Methodology for the Prediction of the Thermal Conductivity of Concrete by Using Neural Networks
Source abstract
Abstract
The energy consumption of buildings presents a significant concern, which has led to a demand for materials with better thermal performance. Thermal conductivity (TC), among the most relevant thermal properties, is essential to address this demand. This study introduces a methodology integrating a Multilayer Perceptron (MLP) and a Generative Adversarial Network (GAN) to predict the TC of concrete based on its mass composition and density. Three scenarios using experimental data from published papers and synthetic data are compared and reveal the model’s outstanding performance across training, validation, and test datasets. Notably, the MLP trained on the GAN-augmented dataset outperforms the one with the real dataset, demonstrating remarkable consistency between the model’s predictions and the actual values. Achieving an RMSE of 0.0244 and an R2 of 0.9975, these outcomes can offer precise quantitative information and advance energy-efficient materials.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Concrete and Cement Materials Research · Innovative concrete reinforcement materials · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Environmental Engineering Program, Federal University of Rio de Janeiro, Rio de Janeiro 21941-901, Brazil
Department of Mechanical Engineering, University Rovira i Virgili, Av. Països Catalans 26, 43007 Tarragona, Spain
Department of Materials Science and Physical Chemistry, Universitat de Barcelona, Martí i Franquès 1-11, 08028 Barcelona, Spain
Department of Computer Science and Industrial Engineering, University of Lleida, 25003 Lleida, Spain
Funding
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) · Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) · Fundação de Amparo à Pesquisa do Estado do Rio de Janeiro (Faperj) · “Ministerio de Ciencia, Innovación y Universidades” of Spain · EU
References (45)
Show source-provided references
1. Evaluation of the thermal performance of a Thermally Activated Building System (TABS) according to the thermal load in a residential building10.1016/j.enbuild.2014.01.008 ↗
2. Development of thermal energy storage concrete10.1016/j.cemconres.2003.10.022 ↗
3. The impact of concrete structure on the thermal performance of the dual-media thermocline thermal storage tank using concrete as the solid medium10.1016/j.apenergy.2013.08.044 ↗
4. Computational design optimization of concrete mixtures: A review10.1016/j.cemconres.2018.04.007 ↗
5. Thermal energy storage in concrete: Review, testing, and simulation of thermal properties at relevant ranges of elevated temperature10.1016/j.cemconres.2023.107096 ↗
6. Machine learning based prediction model for thermal conductivity of concrete10.1016/j.jobe.2020.101956 ↗
7. Predictive modelling of sustainable lightweight foamed concrete using machine learning novel approach10.1016/j.jobe.2022.104746 ↗
8. Machine learning study of the mechanical properties of concretes containing waste foundry sand10.1016/j.conbuildmat.2020.118152 ↗
9. An ensemble machine learning approach for prediction and optimization of modulus of elasticity of recycled aggregate concrete10.1016/j.conbuildmat.2020.118271 ↗
10. Machine learning approach for predicting concrete compressive, splitting tensile, and flexural strength with waste foundry sand10.1016/j.jobe.2023.106363 ↗
11. A concrete mix proportion design algorithm based on artificial neural networks10.1016/j.cemconres.2006.01.009 ↗
12. Evaluation of chloride penetration in high performance concrete using neural network algorithm and micro pore structure10.1016/j.cemconres.2009.05.013 ↗
13. Predicting carbonation depth of concrete using a hybrid ensemble model10.1016/j.jobe.2023.107320 ↗
14. Prediction of surface chloride concentration of marine concrete using ensemble machine learning10.1016/j.cemconres.2020.106164 ↗
15. Predictive models for concrete properties using machine learning and deep learning approavhes: A review10.1016/j.jobe.2022.105444 ↗
16. Compressive strength prediction of environmentally friendly concrete using artificial neural networks10.1016/j.jobe.2018.01.007 ↗
17. An integrated building energy performance evaluation method: From parametric modeling to GA-NN based energy consumption prediction modeling10.1016/j.jobe.2021.103571 ↗
18. Experimental study and machine learning algorithms for evaluating the performance of U-shaped ultra-high performance reinforced fiber concrete under static and impact loads10.1016/j.jobe.2023.106389 ↗
19. Compressive strength assessment of concrete containing metakaolin using ANN
20. Generative Adversarial Nets
21. Xu, L., Skoularidou, M., Cuesta-Infante, A., and Veeramachaneni, K. (2019). Modeling Tabular Data using Conditional GAN. Adv. Neural Inf. Process. Syst., 32.
