| تعداد نشریات | 286 |
| تعداد نشریات سازمان | 84 |
| تعداد شماره‌ها | 2,846 |
| تعداد مقالات | 32,300 |
| تعداد مشاهده مقاله | 41,387,038 |
| تعداد دریافت فایل اصل مقاله | 18,562,155 |
مقایسۀ مدل‌های ریاضی، شبکۀ عصبی مصنوعی و سیستم استنتاج عصبی-فازی تطبیقی (انفیس) در پیش‌بینی منحنی خشک شدن لایۀ نازک ورقه‌های سیب‌زمینی | ||
| تحقیقات مهندسی صنایع غذایی | ||
| دوره 19، شماره 1 - شماره پیاپی 68، شهریور 1399، صفحه 137-154 اصل مقاله (896 K) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22092/fooder.2020.127271.1234 | ||
| نویسندگان | ||
| هادی عظیمی نژادیان* ؛ مهدی مرادی | ||
| گروه مکانیک بیوسیستم، دانشکده کشاورزی، دانشگاه شیراز، شیراز، ایران | ||
| چکیده | ||
| هدف اصلی این پژوهش، مقایسه دقت عملکرد سه روش پرکاربرد شبیه‌سازی شامل مدل‌های ریاضی لایه نازک، شبکه‌های عصبی مصنوعی و سیستم استنتاج عصبی-فازی تطبیقی (انفیس) در تخمین نسبت رطوبت لحظه‌ای ورقه‌های سیب‌زمینی در فرآیند خشک کردن با توان مایکروویو است. برای پیش‌بینی نسبت رطوبت، از هفت مدل ریاضی استفاده شد. بر اساس داده‌های تجربی، توان مایکروویو، ضخامت نمونه‌ها و زمان فرآیند به عنوان پارامترهای ورودی و نسبت رطوبت به عنوان پارامتر خروجی شبکه‌های عصبی مصنوعی و سیستم استنتاج عصبی-فازی تطبیقی در نظر گرفته شدند. شبکه‌های عصبی بر اساس ساختار پس‌انتشار پیش‌خور چند لایه (MFFBp ) و پس‌انتشار پیشرو زنجیره‌ای (CFBp )، توابع فعال‌سازی خطی (Lin)، تانژانت هایپربولیک سیگموئید (Tan) و لگاریتمی (Log) و الگوریتم‌های یادگیری لونبرگ-مارکوارت (LM) و تنظیم بیزی (BR) طراحی شد. برای شبیه‌سازی با استنتاج تطبیقی عصبی-فازی، سیستم فازی از نوع تاکاگی-سوگنو انتخاب، ساختار سیستم استنتاج فازی (FIS) به روش خوشه‌بندی شبکه‌ای (Grid partitioning) ایجاد و از توابع عضویت ANFIS در جعبه‌ابزار منطق فازی نرم‌افزار MATLAB استفاده شد. در میان روش‌های مدل‌سازی مورد مطالعه، مدل میدیلی (Midilli)، شبکه CFBp با توپولوژی 1-10-10-3، الگوریتم آموزش LM و تابع Tan-Tan-Lin و مدل ANFIS با تابع عضویت سیگموئید در ورودی و قوانین فازی 4×3×3 بهترین مدل‌ها شناخته شدند. با توجه به نتایج به دست آمده، هر سه روش مدل‌سازی با دقت مطلوبی قادر به برآورد نسبت رطوبت لحظه‌ای نمونه‌ها بودند. با این حال، مدل ANFIS با ضریب تبیین 0.9997 و میانگین مربعات خطای 5-10×4.53 در برآورد داده‌های تجربی عملکرد بهتری داشت. | ||
| کلیدواژه‌ها | ||
| شبیه‌سازی فرآیند خشک شدن؛ مدل‌های رگرسیونی؛ هوش مصنوعی؛ نسبت رطوبت لحظه‌ای | ||
| عنوان مقاله [English] | ||
| Comparison of mathematical models, artificial neural networks and adaptive neuro-fuzzy inference system (ANFIS) in prediction of instantaneous drying curves of potato slices in a microwave dryer | ||
| چکیده [English] | ||
| The main objective of this research was to compare of accuracy of three widely used simulation methods including mathematical thin0layer models, artificial neural networks (ANN), and adaptive neuro-fuzzy inference system (ANFIS) in estimation of instantaneous moisture ratio of microwave power dried potato slices. To predict the moisture ratio, seven mathematical models were used. Furthermore, based on the experimental data, microwave power, samples thickness and process time, and the moisture ratio were considered as inputs and output of artificial neural networks and adaptive neuro-fuzzy inference system, respectively. Designing of neural networks was performed based on multi-layer feed-forward back-propagation (MFFBP) and cascade forward back-propagation (CFBP) structures, linear (Lin), sigmoid