membrane processes modeled by artificial neural networks and hybrid systems. Desalination, 236(1–3), 234–243.CrossRefGoogle Scholar
  13. Curcio, S., Aversa, M., & Saraceno, A. (2010). Advanced modeling of food convective drying: A comparative study among fundamental, artificial neural networks and hybrid approaches. In B. C. Siegler (Ed.), Food Engineering. New York: Nova Publishers.Google Scholar
  14. Datta, A. K. (2007a). Porous media approaches to studying simultaneous heat and mass transfer in food processes. I: Problem formulations. Journal of Food Engineering, 80, 80–95.CrossRefGoogle Scholar
  15. Datta, A. K. (2007b). Porous media approaches to studying simultaneous heat and mass transfer in food processes. II: Property data representative results. Journal of Food Engineering, 80, 96–110.CrossRefGoogle Scholar
  16. Dehghani, A. A., Mohammadi, Z. B., Maghsoudlou, Y., & Mahoonak, A. S. (2009). Intelligent estimation of the canola oil stability using artificial neural network. Food and Bioprocess Technology doi: 10.1007/s11947-009-0314-8.
  17. Demuth, H., & Beale, M. (2000). Neural Network Toolbox User's Guide. Natick: The MathWorks.Google Scholar
  18. Doymaz, İ. (2004). Convective air drying characteristics of thin layer carrots. Journal of Food Engineering, 61, 359–364.CrossRefGoogle Scholar
  19. Erenturk, S., & Erenturk, K. (2007). Comparison of genetic algorithm and neural network approaches for the drying process of carrots. Journal of Food Engineering, 78, 905–912.CrossRefGoogle Scholar
  20. Erenturk, K., Erenturk, S., & Tabil, L. (2005). A comparative study for the estimation of dynamical drying behavior of Echinacea angustifolia: regression analysis and neural network. Computers and Electronics in Agriculture, 45, 71–90.CrossRefGoogle Scholar
  21. Ertekin, C., & Yaldiz, O. (2004). Drying of eggplant and selection of a suitable thin layer drying model. Journal of Food Engineering, 63, 349–359.CrossRefGoogle Scholar
  22. Fathi, M., Mohebbi, M., & Razavi, S. M. A. (2009). Application of image analysis and artificial neural network to predict mass transfer kinetics and colour changes of osmotically dehydrated kiwifruit. Food and Bioprocess Technology doi: 10.1007/s11947-009-0222-y.
  23. Hernàndez-Pèrez, J. A., Garcia-Alvarado, M. A., Trystram, G., & Heyd, B. (2004). Neural networks for the heat and mass transfer prediction during drying of cassava and mango. Innovative Food Science & Emerging Technologies, 5, 57–64.CrossRefGoogle Scholar
  24. Kahrs, O., & Marquardt, W. (2007). The validity domain of hybrid models and its application in process optimization. Chemical Engineering Processes, 46, 1054–1066.CrossRefGoogle Scholar
  25. Klaypradit, W., Kerdpiboon, S., & Singh, R. K. (2010). Application of artificial neural network to predict the oxidation of Menhaden fish oil obtained from Fourier transform infrared spectroscopy method. Food and Bioprocess Technology doi: 10.1007/s11947-010-0386-s.
  26. Kondjoyan, A., & Boisson, H. C. (1997). Comparison of calculated and experimental heat transfer coefficients at the surface of circular cylinders placed in a turbulent cross-flow of air. Journal of Food Engineering, 34, 123–143.CrossRefGoogle Scholar
  27. Krokida, M. K., Karathanos, V. T., Maroulis, Z. B., & Marinos-Kouris, D. (2003). Drying kinetics of burdens vegetables. Journal of Food Engineering, 59, 391–403.CrossRefGoogle Scholar
  28. Lewiki, P. P. (2000). Raoult's law based food water sorption isotherm. Journal of Food Engineering, 43, 31–40.CrossRefGoogle Scholar
  29. Liu, X., Chen, X., Wu, W., & Peng, G. (2007). A neural network for predicting moisture content of grain drying process using genetic algorithm. Food Control, 18, 928–933.CrossRefGoogle Scholar
  30. Lopez, J., Uribe, E., Vega-Galvez, M. M., Vergara, J., Gonzales, E., & Di Scala, K. (2010). Effect of air temperature on drying kinetics, vitamine c, antioxidant activity, total phenolic content, non-enzymatic browning and firmness of blueberries variety O’Neill. Food and Bioprocess Technology, 3(5), 772–777.CrossRefGoogle Scholar
  31. Marquez, C. A., & de Michelis, A. (2009). Comparison of drying kinetics for small fruits with and without particle shrinkage considerations, Food and Bioprocess Technology doi: 10.1007/s11947-009-0218-7.
  32. Martynenko, A. I., & Yang, S. X. (2006). Biologically inspired neural computation for ginseng drying rate. Biosystems Engineering, 5(3), 385–396.CrossRefGoogle Scholar
