تخمین محتوای رطوبتی خربزه درختی با استفاده از مدل‌سازی GMDH

نوع مقاله : مقاله پژوهشی لاتین

نویسندگان

• علیرضا یوسفی ¹
• ناصر قاسمیان ²

¹ دانشگاه فردوسی مشهد

² دانشگاه بناب

https://doi.org/10.22067/ifstrj.v1394i6.51651

چکیده

در این تحقیق یک مدل هیبریدی شبکه عصبی-GMDH جهت تخمین محتوای رطوبتی قطعات خربزه درختی در حین خشک‌شدن با هوای داغ در یک خشک‌کن کابینتی تعیین شد. برای این منظور پارامترهای زمان خشک‌‌کردن، ضخامت قطعات و دمای خشک‌کردن به‌عنوان ورودی تعریف گردید و مقدار نسبت رطوبتی (MR) به‌عنوان خروجی تخمین زده شد. دقیقاً 50 درصد داده‌ها جهت آموزش و 50 درصد دیگر برای تست کردن مدل استفاده شد. به‌علاوه، چهار مدل ریاضی مختلف بر داده‌های آزمایشگاهی برازش داده شدند و نتایج این مدل‌سازی با GMDH مقایسه گردید. مقدار ضریب تبیین (R2) و جذر میانگین مربعات خطا (RMSE) به‌دست آمده برای مدل GMDH به‌ترتیب  9960/0 و 0220/0 به‌دست آمد، درحالی‌که برای بهترین مدل ریاضی (مدل نیوتن) این مقادیر به‌ترتیب برابر 9954/0 و 0230/0 تعیین شد. پس می‌توان نتیجه گرفت که مدل‌سازی با GMDH کارایی بالاتری نسبت به مدل ریاضی در تخمین محتوای رطوبتی قطعات لایه نازک خربزه درختی دارد.

کلیدواژه‌ها

• خشک کردن
• GMDH
• خربزه درختی
• شبکه عصبی

عنوان مقاله [English]

Prediction of Papaya fruit moisture content using hybrid GMDH - neural network modeling during thin layer drying process

نویسندگان [English]

• Alireza Yousefi ¹
• Naser Ghasemian ²

¹ ferdowsi university of mashhad

² University of Bonab

چکیده [English]

In this work, a hybrid GMDH–neural network model was developed in order to predict the moisture content of papaya slices during hot air drying in a cabinet dryer. For this purpose, parameters including drying time, slices thickness and drying temperature were considered as the inputs and the amount of moisture ratio (MR) was estimated as the output. Exactly 50% of the data points were used for training and 50% for testing. In addition, four different mathematical models were fitted to the experimental data and compared with the GMDH model. The determination coefficient (R2) and root mean square error (RMSE) computed for the GMDH model were 0.9960 and 0.0220,and for the best mathematical model (Newton model) were 0.9954 and 0.0230, respectively. Thus, it was deduced that the estimation of moisture content of thin layer papaya fruit slices could be better modeled by a GMDH model than by the mathematical models.

کلیدواژه‌ها [English]

• Drying process
• GMDH
• Neural Network
• Papaya fruit

مراجع

Abdolrahimi, S., Nasernejad, B., Pazuki, G. 2014. Prediction of partition coefficients of alkaloids in ionic liquids based aqueous biphasic systems using hybrid group method of data handling (GMDH) neural network. Journal of Molecular Liquids. 191, 79-84.

Aghajani, N., Kashaninejad, M., Dehghani, A.A., Daraei Garmakhany, A. 2012. Comparison between artificial neural networks and mathematical models for moisture ratio estimation in two varieties of green malt. Quality Assurance and Safety of Crops & Food. 4, 93-101.

Aghdam, S., Yousefi, A., Mohebbi, M., Razavi, S., Orooji, A., Akbarzadeh-Totonchi, M. 2015. Modeling for drying kinetics of papaya fruit using fuzzy logic table look-up scheme. International Food Research Journal. 22, 1234-1239.

Ahmadi, H., Mottaghitalab, M., Nariman-Zadeh, N. 2007. Group method of data handling-type neural network prediction of broiler performance based on dietary metabolizable energy, methionine, and lysine. The Journal of Applied Poultry Research. 16, 494-501.

Akgun, N.A., Doymaz, I. 2005. Modelling of olive cake thin-layer drying process. Journal of Food Engineering. 68, 455-461.

Atashrouz, S., Pazuki, G., Kakhki, S.S. 2015. A GMDH-type neural network for prediction of water activity in glycol and Poly (ethylene glycol) solutions. Journal of Molecular Liquids. 202, 95-100.

De Oliveira, J.G., Vitoria, A.P. 2011. Papaya: Nutritional and pharmacological characterization, and quality loss due to physiological disorders. An overview. Food Research International. 44, 1306-1313.

Demirtas, C., Ayhan, T., Kaygusuz, K. 1998. Drying behaviour of hazelnuts. Journal of the Science of Food and Agriculture. 76, 559-564.

Dinani, S.T., Hamdami, N., Shahedi, M., Havet, M. 2014. Mathematical modeling of hot air/electrohydrodynamic (EHD) drying kinetics of mushroom slices. Energy Conversion and Management. 86, 70-80.

