مدل‌سازی پارامترهای کیفی توت سفید در فرآیند خشک شدن با استفاده از شبکه عصبی مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجو کارشناسی ارشد-دانشگاه شهرکرد

2 عضو هیات علمی دانشگاه شهرکرد

3 هیئت علمی- دانشگاه شهرکرد

4 هیئت علمی - دانشگاه شهرکرد

چکیده

توت سفید یکی از میوه‌های سرشار از قند مفید بوده و از راه‌های نگه‌داری این محصول خشک کردن می‌باشد. امروزه شبکه‌های عصبی مصنوعی در مدل‌سازی خشک‌کردن در حال رشد و توسعه است. پژوهش حاضر با هدف مدل‌سازی کیفیت خشک‌شدن توت سفید توسط شبکه عصبی انجام گردید. آزمایش‌های خشک‌کردن توسط خشک‌کن جریان هوای داغ در دو رطوبت اولیه  (1± 85% و 1±80%) و در سه دمای 50، 60 و70 درجه سلسیوس و سه جریان هوای 5/1، 2و 5/2 متر بر ثانیه در رطوبت هوای ثابت خشک گردید. به منظور مدل‌سازی از شبکه عصبی چند لایه (MLP) با توابع آستانه مختلف و تعداد نورون مختلف و الگوریتم آموزش (trainlm) برای آموزش شبکه‌ها استفاده گردید. نتایج نشان داد که شبکه عصبی با ساختار (3-8-3) با توابع آستانه لگاریتمی و تانژانت سیگموئید با ضریب تعیین (9998/0) و مقدار میانگین مربعات خطا (00002/0) در مقایسه با سایر ساختارهای شبکه، نتایج بهتری را ارائه می‌کند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Mulberry qualitative pramaters modelling in drying process using artificial neural networks

نویسندگان [English]

  • Mohammad reza Asghari 1
  • Rahim Ebrahimi 2
  • Bahram Hosseinzadeh 3
  • Davood ghanbarian 4
1
2
3
4
چکیده [English]

Mulberry (Morus alba) has been considered as one of the strategic fruits with high levels of useful sugar. Regarding to the advantages of artificial intelligence technology, the application of this technology has been developed extensively to modelling the required parameters in drying procedures.In this study, mulberry drying experiments were implemented in a hot air dryer in two initial moisture levels (%80±1-85%±1) three temperature levels of 50, 60 and 70 and three air speed levels of 1/5, 2 and 2/5 m/s in stable moisture. In order to model the quality of drying, (MLP) neural networks with various threshold and neurons as well as Levenberg-Marquardt algorithm and threshold function of tan-sigmoid were used to instruct networks. The results indicated that the best neural network layout with the structure of (3-12-3) and the threshold function of (Logsig and Purelin) indicate the best result compared to other topologies with the largest coefficient (0/9998) and lowest MSE (0/00002).

کلیدواژه‌ها [English]