hyperbolic tangent (Tan) and logarithmic (Log) threshold functions, and Levenberg-Marquardt (LM) and Bayesian Regularization (BR) training algorithms. For simulation by adaptive neuro-fuzzy inference system, Takagi-Sugeno fuzzy system was selected, structure of the fuzzy inference system (FIS) created by grid partitioning method, and the membership functions in fuzzy logic toolbar of MATLAB software used. Among the studied modeling methods, Midilli model, CFBP network with 3-10-10-1 topology, LM training algorithm and Tan-Tan-Lin function, and ANFIS model with sigmoid membership function in input and 3×3×4 fuzzy rules were found as the best models. Based on the obtained results, all the three modeling methods were capable t estimate the instantaneous moisture ratio with desirable accuracy. However, showing the coefficient of determination of 0.9997 and mean square error of 4.53×10-5, ANFIS model had the better performance in estimation of the experimental data. | ||
| کلیدواژه‌ها [English] | ||
| Simulation of drying process, Regression models, Artificial intelligence, Instantaneous moisture ratio | ||
| مراجع | ||
|
Behmanesh, M. and Mohammadi, M. 2017. Adaptive neuro-fuzzy inference system with self-feedback and imperialist competitive learning algorithm for chaotic time series prediction. Computational Intelligence in Electrical Engineering. 7(4): 13–30. (in Persian) Beigi, M. 2016. Energy efficiency and moisture diffusivity of apple slices during convective drying. Food Science and Technology. 36(1): 145‒150. Beigi, M. 2019. Drying of mint leaves: Influence of the process temperature on dehydration parameters, quality attributes, and energy consumption. Journal of Agricultural Science and Technology. 21(1): 77‒88. Beigi, M., Torki-Harchegani, M. and Tohidi, M. 2017. Experimental and ANN modeling investigations of energy traits for rough rice drying. Energy. 141, 2196–2205. Darvishi, H., Zarein, M. and Farhudi, Z. 2016. Energetic and exergetic performance analysis and modeling of drying kinetics of kiwi slices. Journal of Food Science and Technology. 53(5): 2317–2333. Darvishi, H., Mohammadi, P., Azadbakht, M. and Farhudi, Z. 2018. Effect of different drying conditions on the mass transfer characteristics of kiwi slices. Journal of Agricultural Science and Technology. 20(2): 249–264. Dehghani, N., Vafakhah, M. and Bahremand, A. 2016. Rainfall-runoff modeling using artificial neural network and neuro-fuzzy inference system in Kasilian watershed. Journal of Watershed Management Research. 7(13): 128–137. (in Persian) Demiray, E. and Tulek, Y. 2012. Thin-layer drying of tomato (Lycopersicum esculentum Mill. cv. Rio Grande) slices in a convective hot air dryer. Heat and Mass Transfer. 48(5): 841–847. Dokoohaki, H., Gheisari, M., Mousavi, S. F., Zandparsa, S. and Hoogenboom, G. 2014. Development complex crop model based on CSM-CERES-Maize model for irrigation management and evaluating the maize growth simulations. Journal of Water and Irrigation Management. 3(2): 121–133. (in Persian) Ghanbarian, D., Baraani Dastjerdi, M. and Torki-Harchegani, M. 2016. Mass transfer characteristics of bisporus mushroom (Agaricus bisporus) slices during convective hot air drying. Heat and Mass Transfer. 