Erenturk, K., Erenturk, S., Tabil, L.G. 2004. 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.

Ghanadzadeh, H., Ganji, M., Fallahi, S. 2012. Mathematical model of liquid–liquid equilibrium for a ternary system using the GMDH-type neural network and genetic algorithm. Applied Mathematical Modelling. 36, 4096-4105.

Huang, Y., Chen, M. 2015. Artificial neural network modeling of thin layer drying behavior of municipal sewage sludge. Measurement. 73, 640-648.

Ivakhnenko, A. 1968. The group method of data handling-a rival of the method of stochastic approximation. Soviet Automatic Control. 13, 43-55.

Ivakhnenko, A. 1971. Polynomial theory of complex systems. Systems, Man and Cybernetics, IEEE Transactions on. 364-378.

Izadifar, M., Mowla, D. 2003. Simulation of a cross-flow continuous fluidized bed dryer for paddy rice. Journal of Food Engineering. 58, 325-329.

Kaleemullah, S., Kailappan, R. 2005. Drying kinetics of red chillies in a rotary dryer. Biosystems Engineering. 92, 15-23.

Kamiński, W., Tomczak, E., Strumill, P. 1998. Neurocomputing approaches to modelling of drying process dynamics. Drying technology. 16, 967-992.

Khazaei, N.B., Tavakoli, T., Ghassemian, H., Khoshtaghaza, M.H., Banakar, A. 2013. Applied machine vision and artificial neural network for modeling and controlling of the grape drying process. Computers and Electronics in Agriculture. 98, 205-213.

Kingsly, A.R.P., Singh, D.B. 2007. Drying kinetics of pomegranate arils. Journal of Food Engineering. 79, 741-744.

Koukouch, A., Idlimam, A., Asbik, M., Sarh, B., Izrar, B., Bah, A., Ansari, O. 2015. Thermophysical characterization and mathematical modeling of convective solar drying of raw olive pomace. Energy Conversion and Management. 99, 221-230.

Liebman, B. 1992. Nutritional aspects of fruit. Nut Action Newslett May. 10-11.

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.

Midilli, A., Kucuk, H., Yapar, Z. 2002. A new model for single-layer drying. Drying Technology. 20, 1503-1513.

Momenzadeh, L., Zomorodian, A., Mowla, D. 2011. Experimental and theoretical investigation of shelled corn drying in a microwave-assisted fluidized bed dryer using Artificial Neural Network. Food and bioproducts processing. 89, 15-21.

Movagharnejad, K., Nikzad, M. 2007. Modeling of tomato drying using artificial neural network. Computers and Electronics in Agriculture. 59, 78-85.

Nadian, M.H., Rafiee, S., Aghbashlo, M., Hosseinpour, S., Mohtasebi, S.S. 2015. Continuous real-time monitoring and neural network modeling of apple slices color changes during hot air drying. Food and bioproducts processing. 94, 263-274.

Najafzadeh, M. 2015. Neuro-fuzzy GMDH based particle swarm optimization for prediction of scour depth at downstream of grade control structures. Engineering Science and Technology, an International Journal. 18, 42-51.

Nariman-Zadeh, N., Jamali, A. 2007. Pareto genetic design of GMDH-type neural networks for nonlinear systems. In: Proc. of the International Workshop on InductiVe Modelling, Drchal J, Koutnik J,(eds.). Czech Technical University: Prague, Czech Republic, pp. 96-103, Citeseer.

Nikbakht, A.M., Motevali, A., Minaei, S. 2014. Energy and exergy investigation of microwave assisted thin-layer drying of pomegranate arils using artificial neural networks and response surface methodology. Journal of the Saudi Society of Agricultural Sciences. 13, 81-91.

Onwubolu, G.C. 2009. Hybrid self-organizing modeling systems. Springer.

Park, J., Sandberg, I.W. 1991. Universal approximation using radial-basis-function networks. Neural computation. 3, 246-257.

Park, K.J., Vohnikova, Z., Brod, F.P.R. 2002. Evaluation of drying parameters and desorption isotherms of garden mint leaves (Mentha crispa L.). Journal of Food Engineering. 51, 193-199.

Pazuki, G., Kakhki, S.S. 2013. A hybrid GMDH neural network to investigate partition coefficients of Penicillin G Acylase in polymer–salt aqueous two-phase systems. Journal of Molecular Liquids. 188, 131-135.

Powell, M.J. 1987. Radial basis functions for multivariable interpolation: a review. In: Algorithms for approximation, pp. 143-167, Clarendon Press.

Wang, Z., Sun, J., Liao, X., Chen, F., Zhao, G., Wu, J., Hu, X. 2007. Mathematical modeling on hot air drying of thin layer apple pomace. Food Research International. 40, 39-46.

Yousefi, A., Asadi, V., Nassiri, S.M., Niakousari, M., Aghdam, S.K. 2013a. Comparison of mathematical and neural network models in the estimation of papaya fruit moisture content. The Philippine Agricultural Scientist. 95, 186-191.

Yousefi, A., Niakousari, M., Moradi, M. 2013b. Microwave assisted hot air drying of papaya (Carica papaya L.) pretreated in osmotic solution. African Journal of Agricultural Research. 8, 3229-3235.