Abstract




 
   

IJE TRANSACTIONS A: Basics Vol. 26, No. 10 (October 2013) 1235-1242   

downloaded Downloaded: 215   viewed Viewed: 1987

  ARTIFICIAL NEURAL NETWORK INVOLVED IN THE ACTION OF OPTIMUM MIXED REFRIGERANT (DOMESTIC REFRIGERATOR) (TECHNICAL NOTE)
 
N. Austin, P. Senthil Kumar and N. Kanthavelkumaran
 
( Received: December 07, 2012 – Accepted: February 28, 2013 )
 
 

Abstract    This analysis principally focuses on the implementation of Radial basis function (RBF) and back propagation (BPA) algorithms for training artificial neural network (ANN) to get the optimum mixture of Hydro fluorocarbon (HFC) and organic compound (Hydrocarbons) for obtaining higher coefficient of Performances (COPs). The thermodynamical properties of mixed refrigerants are observed using REFPROP 9 software system that contains details of refrigerants. Totally different mixtures of the refrigerants along with their COP are obtained by the REFPROP 9. This task consumes time in getting the right combination of refrigerants as lot of menu choices have to be compelled to be chosen within the REFPROP 9. In order to form the method of checking out the correct mixed refrigerants with minimum manual intervention, RBF is trained and tested with the different patterns of mixed refrigerants. The RBF / BPA mixed refrigerant analysis software has been developed by using MATLAB 11a.

 

Keywords    ANN, artificial neural network, Back propagation algorithm, COP, Radial basis function, Mixed refrigerant

 

چکیده    این تحلیل اساساً بر کاربرد الگوریتم‌های تابع پایه‌ی شعاعی (RBF) و پس انتشار خطا (BPA) برای آموزش شبکه عصبی مصنوعی (ANN) برای به دست آوردن مخلوط بهینه از هیدرو فلوروکربن (HFC) و مواد آلی (هیدروکربن ها) برای به دست آوردن بالاتر متمرکز است. خواص ترمودینامیکی از مبرد مخلوط REFPROP 9 با استفاده از سیستم نرم افزاری حاوی جزئیات مبرد مشاهده شده است. مخلوط‌های کاملاً متفاوت از مبرد همراه با ضریب‌های کارایی‌شان بر اساس 9 REFPROP به دست آمده است. تعیین ترکیب مناسبی از مبرد زمان زیادی لازم دارد زیرا باید گزینه‌های بسیاری از درون REFPROP 9 انتخاب شود. به منظور پیدا کردن یک روش چک کردن مخلوط صحیح مبرد با حداقل مداخله‌ی دستی، RBF آموزش دیده و با الگوهای مختلف مبرد مخلوط مورد آزمایش قرار می‌گیرد. نرم افزار تجزیه و تحلیل مخلوط مبرد RBF / BPA با استفاده از MATLAB 11A توسعه یافته است.

References   

 

1.     Sozen, A., Arcaklioglu, E. and Ozalp, M., "A new approach to thermodynamic analysis of ejector–absorption cycle: Artificial neural networks", Applied Thermal Engineering,  Vol. 23, No. 8, (2003), 937-952.

2.     Arcaklıoglu, E., Cavusoglu, A. and Erisen, A., "Thermodynamic analyses of refrigerant mixtures using artificial neural networks", Applied Energy,  Vol. 78, No. 2, (2004), 219-230.

3.     Pacheco-Vega, A., Sen, M., Yang, K. and McClain, R. L., "Neural network analysis of fin-tube refrigerating heat exchanger with limited experimental data", International Journal of Heat and Mass Transfer,  Vol. 44, No. 4, (2001), 763-770.

4.     Olofsson, T. and Andersson, S., "Long-term energy demand predictions based on short-term measured data", Energy and Buildings,  Vol. 33, No. 2, (2001), 85-91.

5.     Sharma, R., Singhal, D., Ghosh, R. and Dwivedi, A., "Potential applications of artificial neural networks to thermodynamics: Vapor–liquid equilibrium predictions", Computers & Chemical Engineering,  Vol. 23, No. 3, (1999), 385-390.

6.     Arcaklioglu, E., Erisen, A. and Yilmaz, R., "Artificial neural network analysis of heat pumps using refrigerant mixtures", Energy Conversion and Management,  Vol. 45, No. 11, (2004), 1917-1929.

7.     McMullan, J. T., "Refrigeration and the environment—issues and strategies for the future", International Journal of Refrigeration,  Vol. 25, No. 1, (2002), 89-99.

8.     Camporese, R., Bigolaro, G., Bobbo, S. and Cortella, G., "Experimental evaluation of refrigerant mixtures as substitutes for CFC12 and r502", International Journal Of Refrigeration,  Vol. 20, No. 1, (1997), 22-31.

9.     Günther, D. and Steimle, F., "Mixing rules for the specific heat capacities of several hfc-mixtures", International Journal of Refrigeration,  Vol. 20, No. 4, (1997), 235-243.

10.   Richardson, R. and Butterworth, J., "The performance of propane/isobutane mixtures in a vapour-compression refrigeration system", International Journal of Refrigeration,  Vol. 18, No. 1, (1995), 58-62.

11.   Didion, D. A. and Bivens, D. B., "Role of refrigerant mixtures as alternatives to CFCs", International Journal of Refrigeration,  Vol. 13, No. 3, (1990), 163-175.

12.   Chen, S., Billings, S., Cowan, C. and Grant, P., "Practical identification of narmax models using radial basis functions", International Journal of Control,  Vol. 52, No. 6, (1990), 1327-1350.

13.   Chen, S., Billings, S. and Grant, P., "Recursive hybrid algorithm for non-linear system identification using radial basis function networks", International Journal of Control,  Vol. 55, No. 5, (1992), 1051-1070.

14.   Chen, S. and Billings, S., "Neural networks for nonlinear dynamic system modelling and identification", International journal of control,  Vol. 56, No. 2, (1992), 319-346.

15.   Moody, J. and Darken, C. J., "Fast learning in networks of locally-tuned processing units", Neural Computation,  Vol. 1, No. 2, (1989), 281-294.

16.   Sanner, R. M. and Slotine, J.-J., "Stable adaptive control and recursive identification using radial gaussian networks", in Decision and Control, 1991., Proceedings of the 30th IEEE Conference on, IEEE, (1991), 2116-2123.

17.           Arcaklioglu, E., "Performance comparison of cfcs with their substitutes using artificial neural network", International Journal of Energy Research,  Vol. 28, No. 12, (2004), 1113-1125. 





International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir