Using Artificial Intelligence to Analyze the Thermal Behavior of Building Roofs
Publication: Journal of Energy Engineering
Volume 146, Issue 4
Abstract
This paper presents the application of an artificial neural network to model the thermal behavior of some roof coatings used in buildings. A set of test cells was built to evaluate these roof coatings. The cells were placed outdoors and several parameters were measured and collected for several weeks. The measured parameters included the temperature in different parts of the test cells. Additionally, the solar irradiance, the humidity, and the wind speed were measured and stored. We designed, built, and calibrated several heat flux transducers to measure the heat flux in each cell. Further, the reflectance and emissivity of the roof coatings were measured and used to create the model. The main contribution of this work is the modeling of an experimental system to evaluate the variability of the heat flux in building roofs using histograms. A statistical analysis based on computer simulations employing neural networks was performed to analyze those parameters that affect the heat flux in the roofs the most and the least. Finally, it was found that under specific conditions small increments in the reflectance of the coating can produce significant changes in the heat flux in the roof.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the study are proprietary or confidential in nature and may only be provided with restrictions. Data from the roofs and the artificial neural network models, however, are available from the authors upon reasonable request and with permission of División Académica de Ingeniería y Arquitectura (DAIA).
Acknowledgments
We acknowledge Dirección de Apoyo a la Investigación y Posgrado (DAIP), the University of Guanajuato, and the University of Ottawa for their sponsorship in the realization of this work. This work was developed during the sabbatical stay of Sergio Ledesma at the Faculty of Health Sciences at the University of Ottawa, Canada.
References
Alqalaf, H. J., and E. M. Alawadhi. 2016. “Thermal analysis of a concrete roof with an outdoor reflective surface.” J. Energy Eng. 142 (3): 05015001. https://doi.org/10.1061/(ASCE)EY.1943-7897.0000321.
ASTM. 1996. Standard test method for solar absorptance, reflectance, and transmittance of materials using integrating spheres. ASTM E903. West Conshohocken, PA: ASTM.
ASTM. 2019. Standard test method for calibration of thermocouples by comparison techniques. ASTM E220. West Conshohocken, PA: ASTM.
Bre, F., J. M. Gimenez, and V. D. Fachinotti. 2018. “Prediction of wind pressure coefficients on building surfaces using artificial neural networks.” Energy Build. 158 (Jan): 1429–1441. https://doi.org/10.1016/j.enbuild.2017.11.045.
Clear, R. D., L. Gartland, and F. C. Winkelmann. 2003. “An empirical correlation for the outside convective air-film coefficient for horizontal roofs.” Energy Build. 35 (8): 797–811. https://doi.org/10.1016/S0378-7788(02)00240-2.
CONNUE (Comisión Nacional para el Uso Eficiente de la Energía). 2017. Comisión Nacional para el Uso Eficiente de la Energía, costos y beneficios de la norma oficial mexicana para envolvente de edificaciones residenciales. Mexico City: CONNUE.
Deng, Z., and Q. Chen. 2018. “Artificial neural network models using thermal sensations and occupant’s behavior for predicting thermal comfort.” Energy Build. 174 (Sep): 587–602. https://doi.org/10.1016/j.enbuild.2018.06.060.
Frankish, K. 2014. The Cambridge handbook of artificial intelligence. Cambridge, UK: Cambridge University Press.
Hamdan, M. H., J. Yamin, and E. M. Abdel Hafez. 2012. “Passive cooling roof design under Jordanian climate.” Sustainable Cities Soc. 5 (Dec): 26–29. https://doi.org/10.1016/j.scs.2011.10.004.
Hernández-Pérez, I., J. Xamán, E. V. Macías-Melo, K. M. Aguilar-Castro, I. Zavala-Guillén, I. Hernandez-López, and E. Sima. 2018. “Experimental thermal evaluation of building roofs with conventional and reflective coatings.” Energy Build. 158 (Jan): 569–579. https://doi.org/10.1016/j.enbuild.2017.09.085.
Hernández-Roman, F., C. Sheinbaum-Pardo, and A. Calderon-Irazoque. 2017. “Socially neglected effect in the implementation of energy technologies to mitigate climate change: Sustainable building program in social housing.” Energy Sustainable Dev. 41 (Dec): 149–156. https://doi.org/10.1016/j.esd.2017.09.005.
