پیش بینی دمای هوای داخل گلخانه مجهز به سامانه ی سرمایش تبخیری با استفاده از مدل رگرسیونی و شبکه های عصبی مصنوعی (مطالعه موردی در شهر کرمان)

نوع مقاله: مقاله پژوهشی

نویسندگان

1 بخش مهندسی مکانیک بیوسیستم، دانشکده کشاورزی، دانشگاه شهید باهنر کرمان، کرمان، ایران

2 استادیار بخش مکانیک بیوسیستم، دانشکده کشاورزی، دانشگاه شهید باهنر کرمان، کرمان، ایران

چکیده

در کشاورزی امروزی، نقش گلخانه به عنوان ابزاری برای افزایش کمیت و کیفیت محصول، دارای اهمیت فراوان می­باشد. شرایط داخلی گلخانه به برخی  عوامل بیرونی وابسته است که به­طور معمول پیش­بینی دقیق آن­ها به سادگی امکان پذیر نیست. هدف از اجرای این تحقیق، تخمین دمای هوای داخل گلخانه در حالت­های بدون تهویه و با استفاده از سامانه­ی سرماش تبخیری با روش شبکه عصبی مصنوعی و مدل رگرسیونی است. از برخی عوامل مانند شدت تابش خورشید، دمای هوای محیط، دمای دیواره شمالی گلخانه، دبی و دمای هوای ورودی به گلخانه، به­عنوان ورودی مدل رگرسیونی و شبکه عصبی استفاده گردید. برای آموزش شبکه عصبی از پرسپترون چندلایه با الگوریتم یادگیری پس‌انتشار خطا و از الگوریتم­های آموزش لونبرگ مارکوارت، تنظیم به­روش بیزی و اسکالت کانژوگیت گرادینت و در مدل رگرسیونی از روش پیشرو و پسرو برای تعیین معادلات رگرسیونی استفاده شد. ارزیابی مدل شبکه عصبی و رگرسیونی با شاخص­های آماری میانگن مربعات خطا، ضریب تبیین و معیار متوسط قدر مطلق خطا تعیین گردید. مقایسه نتایج آماری حاکی از دقت بالاتر شبکه عصبی مصنوعی نسبت به مدل رگرسیونی است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Temperature Prediction of a Greenhouse Equipped with Evaporative Cooling System Using Regression Models and Artificial Neural Network (Case Study in Kerman City)

نویسندگان [English]

  • Mohammad Hossein Shojaei 1
  • Hamid Mortezapour 2
  • Kazem Jafari Naeimi 1
  • Mohammad Mehdi Maharlooei 1
1 Department of Biosystems Engineering, Faculty of Agriculture, Shahid Bahonar University of Kerman, Kerman, Iran
2 Assistant Professor in Department of Biosystems Engineering, Faculty of Agriculture, Shahid Bahonar University of Kerman, Kerman, Iran
چکیده [English]

Today's agriculture, greenhouse cultivation plays a key role in increasing the quantity and quality of products. Indoor conditions of the greenhouse depend on some external factors, which are usually not easily predictable. The purpose of this study was to estimate the air temperature inside the greenhouse in two modes of ventilation (non-ventilated conditions and evaporative cooling system) using artificial neural network and regression models. Some factors such as solar irradiance, ambient temperature, northern wall temperature and flow rate and temperature of the cooling air were employed as the inputs of the models. Verification of the models was conducted using statistical criteria of mean square error, correlation coefficient and mean absolute percentage error. In order to train the neural network from multilayer perceptron with the algorithm of post-error learning and using the Levenberg-marquart training algorithms, the Bayesian regression and the gradient conjugate scalar, and in the regression model of the progressive and forward method for determining regression equations were used. Comparison of the statistical criteria indicated that the artificial neural network method predicted the greenhouse temperature with a higher accuracy than the regression model.

کلیدواژه‌ها [English]

  • artificial neural network
  • Evaporative Cooling
  • Greenhouse Temperature
  • modeling
Acosta, G. & Tosini, M., (2001). A firmware digital neural network for climate prediction applications, Intelligent Control, 2001.(ISIC'01). Proceedings of the 2001 IEEE International Symposium on. IEEE. 127-131.

Arahal, M. R., Rodriguez, F., Ramirez-Arias, A. & Berenguel, M., (2005). Discrete-time nonlinear FIR models with integrated variables for greenhouse indoor temperature simulation, Decision and Control, 2005 and 2005 European Control Conference. CDC-ECC'05. 44th IEEE Conference on. IEEE. 4158-4162.

