Prediction of Head Rice Yield in Fixed Bed Drying Using Artificial Neural Networks

Document Type : Research Paper

Abstract

The objective of this research was the prediction of head rice yield (HRY) in fixed bed dryer by using artificial neural network approach. Several parameters affect on operation of fixed bed dryers that were considered as input variables for artificial neural network. These variables were: air relative humidity, air temperature, inlet air velocity, bed depth, initial moisture content, final moisture content and inlet air temperature. In total, 375 drying experiments were accomplished for creating of training and testing patterns by a laboratory dryer. Samples were separated from various depths of dryer and then dehulling and polishing operations were done by laboratory apparatues. HRY was measured for all the depths and average of them was considered as HRY for each experiment. Feed forward neural network and cascade forward neural network with Levenberg-Marquardt and Bayesians regulation back propagation algorithm were used for training of presented patterns. Results showed that the feed forward back propagation algorithm with topology of 7-7-7-1 and Levenberg-Marquardt training algorithm and similar activation functions for all of the layers (Sigmoid Tangent) predicted the HRY with coefficient of determination 0.9655 and mean absolute error 0.019 at different conditions of fixed bed paddy drying method. Results showed that the input air temperature and final moisture content had the strongest effect on HRY.

Keywords

20.1001.1.26454531.1386.8.2.10.0

References

Aguerre, R., Suarez, C. and Viollaz, P. E. 1986. Effect of drying on the quality of milled rice. J. Food Tech. 21, 75-80.

Ancheta, C. J. and Andales, S. C. 1990. Total milled and head rice recoveries of paddy as influenced by its physico-varietal characteristics. AMA. 21, 34-39.

Anon. 2004. Moisture Measurement-Unground Grain and Seeds. ASAE Standard S352.2 47th Ed. ST. Joseph. MI: USA.

Bandyopadhyay, S. and Roy, N. C. 1992. Rice Process Technology. Oxford and IBH Pub. Co. New Delhi. India.

Bonazzi, C., Du Peuty, M. A. and Themelin, A. 1997. Influence of drying conditions on the processing quality of rough rice. Drying Tech. 15 (3,4): 1141-1157.

Brooker, D. B., Bakker-Arkema F. W. and Hall C. W. 1992. Drying and Storage of Grain and Oilseeds. Van Nostrand Reinhold. N. Y.

Chen, H., Siebenmorgen, T. J. and Marks, B. P. 1997. Relating drying rate constant to reduction of long-grain head-rice yield. Trans. ASAE. 40(4): 1132-1139.

Dayhoff, J. E. 1990. Neural Networks Principles. Prentice-Hall International. USA.

Farkas, I., Remenyi, P. and Biro, A. 2000a. A neural network topology for modeling grain drying. Computers Electronics Agric. 26, 147-158.

Farkas, I., Remenyi, P. and Biro, A. 2000b. Modeling aspects of grain drying with a neural network. Computers Electronics Agric. 29, 99-113.

Girosi, F., Jones, M. and Poggio, T. 1995. Regularization theory and neural network architectures. Neural Computing. 7, 219-269.

Hagan, M. T. and Menhaj, M. B. 1994. Training feed forward networks with the marquardt algorithm. IEEE Trans. Neural Networks. 5(6): 989-993.

Hashemi Soleymani, S. J. 1997. Necessity of preparation and implementation of universal program in rice processing industrial. Research Report. 6th Symposium of Rice. Isfahan. Iran. (in Farsi)

Islam, M. R., Sablani, S. S. and Mujumdar, A. S. 2003. An artificial neural network model for prediction of drying rates. Drying Tech. 21(9): 1867-1884.

Juliano, B. O. 1993. Rice in Human Nutrition. Rome: Food and Nutrition Series. FAO. No. 26. International Rice Research Institute.

Khanna, T. 1990. Foundations of Neural Networks. Addison-Wesley Pub. Co. USA.

Khoshtaghaza, M. H. and Soleymani, M. 1999. Effect of drying parameters on rice fissuring. Agric. Sci. J. 5(20): 49-62. (in Farsi)

Kunni, D. and Levenspiel, O. 1991. Fluidization Engineering. Stoneham-Butterworth Heineman. USA.

Peyman, M. H., Tavakoli Hashjin, T. and Minaei, S. 2000. Determination of proper distance between plastic rollers of paddy huller for dehulling of three popular rice varieties in Gilan province. Agric. Sci. J. 5(20): 37-48. (in Farsi)

Peuty, M. A., Themelin, A., Cruz, J. F., Arnand, G. and Fohr, J. P. 1994. Improvement of Paddy Quality by Optimization of Drying Conditions. In: Roudolph, V. and Keey, P. B. (Eds.). Drying.

Sadeghi, M., Khoshtaghaza, M. H. and Khayyat, A. A. 2004. Principles of design and fabrication of laboratory vibration fluidized bed dryer for fluidization study of humid materials. Amir-Kabir J. (Mechanical Engineering and Dependent Branches). 15(58-b): 385-397. (in Farsi)

Shariatmadar, H.1997. Research Report of the 6^th Symposium of Rice. Isfahan, Iran. (in Farsi)

Teter, N. 1987. Paddy Drying Manual. Rome: Food and Nutrition Series. FAO. Italy.

Zbicincski, I. and Ciesielski, K. 2000. Extension of the neural networks operating range by the application of dimensionless numbers in prediction of heat transfer coefficients. Drying Tech. 18(3): 649-660.

Zbicincski, I., Strumillo, P. and Kaminski, W. 1996. Hybrid neural model of thermal drying in a fluidized bed. Computers Chemical Eng. 20, 695-700.

Zhang, Q., Yang, S. X., Mittal, G. S. and Yi, S. 2002. Prediction of performance indices and optimal parameters of rough rice drying using neural network. Biosystems Eng. 83(3): 281-290.

Food Engineering Research

Prediction of Head Rice Yield in Fixed Bed Drying Using Artificial Neural Networks

References

References

Volume 8, Issue 2 - Serial Number 2
January 0
Pages 135-156

Prediction of Head Rice Yield in Fixed Bed Drying Using Artificial Neural Networks

References

References

Volume 8, Issue 2 - Serial Number 2January 0Pages 135-156

Volume 8, Issue 2 - Serial Number 2
January 0
Pages 135-156