ISO. 2007. Information technology—Programming languages—Technical report on C++ library extensions. ISO/IEC TR 19768. Geneva: ISO.
Jones, T. 2005. AI application programming (programming series). 2nd ed. Needham Heights, MA: Charles River Media.
Kachkouch, S., F. Ait-Nouh, B. Benhamou, and K. Limam. 2018. “Experimental assessment of thermal performance of three passive cooling techniques for roofs in a semi-arid climate.” Energy Build. 164 (Apr): 153–164. https://doi.org/10.1016/j.enbuild.2018.01.008.
Kazanasmaz, T., M. Gunaydin, and S. Binol. 2009. “Artificial neural networks to predict daylight illuminance in office buildings.” Build. Environ. 44 (8): 1751–1757. https://doi.org/10.1016/j.buildenv.2008.11.012.
Kumar, R., R. K. Aggarwal, and J. D. Sharma. 2013. “Energy analysis of a building using artificial neural network: A review.” Energy Build. 65 (Oct): 352–358. https://doi.org/10.1016/j.enbuild.2013.06.007.
Ledesma, S., M. A. Ibarra-Manzano, M. G. García-Hernández, and D. L. Almanza-Ojeda. 2017. “Neural lab a simulator for artificial neural networks.” In Proc., IEEE Computing Conf., 716–721. New York: IEEE. https://doi.org/10.1109/SAI.2017.8252175.
Lucero-Álvarez, J., and I. R. Martín-Domínguez. 2019. “The effect of solar reflectance, infrared emissivity, and thermal insulation of roofs on the annual energy consumption of single-family households in Mexico.” Indoor Built Environ. 28 (1): 17–33. https://doi.org/10.1177/1420326X17729194.
Marvuglia, A., A. Messineo, and G. Nicolosi. 2014. “Coupling a neural network temperature predictor and a fuzzy logic controller to perform thermal comfort regulation in an office building.” Build. Environ. 72 (Feb): 287–299. https://doi.org/10.1016/j.buildenv.2013.10.020.
Masters, T. 1994. Practical neural network recipies in C++. San Francisco: Academic.
Masters, T. 1995. Neural, novel & hybrid algorithms for time series prediction. New York: Wiley.
Moona, J. W., S.-H. Yoon, and S. Kim. 2013. “Development of an artificial neural network model based thermal control logic for double skin envelopes in winter.” Build. Environ. 61 (Mar): 149–159. https://doi.org/10.1016/j.buildenv.2012.12.010.
Papoulis, A., and S. U. Pillai. 2002. Probability, random variables and stochastic processes. 4th ed. New York: McGraw-Hill Higher Education.
Pearson, K. 1895. “Contributions to the mathematical theory of evolution: Skew variation in homogeneous material.” Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. 186: 343–414.
Press, W. H., S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery. 2007. Numerical recipes: The art of scientific computing. 3rd ed. New York: Cambridge University Press.
Russel, S., and P. Norvig. 2017. Artificial intelligence a modern approach. 3rd ed. Hoboken, NJ: Pearson Education.
Steigerwald, D. G. 2013. Economics—Introduction to measure theory. Santa Barbara, CA: Univ. of California.
Tsang, S. W., and C. Y. Jim. 2016. “Applying artificial intelligence modeling to optimize green roof irrigation.” Energy Build. 127 (Sep): 360–369. https://doi.org/10.1016/j.enbuild.2016.06.005.
Xu, X., W. Wang, T. Hong, and J. Chen. 2019. “Incorporating machine learning with building analysis to predict multi-building energy use.” Energy Build. 186 (Mar): 80–97. https://doi.org/10.1016/j.enbuild.2019.01.002.
Information & Authors
Information
Published In
Journal of Energy Engineering
Volume 146 • Issue 4 • August 2020
Copyright
©2020 American Society of Civil Engineers.
History
Received: May 22, 2019
Accepted: Feb 12, 2020
Published online: May 7, 2020
Published in print: Aug 1, 2020
Discussion open until: Oct 7, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.