Azadeh, A., Maghsoudi, A. & Sohrabkhani, S. (2009). An integrated artificial neural networks approach for predicting global radiation. Energy Conversion and Management, 50(6), 1497-1505.

Boaventura Cunha, J., Couto, C. & Ruano, A., (2000). A greenhouse climate multivariable predictive controller, International Conference and British-Israeli Workshop on Greenhouse Techniques towards the 3rd Millennium 534. 269-276.

Dariouchy, A., Aassif, E., Lekouch, K., Bouirden, L. & Maze, G. (2009). Prediction of the intern parameters tomato greenhouse in a semi-arid area using a time-series model of artificial neural networks. Measurement, 42(3), 456-463.

Dodange, M., (2011). Evaluation and evaluation of solar greenhouses against fossil greenhouses, Faculty of Economics and Accounting. Islamic Azad University, Central Tehran Branch.

Du, J., Bansal, P. & Huang, B. (2012). Simulation model of a greenhouse with a heat-pipe heating system. Applied energy, 93, 268-276.

Ferreira, P., Faria, E. & Ruano, A. (2002). Neural network models in greenhouse air temperature prediction. Neurocomputing, 43(1), 51-75.

Haykin, S. (1994). Neural networks: A comprehensive foundation: Macmillan college publishing company. New York.

Hecht-Nielsen, R., (1987). Kolmogorov’s mapping neural network existence theorem, Proceedings of the international conference on Neural Networks. New York: IEEE Press. 11-13.

Hornik, K., Stinchcombe, M. & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks, (5), 2359-2366.

Jain, S., Das, A. & Srivastava, D. (1999). Application of ANN for reservoir inflow prediction and operation. Journal of Water Resources Planning and Management, 125(5), 263-271.

Joudi, K. A. & Farhan, A. A. (2015). A dynamic model and an experimental study for the internal air and soil temperatures in an innovative greenhouse. Energy Conversion and Management, 91, 76-82.

Karimi, S., Kisi, O., Shiri, J. & Makarynskyy, O. (2013). Neuro-fuzzy and neural network techniques for forecasting sea level in Darwin Harbor, Australia. Computers & Geosciences, 52, 50-59.

Linker, R. & Seginer, I. (2004). Greenhouse temperature modeling: a comparison between sigmoid neural networks and hybrid models. Mathematics and computers in simulation, 65(1), 19-29.

Makarian, H. a. R., A (2013). Prediction of Spatial Distribution Pattern of Acroptilon repens L. Population Using Learning Vector Quantization Neural Network Model Knowledge of agriculture and sustainable production, 23(1), 85-98.

Marcos, S., Macchi, O., Vignat, C., Dreyfus, G., Personnaz, L. & Roussel‐Ragot, P. (1992). A unified framework for gradient algorithms used for filter adaptation and neural network training. International journal of circuit theory and applications, 20(2), 159-200.

Møller, Martin Fodslette. (1993). A scaled conjugate gradient algorithm for fast supervised learning. Neural networks, 6(4), 525-533

Omid, M. & Shafaei, A. (2004). Investigation of temperature and humidity variations within a greenhouse using a computer-based data acquisition system pajouhesh-va-sazandegi, 17(3), 67-73. (In Farsi)

Peyman, M. a. M., A, H, (2007). Experimental criteria for determining the appropriateness of using multi-layered perceptron neural network to classify patterns, First Iranian Data Mining Conference.

Sabziparvar, A., A and Khataar, B (2014). Evaluation of Artificial Neural Network (ANN) and Irmak Experimental Models to Predict Daily Solar Net Radiation (Rn ) in Cold Semi-arid Climate (Case study: Hamedan). Water and soil knowledge, 25(2), 37-50.

Seginer, I. (1997). Some artificial neural network applications to greenhouse environmental control. Computers and Electronics in Agriculture, 18(2-3), 167-186.

Saini, Lalit Mohan. (2008). Peak load forecasting using Bayesian regularization, Resilient and adaptive backpropagation learning based artificial neural networks. Electric Power Systems Research, 78(7), 1302-1310. 

Van Henten, E., (1994). Greenhouse climate management: an optimal control approach. Van Henten, Place: Published.

Wang, Y.-M. & Elhag, T. M. (2007). A comparison of neural network, evidential reasoning and multiple regression analysis in modelling bridge risks. Expert Systems with Applications, 32(2), 336-348.