22. Abedi, M., Hempel, L., Sadeghi, S., and Kirsten, T. (2022). GAN-Based Approaches for Generating Structured Data in the Medical Domain. Appl. Sci., 12.10.3390/app12147075 ↗
23. Modeling of strength of high-performance concrete using artificial neural networks10.1016/S0008-8846(98)00165-3 ↗
24. Modeling slump flow of concrete using second-order regressions and artificial neural networks10.1016/j.cemconcomp.2007.02.001 ↗
25. Estimation of the compressive strength of concretes containing ground granulated blast furnace slag using hybridized multi-objective ANN and salp swarm algorithm10.1016/j.conbuildmat.2020.118676 ↗
26. Four-layer perceptron approach for strength prediction of UHPC10.1016/j.conbuildmat.2020.119465 ↗
27. Properties prediction of environmentally friendly ultra-high-performance concrete using artificial neural networks10.1080/19648189.2020.1762749 ↗
28. An Artificial Neural Network Model to Predict the Thermal Properties of Concrete Using Different Neurons and Activation Functions10.1155/2019/3831813 ↗
29. Kurpińska, M., Kułak, L., Miruszewski, T., and Byczuk, M. (2021). Application of artificial neural networks to predict insulation properties of lightweight concrete. Appl. Sci., 11.10.3390/app112210544 ↗
30. Optimization of foam concrete characteristics using response surface methodology and artificial neural networks10.1016/j.conbuildmat.2022.127575 ↗
31. Modeling of thermal conductivity of concrete with vermiculite by using artificial neural Networks approaches10.1080/08916152.2012.669810 ↗
32. Effective Prediction of Thermal Conductivity of Concrete Using Neural Network Method10.1007/s40069-012-0016-x ↗
33. Comparison between ANFIS and ANN for estimation of the thermal conductivity coefficients of construction materials
34. Investigation of thermal conductivity of rubberized concrete as an energy-efficient building material and modeling by artificial intelligence10.1007/s43452-023-00701-y ↗
35. Xu, H., Chang, R., Pan, M., Li, H., Liu, S., Webber, R.J., Zuo, J., and Dong, N. (2022). Application of Artificial Neural Networks in Construction Management: A Scientometric Review. Buildings, 12.10.3390/buildings12070952 ↗
36. Study on thermal properties of recycled aggregate concrete and recycled concrete blocks10.1016/j.conbuildmat.2015.07.058 ↗
37. An experimental study on thermal conductivity of concrete10.1016/S0008-8846(02)00965-1 ↗
38. Mechanical and thermal properties of moderate-strength concrete with ceramic powder used as supplementary cementitious material
39. Thermal conductivity and compressive strength of concrete incorporation with mineral admixtures10.1016/j.buildenv.2006.06.010 ↗
40. Effects of Modern Concrete Materials on Thermal Conductivity10.1061/(ASCE)MT.1943-5533.0003026 ↗
41. Characterization of RCAs and their concrete using simple test methods
42. Predicting thermal performance of a mass concrete foundation—A field monitoring case study
43. Impact of lightweight aggregate on concrete thermal properties
44. Kurpińska, M., Karwacki, J., Maurin, A., and Kin, M. (2021). Measurements of thermal conductivity of LWC cement composites using simplified laboratory scale method. Materials, 14.10.3390/ma14061351 ↗
45. Physico-mechanical, durability and thermal properties of basalt fiber reinforced foamed concrete containing waste marble powder and slag10.1016/j.conbuildmat.2021.123128 ↗