  • Mulberry
  • Drying
  • modelling
  • Total dissolved solids
  • Acidity
Arslan, O., Erzengin, M., Sinan , S. & Ozensoy, O. (2004). Purification of mulberry (Morus alba L.) polyphenol oxidase by affinity chromatography and investigation of its kinetic and electrophoretic properties, Food chemistry. 88(3): 479-484.
Amirnejat, H., & Khoshtaghaza, M. (2011). Mathematical modeling of drying thin layer of edible mushrooms. In: Fifth National Congress of Agricultural Engineering and Mechanisation. 61-53. (In Farsi)
Behroozie khazayi, N. (2007). Using artificial neural network to predict the quality parameters raisins. M.Sc thesis Mechanics of Agricultural Machinery. Faculty of Agriculture. Tarbiat Modarres University. (In Farsi)
Bonazzi, C. & Dumoulin, E. (2011). Quality Changes in Food Materials as Influenced by Drying Processes. Modern Drying Technology Volume 3: Product Quality and Formulation, First Edition. Wiley-VCH Verlag GmbH & Co. KGaA.
Bowers, J. A. & Shedrow, C.B. (2000). Predicting stream water quality using artificial neural networks.WSRC-MS-2000-00112.
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: 534–543.
Dayhoff, J. E. (1990). Neural Network Principles. Prentice-Hall International, U.S.A.
Duke, J. A. (1983). Handbook of Energy Crops, Centrer for New Crops & Plants Products, Purdue University.
Doymaz, I. 2004. Pretreatment effect on sun drying of mulberry fruits (Morus.alba). J. Food engineering. 65: 205-209.
Esmaeili Adabi, M.,  Nikbakht, A, M., Motevali, A. & Mousavi Seyedi,S, R. (2013). Investigation of Black Mulberry Drying Kinetics Applying Different Pretreatments. Journal of Agricultural Science and Technology. 61: 23-44.
Fazaeli, M., Emam, Z., Omid, M. & Kalbasi, A. (2013). Prediction of the Physicochemical Properties of Spray-Dried Black Mulberry (Morus nigra) Juice using Artificial Neural Networks. Food Bioprocess Technol. 6:585–590.
Guine, R. (2006). Influence of drying method on density and porosity of pears. Food and Bioproducts Processing. 84(3): 179-185.
Hornik, K., Stinchcombe, M. & White, H. (1989). "Multilayer Feed Forward Networks Are Universal Approximators", Neural Networks. 2: 359-366.
Hoseini, Z. (1994). Conventional methods in food analysis. Shiraz University Press. (In Farsi)
Hoseini, Z. (2000). Common methods for food analysis. Tabriz University Press. (In Farsi)
Jamshidi, N., Hoseinpoor, A., Zaki, H., & Forooghirad, A. (2014). The use of artificial neural networks in evaluating the Hayward variety kiwifruit firmness to sonication. In: Twenty-first National Congress of Food Science and Technology. Shiraz University. (In Farsi)
Kianmehr, M. H. & Aghbashlo, M. (2011). Prediction of carrot cubes drying kinetics during fluidized bed drying by artificial neural network. J Food Sci Technol. 48(5): 542–550.
Krulis, M., Kuhnert, S., Leiker, M. & Rohm, H. (2005). Influence of energy input and initial moisture on physical properties of microwave-vacuum dried strawberries.
Kassem, A.S. (1998). Comparative studies on thin layer drying models for wheat. 13th international congress on agricultural engineering, Morocco. 6: 2-6.
Khoshtaghaza, M. H., Hosseinzadeh, B., Fayyazi, A. & Amirnejat, H. (2015). Prediction of thin layer drying of edible mushroom moisture content by feed forward artificial neural networks method. Journal of Food Science and Technology. 50(13): 171-182. (In Farsi)
Lahsasni, S., M. Kouhila & M. Mahrouz. (2004). Thin layer convective solar drying and mathematical modeling of prickly pear peel (Opuntia ficus indica). Journal of Food Engineering. 29: 211-224.
Martin-Diana, A., Rico, D., Barat, J.M. & Barry-Ryan, C. (2009). Orange juices enriched with chitosan: Optimisation for extending the shelf-life. Innovative Food Science and Emerging Technologies. 10:590–600.
Mokhtarian, M. & Shafafi, M. (2012). CRM to help predict the kinetics of osmotic dehydration process of neural network intelligent tools in a static state. In: Journal of Food Science and Technology. 7 (1): 73-61 (In Farsi).
Mokhtarian, M. & Coushki, F. (2013). Estimation of tomato drying parameters using artificial neural networks. In: Journal of Food Science and Technology. 1(1): 74-61. (In Farsi)
Prats-Montalban, J.M. & Ferrer, A. (2008). "Integration of Color and Textural Information in Multivariate Image Analysis: Defect Detection and Classification Issues", Journal of Chemometrics. 21 (2): 10-23.
Petrucci, V., Canata, N., Bolin, H. R., Fuller, G. & Stafford, A. E. (1974). Use of oleic acid derivatives to accelerate drying of Thompson seedless grapes, J. American oil chemistry. 51: 77-80.
Rahman, M. S. (2007). Handbook of food preservation .2nd ed. CRC press. P. 408,409,420.
Rahman, M. S. & Perera, C. O. (1999). Drying and food preservation. In Handbook of food preservation. Marcel Dekker New York. 173-216.
Saini, R.S., Sharma, K.D., Dhankhar, O.P. & Kaushik, R. A. (2001). Laboratory manual of analytical techniquesin in Horticulture. Agrobios. Publisher India. 135P.
Schalkoff, R. J. (1997). Artificial neural networks, McGraw-Hill.
Sacmi, C. (1989). "From Technology Through Machinery to Kilns for SACMI Tile, Italy", SACMI Press.
Tzempelikos, D. A., Vouros, A. P., Bardakas, A. V., Filios, A. E. & Margaris, D. P. (2014). Case studies on the effect of the air drying conditions on the convective drying of quinces. Case Studies in Thermal Engineering, 3, 79–85.
Togrul, I. T. & pehlivan, D. (2004). Modelling of thin layer drying kinetic of some fruits under open-air sun drying process. Journal of Food Engineering. 65: 413-425.
Yaldiz, O. C. & Ertekinn, H. I. Uzun. (2001). Mathematical modeling of thin layer solar drying of sultana grapes. Energy. 26: 457-465.
Yilmaz, F., M. Yuksekkaya, S., Vardin, H. & Karaaslan, M. (2015). The effects of drying conditions on moisture
transfer and quality of pomegranate fruit leather (pestil), Journal of the Saudi Society of Agricultural Sciences
Zarein, M. & Jaliliantabar, F. (2014). ANN Modeling of White Mulberry Drying by Microwave Oven, Advances in Environmental Biology. 8(16): 172-178.