52(5): 1081–1088. Ghorbanpour, M. and Yousefi, M. 2019. Kinetics of biodegradable film drying in microwave oven. Innovative Food Technologies. 6(1): 1–8. (in Persian) Gorjian, Sh., Tavakoli Hashtjin, T. and Kohsh Taghaza, M. H. 2014. Modeling of thin-layer drying kinetics of barberry fruit (Berberis Vulgaris) using artificial neural network. Journal of Food Science and Technology. 45(11): 1–12. (in Persian) Hafezi, N., Sheikhe Davoodi, M. J. and Sajjadieh, S. M. 2016a. A Study of drying rate of sliced potatoes during radiation-vacuum drying process using regression and artificial neural network models. Iranian Journal of Biosystem Engineering. 47(2): 279–289. (in Persian) Hafezi, N., Sheikhdavoodi, M. J., Sajadiye, S. M. and Khorasani Ferdavani, M. E. 2016b. The study of some physical properties and energy aspects of potatoes drying process by the infrared-vacuum method. Journal of Agricultural Machinery. 6(2): 463–475. (in Persian) Joardder, M. U. H., Brown, R., Kumar, C. and Karim, M. A. 2015. Effect of cell wall properties on porosity and shrinkage of dried apple. International Journal of Food Properties. 18(10): 2327‒2337. Kaveh, M., Abbaspour-Gilandeh, Y., Amiri Chayjan, R. and Mohammadigol, R. 2019a. Comparison of mathematical modeling, artificial neural networks and fuzzy logic for predicting the moisture ratio of garlic and shallot in a fluidized bed dryer. Journal of Agricultural Machinery. 9(1): 99–112. (in Persian) Kaveh, M., Jahanbakhshi, A., Abbaspour-Gilandeh, Y., Taghinezhad, E. and Farshbaf Moghimi, M. B. 2018. The effect of ultrasound pre-treatment on quality, drying, and thermodynamic attributes of almond kernel under convective dryer using ANNs and ANFIS network. Journal of Food Processing and Preservation. 47(1): e12868. Kaveh, M., Jahanbakhshi, A., Golpour, I., Mesri Gandshmin, T., Abbaspour-Gilandeh, Y. and Jahedi Rad, Sh. 2019b. Prediction of white mulberry drying kinetics in microwave-convective dryer: A comparative study between mathematical model, artificial neural network and ANFIS. Journal of Food Science and Technology. 88(16): 201–219. (in Persian) Khodaparast Shirazi, J. and Sadeghi, Z. 2012. Modeling and forecasting method in seafood export ARIMA and artificial neural networks. Quarterly Journal of Quantitative Economics. 9(4): 111–132. (in Persian) Khoshnevisan, B., Rafiee, S., Iqbal, J., Shamshirband, Sh., Omid, M., Badrul Anuar, N. and Abdul Wahab, A.W. 2015. A comparative study between artificial neural networks and adaptive neuro-fuzzy inference system for modeling energy consumption in greenhouse tomato production: A case study in Isfahan province. Journal of Agricultural Science and Technology. 17(1): 49–62. Mosavi Baygi, S. F., Farahmand, A., Taghi Zadeh, M. and Zia Foroghi, A. 2015. Modeling on hot air and infrared thin layers drying of persimmon slices. Food Science and Technology. 13(53): 161–171. (in Persian) Motevalli, A., Minaei, S., Abbasi, S. and Ghaderi, A. R. 2011. An Investigation of the Variations of Drying Rate, Effective Diffusion Coefficient, and Activation Energy for Microwave-vacuum Drying of Cherry. Iranian Journal of Biosystem Engineering. 41(2): 161‒168. (in Persian) Naghipur Zadeh Mahani, M. and Aghkhani, M.H. 2016. The effect of slicing type on drying kinetics and quality of dried carrot. Journal of Agricultural Machinery. 