Advertisement

Estimating the Ground Temperature Around Energy Piles Using Artificial Neural Networks

  • Mohamad KharsehEmail author
  • Mohamed El koujok
  • Holger Wallbaum
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1069)

Abstract

Ground source heat pump (GSHP) systems are using vertical ground heat exchangers, known as Borehole Heat Exchangers (BHEs), as a heat source or sink. The performance of the GSHP system strongly relies on the ground temperature surrounding the BHEs. This temperature depends on many parameters and varies during the operating time. Therefore, the determination of the ground temperature is crucial to define the design and the proper size of the BHEs so that the performance of the GSHP system can be kept at the desired level. The current study aims to formulate a complex structure of artificial neural network (ANN) model in a mathematical equation that expresses the change in the ground temperature around BHEs due to heat injection in the long run. To fulfill this aim, a numerical model of BHEs was created using the ANSYS (Analysis System) software to generate data. The generated data was then used to train the ANN model, which was built for this study. The simulation results show that the ANN model estimates the ground temperature (Tg) in the target GSHP system with higher accuracy.

Keywords

Artificial neural network Ground heat exchanger Ground source heat pump 

References

  1. 1.
    Wong, S.L., Wan, K.K.W., Li, D.H.W., et al.: Impact of climate change on residential building envelope cooling loads in subtropical climates. Energy Build. 42, 2098–2103 (2010)CrossRefGoogle Scholar
  2. 2.
    IEA. Renewables for Heating And Cooling. International Energy Agency, Paris (2007). http://www.iea.org/textbase/nppdf/free/2007/Renewable_Heating_Cooling_Final_WEB.pdf
  3. 3.
    Seyboth, K., Beurskens, L., Langniss, O., et al.: Recognising the potential for renewable energy heating and cooling. Energy Policy 36, 2460–2463 (2008)CrossRefGoogle Scholar
  4. 4.
    Al Jaber, S.A.,, Amin, A.Z., Clini, C., et al.: Renewables 2011 Global Status Report. Renewable Energy Policy Network for the 21st Century, Paris (2011). http://www.ren21.net
  5. 5.
    Michopoulos, A., Papakostas, K.T., Kyriakis, N.: Potential of autonomous ground-coupled heat pump system installations in Greece. Appl. Energy 88, 2122–2129 (2011)CrossRefGoogle Scholar
  6. 6.
    Esen, M., Yuksel, T.: Experimental evaluation of using various renewable energy sources for heating a greenhouse. Energy Build. 65, 340–351 (2013)CrossRefGoogle Scholar
  7. 7.
    Balbay, A., Esen, M.: Experimental investigation of using ground source heat pump system for snow melting on pavements and bridge decks. Sci. Res. Essays 5, 3955–3966 (2010)Google Scholar
  8. 8.
    Lund, J.W., Freeston, D.H., Boyd, T.L.: Direct utilization of geothermal energy 2010 worldwide review. In: World Geothermal Congress, Bali, Indonesia, pp. 1–23 (2010)Google Scholar
  9. 9.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
  10. 10.
    Beale, M.H., Hagan, M.T., Demuth, H.B.: Neural Network ToolboxTM User’s Guide (2017)Google Scholar
  11. 11.
    Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989)CrossRefGoogle Scholar
  12. 12.
    Demir, H., Atayilmaz, O.S., Agra, O., et al.: Application of artificial neural networks to predict heat transfer from buried pipe for ground source heat pump applications. In: ASME 2013 Heat Transfer Summer Conf. Collocated with the ASME 2013 7th International Conference on Energy Sustainability and the ASME 2013 11th International Conference on Fuel Cell Science, Engineering and Technology, HT 2013. Epub ahead of print 2013.  https://doi.org/10.1115/ht2013-17729
  13. 13.
    Zhang, J., Haghighat, F.: Development of artificial neural network based heat convection algorithm for thermal simulation of large rectangular cross-sectional area earth-to-air heat exchangers. Energy Build. 42, 435–440 (2010)CrossRefGoogle Scholar
  14. 14.
    Esen, H., Inalli, M., Sengur, A., et al.: Performance prediction of a ground-coupled heat pump system using artificial neural networks. Expert Syst. Appl. 35, 1940–1948 (2008)CrossRefGoogle Scholar
  15. 15.
    Benli, H.: Performance prediction between horizontal and vertical source heat pump systems for greenhouse heating with the use of artificial neural networks. Heat Mass Transf und Stoffuebertragung 52, 1707–1724 (2016)CrossRefGoogle Scholar
  16. 16.
    Tingleff, O., Madsen, K., Nielsen, H.B.: Methods for non-linear least squares problems. Lect Note Comput Sci 02611 Optim Data Fitting (2004)Google Scholar
  17. 17.
    Lourakis, M.I.A.: A brief description of the Levenberg-Marquardt algorithm implemented by levmar. Found. Res. Technol. 4, 1–6 (2005)Google Scholar
  18. 18.
    Kermani, B.G., Schiffman, S.S., Nagle, H.T.: Performance of the Levenberg-Marquardt neural network training method in electronic nose applications. Sens. Actuators B Chem. 110, 13–22 (2005)CrossRefGoogle Scholar

Copyright information

© Crown 2020

Authors and Affiliations

  • Mohamad Kharseh
    • 1
    Email author
  • Mohamed El koujok
    • 2
  • Holger Wallbaum
    • 1
  1. 1.Architecture and Civil EngineeringChalmers University of TechnologyCothenburgSweden
  2. 2.CanmetENERGY-Natural Resources CanadaVarennesCanada

Personalised recommendations