Comparison of mathematical models and artificial neural network for prediction of moisture ration of orange slices during drying process

Document Type : Research Article

Authors

1 Assistant professor, Faculty of Chemical Engineering, Babol Noshirvani University of Technology

2 Assistant professor, Department of Chemical Engineering, Ayatollah Amoli Branch, Islamic Azad University, Amol, Iran

3 Professor, Faculty of Chemical Engineering, Babol Noshirvani University of Technology

Abstract

In present study, the thin- layer drying of orange slices in a laboratory scale hot-air dryer has been modeled. Drying experiments were conducted at three different temperatures of 50, 60 and 70°C, and two air velocities of 1.0 and 2.0 m/s. The statistical results of data showed the change of drying temperature and air velocity had significant effects on moisture ratio (p<0.05) but interaction effect of air velocity and temperature had insignificant effect on moisture ratio. Based on the results, the minimum moisture ratio of dried orange slices was obtained 5.3% when the dryer air temperature and velocity were 70°C and 2.0 m/s, respectively. After the end of experiments, the experimental data were fitted to the 7 well-known drying models. According to fitting results, Page’s model with determination coefficient R2-3 showed better performance to predict the moisture ratio. Also, this study used a feed forward back propagation neural network in order to estimate orange slices moisture ratio, based on the temperature, air velocity and time as input variables. In order to design this model, two main activation functions called tanh and purlin, widely used in engineering calculations, were applied in hidden and output layer, respectively. The artificial neural network with 3-20-1 topology and Levenberg-Marquardt training algorithm provided best results with the maximum determination coefficient (0.9994) and minimum Root of Mean Square Error (1.009×10-3) values. The results indicated the artificial neural network model was more accurate than Page’s model for prediction of moisture ratio of orange slices during drying process.

Graphical Abstract

Comparison of mathematical models and artificial neural network for prediction of moisture ration of orange slices during drying process

Highlights

  • In, this study focused on the effects of the temperature and air velocity on moisture ratio and dying kinetics.
  • Artificial neural network and mathematical models were applied to predict the moisture ratio of orange slices in drying process.
  • Artificial neural network model had better performance than mathematical model in prediction of orange slices moisture ratio.

