خشک شدن همرفتی سیر (Allium sativum L.): رویکرد شبکه‌های عصبی مصنوعی برای مدل‌سازی فرآیند خشک کردن

نوع مقاله : مقاله پژوهشی لاتین

نویسنده

• مجید رسولی

گروه مهندسی بیوسیستم، دانشگاه بوعلی سینا.

https://doi.org/10.22067/ifstrj.v14i3.66235

چکیده

در این مطالعه، شبکه عصبی مصنوعی برای مدل‌سازی و پیش‌بینی میزان رطوبت سیر در طی خشک کردن سیر استفاده شد. برای این منظور شبکه عصبی مصنوعی پرسپترون چندلایه تحت‌عنوان پس انتشار پیشرو به‌کار گرفته شد. پارامترهای مهم از جمله دمای هوای خشک کردن (50، 60 و 70 درجه سانتی‌گراد)، ضخامت ورقه‌­ها (2، 3 و 4 میلی‌متر) و زمان خشک کردن به‌عنوان ورودی و محتوای رطوبت به‌عنوان خروجی شبکه در نظر گرفته شد. داده‌های آزمایشگاهی به‌دست آمده از فرآیند خشک کردن لایه نازک سیر برای آموزش و تست شبکه استفاده شد. توپولوژی بهینه 3-25-5-1 با الگوریتم LM و تابع آستانه TANSIG برای لایه‌ها بود. با این شبکه بهینه، مقدار R²  و خطای نسبی به‌ترتیب 9923/0 و 67/9 درصد بود. مقدار MC برای سیر را می‌توان با استفاده از شبکه عصبی، با میانگین خطای متوسط کمتر و ضریب تبیین بیشتر نسبت به مدل ریاضی ویبل پیش‌بینی کرد.

کلیدواژه‌ها

• شبکه‌های عصبی مصنوعی
• انتشار اولیه
• خشک کردن همرفتی
• سیر
• محتوای رطوبت

عنوان مقاله [English]

Convective drying of garlic (Allium sativum L.): Artificial neural networks approach for modeling the drying process

نویسنده [English]

• Majid Rasouli

Department of Biosystem Engineering, Faculty of Agricultural Engineering, Bu-Ali Sina University, Hamedan, Iran.

چکیده [English]

In this study, artificial neural networks (ANNs) was utilized for modeling and the prediction of moisture content (MC) of garlic during drying. The application of a multi-layer perceptron (MLP) neural network entitled feed forward back propagation (FFBP) was used. The important parameters such as air drying temperature (50, 60 and 70°C), slice thickness (2, 3 and 4 mm) and time (min) were considered as the input parameters, and moisture content as the output for the artificial neural network. Experimental data obtained from a thin-layer drying process were used testing the network. The optimal topology was 3-25-5-1 with LM algorithm and TANSIG threshold function for layers. With this optimized network, R2 and mean relative error were 0.9923 and 9.67 %, respectively. The MC (or MR) of garlic could be predicted by ANN method, with less mean relative error (MRE) and more determination coefficient compared to the mathematical model (Weibull model).

کلیدواژه‌ها [English]

• Artificial neural networks
• Back propagation
• Convective drying
• Garlic
• Moisture content

مراجع

Abbasi Souraki, B., & Mowla, D. (2008). Experimental and theoretical investigation of drying behaviour of garlic in an inert medium fluidized bed assisted by microwave. Journal of Food Engineering, 88(4), 438-449. doi:10.1016/j.jfoodeng.2007.12.034

 

AOAC. (1990). Official method of analysis of the Association of Official Analytical Chemists. NO. 934. 06, Arlington: Virginia, USA.

 

Brewester, J. (1997). Onions and Garlic. In: H.C. Wine(eds). The physiology of vegetable crops: CAB International, Cambridge. UK.

 

Chegini, G. R., Khazaei, J., Ghobadian, B., & Goudarzi, A. M. (2008). Prediction of process and product parameters in an orange juice spray dryer using artificial neural networks. Journal of Food Engineering, 84(4), 534-543. doi:10.1016/j.jfoodeng.2007.06.007

 

Demuth, H., & Beale, M. (2003). Neural Network Toolbox for Matlab-Users Guide Version 4.1. Natrick. New York, UAS: The Mathworks Press.

