Industry 4.0
Vol. 9 (2024), Issue 5, pg(s) 173-177

DOMINANT TECHNOLOGIES IN “INDUSTRY 4.0”

Application of artificial neural networks for assessing the Psi-factor of thermal bridges under various geometries and materials

  • 1 University of Architecture, Civil Engineering and Geodesy (UACEG) – Sofia, Bulgaria

Abstract

The publication examines the use of artificial neural networks to calculate the linear thermal conductivity (Psi-factor) of thermal bridges given various parameters, such as geometrical data and the thermal resistance R of the thermal bridge components. The neural network is trained on examples of IF, IW, and B thermal bridges, considering the straightforward task of determining Psi using given parameters. The neural network training results show high accuracy in calculations – RMSE is 1.132% on training data and 1.1423% on test data, and the correlation coefficient (R²) is around 0.9997 for both data sets. The applicability of the approach to seismic conditions in the Balkans is assessed.

Keywords

References

  1. ISO 10211:2017, Thermal bridges in building construction – Heat flows and surface temperatures – Detailed calculations.
  2. P. Chobanov, Energy efficiency in construction, UACEG – Sofia (2016).
  3. BISCO – Physibel. https://www.physibel.be/en/products/bisco, visited on 01.11.2024.
  4. COMSOL Multiphysics, https://www.comsol.com/, visited on 01.11.2024.
  5. COMSOL Reference Manual, https://doc.comsol.com/5.4/doc/com.comsol.help.comsol/COM SOL_ReferenceManual.pdf.
  6. TRISCO – Physibel, https://www.physibel.be/en/products/trisco, visited on 01.11.2024.
  7. Flixo, https://www.flixo.com/, visited on 01.11.2024.
  8. P. Chobanov, A simulation approach for the analysis and assessment of the thermal protection ability of buildings, Doctoral thesis, Sofia (2005).
  9. P. Chobanov, Analysis of thermal bridges in seismic regions – column in a wall, Annual of UACEG, 49, 23-30 (2016).
  10. P. Chobanov, Analysis of Thermal Bridges in Seismic Areas – Corner Column, Annual of UACEG, 49, 31-40 (2016).
  11. ISO TC 163/SC 2, ISO/FDIS 14683:2007(E), Thermal bridges in building construction – Linear thermal transmittance – Simplified methods and default values.
  12. P. Nikolovski, Catalog of linear thermal bridges in buildings in seismic regions, Chamber of Certified Architects and Certified Engineers of the Republic of Macedonia, Skopje (2017).
  13. P. Nikolovski, Thermal bridges in building structures, Institute for Standardization of the Republic of Macedonia, Skopje (2012).
  14. St. Ivanova, Estimation of linear thermal transmittance of thermal bridges in seismic areas through an artificial neural network, Annual of UACEG, 55, 255-273 (2022).
  15. St. Ivanova, Artificial neural networks for energy efficiency, UACEG – Sofia (2022).
  16. D. Hammerstrom, Working with neural networks, IEEE Spectrum, 7, 46-53 (1993).
  17. ISO 14683:2017, Thermal bridges in building construction — Linear thermal transmittance – Simplified methods and default values. https://www.iso.org/standard/65706.html, visited on 01.11.2024.
  18. St. Ivanova, Calculation of ψ (Psi) of thermal bridges, https://ait.uacg.bg/EE/Building/psi-bridge.html, visited on 01.11.2024.
  19. St. Ivanova, Calculation of heat losses during the heating season for sites in Bulgaria, https://ait.uacg.bg/EE/Building/, visited on 01.11.2024.

Article full text

Download PDF