Keywords

Main Subjects

References

[1] خوش‌تقاضا، م. ه.؛ تقی‌نژاد، ا. (1395) بررسی تأثیر پوشش نانو ذرات بر خواص انبارمانی پرتقال تامسون. فصلنامه علوم و صنایع غذایی، جلد 13، شماره 61، ص 121-109.
[2] برزنونی، ع.؛ آق‌خانی، م. ح.؛ مسکوکی، ع.؛ عباسپور فرد، م. ح. (1392) اثر پیش تیمار حرارت و اسانس‌های گیاهی بر خواص پس از برداشت پرتقال خونی. نشریه علوم باغبانی (علوم و صنایع کشاورزی)، جلد 27، شماره 4، ص 423-418.
[3] Ghaderi, A., Abbasi, S., Motevali, A., Minaei, S. (2012). Comparison of mathematical models and artificial neural networks for prediction of drying kinetics of mushroom in microwave-vaccum. Chem. Ind.  Chem. Eng. Q., 18, 283-293.
[4] Movagharnejad, K., Nikzad, M. (2007). Modeling of tomato drying using artificial neural network. Comput. Electron. Agric., 59, 78-85.
[5] Nwakuba, N. R., Chukwuezie, O. C., Osuchukwu, L. C. (2017). Modeling of drying process and energy consumption of onion (Ex-gidankwanoSpp.) slices in a hybrid crop dryer. American J Eng Res., 6, 44-55.
[6] Akoy, E. O. M. (2014). Experimental characterization and modeling of thin-layer drying of mango slices. Int. Food. Res. J., 21, 1911-1917.
[7] Aregbesola, O. A., Ogunsinaa, B. S., Sofolahana, A. E., Chimeb, N. N. (2015). Mathematical modeling of thin layer drying characteristics of dika (Irvingiagabonensis) nuts and kernels. Nigerian. Food. J., 33, 83-89.
[8] da Silva, W. P., e Silva, C. M.D.P.S., Gama, F. J.A., Gomes, J. P. (2014). Mathematical models to describe thin-layer drying and to determine drying rate of whole bananas. J. Saudi. Soc. Agric. Sci., 13, 67-74.
[9] Rayaguru, K., Routray, W. (2012). Mathematical modeling of thin layer drying kinetics of stone apple slices. Int. Food. Res. J., 19, 1503-1510.
[10] Onwude, D. I., Hashim, N., Janius, R. B., Nawi, N., Abdan, K. (2016). Evaluation of a suitable thin layer model for drying of pumpkin under forced air convection. Int. Food. Res. J., 23, 1173-1181.
[11] نایبندی آتشی، س.؛ مرتضوى، ع.؛ طباطبایی یزدی، ف.؛ محبی، م.؛ وریدی، م. ج. (1396) بهینه‌سازی فرایند آبگیری اسمزی و مدل‌سازی سینتیک انتقال جرم طی خشک‌کردن با هوای داغ گوشت شترمرغ. فصلنامهفناوری‌هاینوینغذایی، جلد 4، شماره 15، ص 76-65.
[12] Sonmete, M. H., Mengeş, H. O., Ertekin, C., Özcan, M. M. (2017). Mathematical modeling of thin layer drying of carrot slices by forced convection. J. Food. Meas. Charact., 11, 629-638.
[13] Lutovska, M., Mitrevski, V., Pavkov, I., Mijakovski, V., Radojčin, M. (2016). Mathematical modeling of thin layer drying of pear. Chem. Ind. Chem. Eng. Q., 22, 191-199.
[14] آل‌حسینی، ع.؛ سرابی جماب، م.؛ قرآنی، ب.؛ کدخدایی، ر.؛ وان گساسولاک، س. (1396) بررسی کارایی شبکه های عصبی مصنوعی در پیش‌بینی تأثیر غلظت پلیمر و ولتاژ فرایند الکتروپاشش بر ویژگی‌های فیزیکی ذرات. فصلنامه فناوری‌های نوین غذایی، جلد 4، شماره 16، ص 43-31.
[15] 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. Qual. Assur. Saf. Crop. Foods., 4, 93-101.
[16] مجیدزاده، ح.؛ عمادی، ب.؛ فرزاد، ع. (1394) پیش بینی محتوی رطوبت میوه کیوی در خشک کن خلاء با استفاده از روش شبکه عصبی مصنوعی. نشریه پژوهش‌های علوم و صنایع غذایی ایران، جلد 11، شماره 1، ص 117-107.
[17] Beigi, M., Torki Harchegani, M., Mahmoodi Eshkaftaki, M. (2017). Prediction of paddy drying kinetics: A comparative study between mathematical and artificial neural network modeling. Chem. Ind. Chem. Eng. Q., 23, 251-258.
[18] Abbaszadeh, A., Motevali, A., Khoshtaghaza, M. H., Kazemi, M. (2011). Evaluation of thin-layer drying models and neural network for describing drying kinetics of Lasagnas angustifolia L. Int. Food. Res. J., 18, 1321-1328.
[19] گنجه، م.؛ جعفری، م.؛ قنبری، و.؛ دزیانی، م.؛ عزتی، ر.؛ سلیمانی، م. (1391) مدل‌سازی سینتیک خشک کردن پیاز در یک خشک‌کن بستر سیال مجهز به کنترل‌کننده رطوبت با استفاده از روش‌های رگرسیونی، منطق فازی و شبکه‌های عصبی مصنوعی. مجله علوم تغذیه و صنایع غذایی ایران، جلد 7، شماره 5، ص 407-399.
[20] کریمی، ف.؛ دهقان‌نیا، ج.؛ قنبرزاده، ب.؛ رفیعی، ش. (1391) مدل‌سازی خشک‌کردن لایه نازک موز و بهینه‌سازی فرایند توسط شبکه عصبی مصنوعی. نشریه پژوهشهای صنایع غذایی، جلد 22، شماره 3، ص 348-347.
[21] AOAC, (2000). Official Methods of Analysis Association of Official Analytical Chemists, 17th edn. In:Cunnif, P. (Ed.)., Arlington, VA, USA, PP. 1-37.
[22] Kouchakzadeh, A., Haghighi, K. (2011). Modeling of vacuum-infrared drying of pistachios. Agric. Eng. Int: CIGR. J., 13, 1-6.
[23] Karlovic, S., Bosiljkov, T., Brncic, M., Jezek, D., Tripalo, B., Dujmic, F., Dzineva, I., Skupnjak, A. (2013). Comparison of artificial neural network and mathematical models for drying of apple slices pretreated with high intensity ultrasound. Bulg.  J. Agric. Sci., 19, 1372-1377.
[24] Yousefi1, A., Asadi, V., Nassiri, M., Niakousari, M., Khodabakhsh Aghdam, Sh. (2012). Comparison of Mathematical and Neural Network Models in the Estimation of Papaya Fruit Moisture Content. Philipp Agric Sci., 95, 246-251.
[25] Islam, M. D. R., Sablani, S. S., Mujumdar, A. S., (2003). Artificial neural network model for prediction of drying rates. J Dry Technol., 21, 1867–1884.
[26] یوسفی، ع.؛ قاسمیان، ن.؛ سالاری، ا. (1396) مدل‌سازى سینتیک خشک‌کردن برش‌هاى لیموترش به روش تابش مادون قرمز با استفاده از شبکه‌هاى عصبى GMDH هیبریدى. فصلنامه فناوری‌های نوین غذایی، جلد 5، شماره 1، ص 91-105.
 
Innovative Food Technologies
Volume 6, Issue 2
February 2019
Pages 161-174

Files

History

  • Receive Date: 15 April 2018
  • Revise Date: 21 June 2018
  • Accept Date: 25 June 2018

Share

How to cite

Statistics