 

Erenturk, S., & Erenturk, K. (2007). Comparison of genetic algorithm and neural network approaches for the drying process of carrot. Journal of Food Engineering, 78(3), 905-912. doi:10.1016/j.jfoodeng.2005.11.031

 

Ertekin, C., & Yaldiz, O. (2004). Drying of eggplant and selection of a suitable thin layer drying model. Journal of Food Engineering, 63, 349-359.

 

Kerdpiboon, S., Kerr, W. L., & Devahastin, S. (2006). Neural network prediction of physical property changes of dried carrot as a function of fractal dimension and moisture content. Food Research International, 39(10), 1110-1118. doi:10.1016/j.foodres.2006.07.019

 

Khazaei, J., & Daneshmandi, S. (2007). Modeling of thin-layer drying kinetics of sesame seeds: mathematical and neural networks modeling. Int. Agrophysics, 21, 335-348.

 

Madamba, P. S., Driscoll, R. H., & Buckle, K. A. (1994). Shrinkage, density and porosity of garlic during drying. J Food Eng, 23(3), 309-319.

 

Midilli, A., Kucuk, H., & Yapar, Z. (2002). A new model for single–layer drying. Dry Technol, 20(7), 1503-1513.

 

Mittal, G., & Zhang, J. (2000). Prediction of temperature and moisture content of frankfurters during thermal processing using neural network. Meat Sci, 55(1), 13-24.

 

Movagharnejad, K., & Nikzad, M. (2007). Modeling of tomato drying using artificial neural network. Computers and Electronics in Agriculture, 59(1-2), 78-85. doi:10.1016/j.compag.2007.05.003

 

Nazghelichi, T., Kianmehr, M. H., & Aghbashlo, M. (2010). Prediction of carrot cubes drying kinetics during fluidized bed drying by artificial neural network. Journal of Food Science and Technology, 48(5), 542-550. doi:10.1007/s13197-010-0166-2

 

Poonnoy, P., Tansakul, A., & Chinnan, M. (2007). Artificial neural network modeling for temperature and moisture content prediction in tomato slices undergoing microwave-vacuum drying. Journal of food science, 72(1), E042-047. doi:10.1111/j.1750-3841.2006.00220.x

 

Rasouli, M., Seiiedlou, S., Ghasemzadeh, H. R., & Nalbandi, H. (2011). Convective drying of garlic (Allium sativum L.): Part I: Drying kinetics, mathematical modeling and change in color. Australian Journal of Crop Science, 5(13), 1707-1714.

 

Satish, S., & Pydi Setty, Y. (2005). Modeling of a continuous fluidized bed dryer using artificial neural networks. International Communications in Heat and Mass Transfer, 32(3-4), 539-547. doi:10.1016/j.icheatmasstransfer.2004.06.005

 

Sharma, G. P., & Prasad, S. (2006). Optimization of process parameters for microwave drying of garlic cloves. Journal of Food Engineering, 75(4), 441-446. doi:10.1016/j.jfoodeng.2005.04.029

 

Sharma, G. P., Prasad, S., & Chahar, V. K. (2009). Moisture transport in garlic cloves undergoing microwave-convective drying. Food and Bioproducts Processing, 87(1), 11-16. doi:10.1016/j.fbp.2008.05.001

 

Topuz, A. (2010). Predicting moisture content of agricultural products using artificial neural networks. Advances in Engineering Software, 41(3), 464-470. doi:10.1016/j.advengsoft.2009.10.003

 

Trelea, I. C., Courtois, F., & Trystram, G. (1997). Dynamic models for drying and wet-milling quality degradation of corn using neural networks. Drying Technol, 15, 1095-1102.

 

Zhang, Q., Yang, S., Mittal, G., & Yi, S. (2002). Ae-automation and emerging technologies:prediction of performance indices and optimal parameters of rough rice drying using neural networks. Biosystems Engineering, 83(3), 281.