Advertisement

Artificial Neural Network Analysis of the Solar-Assisted Heat Pumps Performance for Domestic Hot Water Production

  • Alireza Zendehboudi
  • Xianting LiEmail author
  • Siyuan Ran
Conference paper
Part of the Springer Proceedings in Energy book series (SPE)

Abstract

The solar-assisted heat pump devices have attracted ample attention as potential alternatives to the conventional technologies for domestic hot water production. Precise COP estimation of the hybrid system is a prerequisite prior to conducting any effort to design and install as well as a necessity for market support and optimal system assurance. Here, to develop a model along that has a high precision and reliability, but less complexity and computational time, the ability of soft computing approaches for predicting the performance of a solar-assisted heat pump system for domestic hot water production is reported. The experimental data gathered from a real project in China and different intelligent models are developed based on the measurements. First, owing to the complexity of our studied system and the high number of influential parameters, a novel and unique multi-objective optimization technique based on NSGA-II optimization method is proposed to determine a set of optimum variables with the highest influence on the desired output. Based on the Pareto frontier, seven input variables out of forty eight are considered for the desired output. The reliability of the developed models is evaluated via statistical and graphical error analyses. It was inferred that integration of the MLP-ANN with the suggested variable selectin algorithm outperformed the other methods by introducing an R2 = 0.9951 and RMSE = 0.0917. The current investigation can aid as a gear in the direction of improving the precision in estimation of performance of solar-assisted heat pump devices.

Keywords

Domestic hot water system Solar-assisted heat pump Artificial neural network Estimation 

Notes

Acknowledgements

This study was supported by the Innovative Research Groups of the National Natural Science Foundation of China (Grant No. 51521005).

References

  1. 1.
    Tsinghua University Building Energy Saving Research Center, Annual Report on China Building Energy Efficiency (China Architecture and Building Press, Beijing, 2011). (in Chinese)Google Scholar
  2. 2.
    G. Panaras, E. Mathioulakis, V. Belessiotis, Investigation of the performance of a combined solar thermal heat pump hot water system. Sol. Energy 93, 169–182 (2013)CrossRefGoogle Scholar
  3. 3.
    S. Poppi, C. Bales, M.Y. Haller, A. Heinz, Influence of boundary conditions and component size on electricity demand in solar thermal and heat pump combisystems. Appl. Energy 162, 1062–1073 (2016)CrossRefGoogle Scholar
  4. 4.
    S. Poppi, C. Bales, A. Heinz, F. Hengel, D. Chèze, I. Mojic, C. Cialani, Analysis of system improvements in solar thermal and air source heat pump combisystems. Appl. Energy 173, 606–623 (2016)CrossRefGoogle Scholar
  5. 5.
    D. Svozil, V. Kvasnicka, J. Pospichal, Introduction to multi-layer feed-forward neural networks. Chemometr. Intell. Lab. Syst. 39, 43–62 (1997)CrossRefGoogle Scholar
  6. 6.
    K. Deb, A. Pratap, S. Agarwal, T. Meyarivan, A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6, 182–197 (2002)CrossRefGoogle Scholar
  7. 7.
    S. Haykin, Neural Networks. A Comprehensive Foundation (Prentice Hall Inc, New Jersey, 1999)zbMATHGoogle Scholar
  8. 8.
    K.-L. Du, M.N.S. Swamy, Neural Networks in a Soft Computing Framework (Springer, London, 2006)Google Scholar
  9. 9.
    A.T.C. Goh, Back-propagation neural networks for modeling complex systems. Artif. Intell. Eng. 9, 143–151 (1995)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Building Science, School of ArchitectureTsinghua UniversityBeijingChina

Personalised recommendations