Title: Experimental and machine learning research on a multi-functional Trombe wall system

Authors: Andaç Batur Çolak; Marzieh Rezaei; Devrim Aydin; Ahmet Selim Dalkilic

Addresses: Information Technologies Application and Research Center, Istanbul Ticaret University, Istanbul 34445, Türkiye ' Department of Architecture and Built Environment, The University of Nottingham, University Park, Nottingham, NG7 2RD, UK; Department of Mechatronics Engineering, Near East University, Nicosia, TRNC Mersin 10, Türkiye ' Department of Architecture and Built Environment, The University of Nottingham, University Park, Nottingham, NG7 2RD, UK; Department of Mechanical Engineering, Eastern Mediterranean University, G. Magosa, TRNC Mersin 10, Türkiye ' Department of Mechanical Engineering, Mechanical Engineering Faculty, Yildiz Technical University, Istanbul 34349, Türkiye

Abstract: Performance prediction tools can assist architects and engineers in designing and sizing TWs without the extensive effort, time, and costs associated with experimental evaluations. This study aims to develop an artificial neural network (ANN) model for predicting the performance of a multi-functional TW by using 57 experimental datasets and the Levenberg-Marquardt algorithm as the training algorithm. The developed model was found to be capable of TW performance prediction with error rates < 0.23%. The performance parameters for the ANN model, namely the mean squared error (MSE) and the coefficient of determination (R), were calculated to be 0.034 and 0.99917, respectively.

Keywords: Trombe wall; heating; buildings; artificial neural network; ANN; Levenberg-Marquardt; global warming; sustainable architecture.

DOI: 10.1504/IJGW.2024.139902

International Journal of Global Warming, 2024 Vol.33 No.4, pp.404 - 415

Received: 29 Aug 2023
Accepted: 12 Feb 2024
Published online: 09 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article