  33. Mitra, P., Barman, P. C., & Chang, K. S. (2008). Coumarin Extraction from Cuscuta Reflexa using supercritical fluid carbon dioxide and development of an artificial neural network model to predict the coumarin yield. Food and Bioprocess Technology doi: 10.1007/s11947-008-0179-2.
  34. Movagharnejad, K., & Nikzad, M. (2007). Modeling of tomato drying using artificial neural network. Computers and Electronics in Agriculture, 59, 78–85.CrossRefGoogle Scholar
  35. Ni, H., & Datta, A. K. (1999). Heat and moisture transfer in baking of potato slabs. Drying Technology, 17(10), 2069–2092.CrossRefGoogle Scholar
  36. Patnaik, P. R. (2010). Design consideration in hybrid neural optimization of fed-batch fermentation for PHB production by Ralstonia eutropha. Food and Bioprocess Technology, 3, 213–225.CrossRefGoogle Scholar
  37. Pilatowski, I., Mounir, S., Haddad, J., Thai Cong, D., & Allaf, K. (2010). The instant controlled pressure drop process as a new post-harvesting treatment of paddy rice: impacts on drying kinetics and end product attributes. Food and Bioprocess Technology doi: 10.1007/s11947-010-0332-6.
  38. Psichogios, D. D., & Ungar, L. H. (1992). A hybrid neural network–first principle approach to process modeling. AIChE Journal, 38(10), 1499–1511.CrossRefGoogle Scholar
  39. Rahman, S. M. A., Islam, M. R., & Mujumdar, A. S. (2007). A study of coupled heat and mass transfer in composite food products during convective drying. Drying Technology, 25, 1359–1368.CrossRefGoogle Scholar
  40. Reilly, D. L., & Cooper, L. N. (1990). An overview of neural networks: early models to real world systems. In S. F. Zornetzer, J. L. Davis, & C. Lau (Eds.), An introduction to neural and electronic networks (pp. 227–248). New York: Academic.Google Scholar
  41. Saraceno, A., Curcio, S., Calabrò, V., & Iorio, G. (2010). A hybrid neural approach to model batch fermentation of "ricotta cheese whey" to ethanol. Computers & Chemical Engineering, 34, 1590–1596.CrossRefGoogle Scholar
  42. Shittu, T. A., & Raji, A. O. (2008). Thin Layer Drying of African Breadfruits (Treculia Africana) Seeds: Modeling and Rehydration capacity. Food and Bioprocess Technology doi: 10.1007/s11947-008-0161-z.
  43. Uribe, E., Vega-Galvez, A., Di Scala, K., Oyanadel, R., Torrico, J. S., & Miranda, M. (2009). Characteristics of convective drying of Pepino fruits (Solanum Muricatum Ait.): Application of Weibull distribution. Food and Bioprocess Technology doi: 10.1007-009-0230-y.
  44. Uribe, E., Miranda, M., Vega-Galvez, A., Quispe, I., Claveria, R., & Di Scala, K. (2010). Mass transport modelling during the osmotic dehydration of Jumbo Squid (Dosidicus gigas): influence of temperature on diffusion coefficients and kinetic parameters. Food and Bioprocess Technology doi: 10.1007/s-010-0336-2.
  45. van Can, H. J. L., HAB, Te brake, Dubbelman, S., Hellinga, C., Luyben, K. C. A. M., & Heijnen, J. (1998). Understanding and applying the extrapolation properties of serial grey-box models. AIChE Journal, 44, 1071–1089.CrossRefGoogle Scholar
  46. Verbdryer, P., Nicolaï, B. M., Scheerlinck, N., & De Baerdemaeker, J. (1997). The local surface heat transfer coefficient in thermal food process calculations: A CFD approach. Journal of Food Engineering, 33, 15–35.CrossRefGoogle Scholar
  47. Zhang, J., & Datta, A. K. (2004). Some considerations in modeling of moisture transport in heating of hygroscopic materials. Drying Technology, 22(8), 1983–2008.CrossRefGoogle Scholar
  48. Zhang, G., Patuwo, B. E., & Hu, M. J. (1998). Forecasting with artificial neural network: The state of Art. International Journal of Forecasting, 14, 35–62.CrossRefGoogle Scholar
  49. Zhang, Q., Yang, S., Mittal, G., & Yi, S. (2002). Prediction of performance indices and optimal parameters of rough rice drying using neural networks. Biosystems Engineering, 83(3), 281–290.CrossRefGoogle Scholar
  50. Zhang, J., Datta, A. K., & Mukherjee, S. (2005). Transport processes and large deformation during baking of bread. AIChE Journal, 51(9), 2569–2580.CrossRefGoogle Scholar
  51. Zuniga, R., Rouaud, O., Boillereaux, L., & Havet, M. (2007). Conjugate heat and moisture transfer during a dynamic thermal treatment of food. Drying Technology, 25, 1411–1419.CrossRefGoogle Scholar

Copyright information

© Springer Science + Business Media, LLC 2010

Authors and Affiliations

  • Alessandra Saraceno
    • 1
  • Maria Aversa
    • 1
  • Stefano Curcio
    • 1
  1. 1.Department of Engineering ModelingUniversity of CalabriaRendeItaly

Personalised recommendations