6(1): 224–235. (in Persian) Nasiri, A., Mobli, H., Refiee, Sh. and Rezaei, K. 2014. Kinetic modle simulation of thin-layer drying of thyme (Thymus vulgaris L.) using adaptive neuro-fuzzy inference system (ANFIS). Journal of Agricultural Engineering. 36(2): 37–48. (in Persian) Nasiri, A., Mobli, H., Rafiee, Sh, Rezaei, K. 2015. Kinetic model simulation of thin-layer drying of peppermint (Mentha piperita L.) using adaptive neuro-fuzzy inference system (ANFIS). 44(1): 35–43. (in Persian) Noori, M., Kashaninejad, M., Daraei Garme Khani, A. and Bolandi, M. 2013. Optimization of drying process of parsley using the combination of hot air and microwave methods. Electronic Journal of Food Processing and Preservation. 4(2): 103–122. (in Persian) Sattari, M., Salmasi, F. and Torkaman, GH. 2016. Performance evaluation of ANFIS and M5 tree models in crump weir discharge coefficient modeling. Journal of Experimental Research in Civil Engineering. 3(5): 51–61. (in Persian) Sheela, KG. and Deepa, S. N. 2013. Review on methods to fix number of hidden neurons in neural networks. Mathematical Problems in Engineering. http://dx.doi.org/10.1155/2013/425740 Shirazi, R., Bakhshabadi, H. and Bazrafshan, M. 2018. Adaptive neuro-fuzzy inference system (ANFIS) application in modeling the oil extraction from peanut with microwave pretreatment. Journal of Food Science and Technology. 80(15): 61–72. (in Persian) Süfer, Ö., Sezar, S. and Demir, H. 2017. Thin layer mathematical modeling of convective, vacuum and microwave drying of intact and brined onion slices. Journal of Food processing and Preservation. 41(6):e13239. Torki-Harchegani, M., Ghanbarian, D., Ghasemi Pirbalouti, A. and Sadeghi, M. 2016a. Dehydration behavior, mathematical modelling, energy efficiency and essential oil yield of peppermint leaves undergoing microwave and hot air treatments. Renewable and Sustainable Energy Reviews. 58: 407‒418. Torki-Harchegani, M., Ghasemi-Varnamkhasti, M., Ghanbarian, D., Sadeghi, M. and Tohidi, M. 2016b. Dehydration characteristics and mathematical modelling of lemon slices undergoing oven treatment. Heat and Mass Transfer. 52(2): 281–289. Wang, J. and Xi, Y. S. 2005. Drying characteristics and drying quality of carrot using a two-stage microwave process. Journal of Food Engineering. 68(4): 505–511. Wang, J., Xiong, Y. S. and Yu, Y. 2004. Microwave drying characteristics of potato and the effect of different microwave powers on the dried quality of potato. European Food Research and Technology. 219(5): 500–506. Yousefi, A. R. 2017. Estimation of papaw (Carcia papaw L.) moisture content using adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm-artificial neural network (GA-ANN). Iran Food Science and Technology Research Journal. 12(6): 767‒779. Ziaforoughi, A., Yousefi, A. R. and Razavi, S. M. A. 2016. A comparative modeling study of quince infrared drying and evaluation of quality parameters. International Journal of Food Engineering, 12(9): 901-910. Zojaji, M., Mazaheri, A. F., Namayandeh, S. and Abolhasani, M. 2016. Investigation of black mulberry drying kinetics and energy consumption under microwave oven. Journal of Food Technology and Nutrition. 13(3): 57–64. (in Persian) | ||
|
آمار تعداد مشاهده مقاله: 397 تعداد دریافت فایل اصل مقاله: 241 |
||