Machine Learning Modeling of Foam Concrete Performance: Predicting Mechanical Strength and Thermal Conductivity from Material Compositions
This study investigates the quantitative relationship between material composition and the performance of foam concrete based on 170 validated experimental datasets extracted from the existing literature. The statistical approach combined with machine learning modeling was employed to systematically...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/13/7125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839632472856330240 |
|---|---|
| author | Leifa Li Wangwen Sun Askar Ayti Wangping Chen Zhuangzhuang Liu Lauren Y. Gómez-Zamorano |
| author_facet | Leifa Li Wangwen Sun Askar Ayti Wangping Chen Zhuangzhuang Liu Lauren Y. Gómez-Zamorano |
| author_sort | Leifa Li |
| collection | DOAJ |
| description | This study investigates the quantitative relationship between material composition and the performance of foam concrete based on 170 validated experimental datasets extracted from the existing literature. The statistical approach combined with machine learning modeling was employed to systematically analyze and predict key performance indicators. Pearson correlation analysis was used to identify the parameters affecting mechanical and thermal properties. The analysis revealed that the water-to-cement ratio (W/C) and cement content were the most influential factors for mechanical properties, while density and the coarse-to-fine aggregate ratio (Cag/Fag) had the greatest impact on thermal conductivity. To overcome the limitations of traditional empirical models in capturing complex nonlinear relationships, a predictive framework with eight machine learning algorithms was established. Among these, Neural Network Regression exhibited the highest accuracy for mechanical property prediction, with a coefficient of determination of R<sup>2</sup> = 0.987 for compressive strength and R<sup>2</sup> = 0.932 for flexural strength. For thermal conductivity, support vector regression achieved the best predictive performance with R<sup>2</sup> = 0.933. Error analysis demonstrated significant differences in prediction accuracy across performance indicators: compressive strength was the easiest to predict, followed by flexural strength, while thermal conductivity was the most challenging. Based on practical engineering requirements, a hierarchical model selection strategy was proposed. Specifically, Neural Network Regression is prioritized for mechanical properties, and support vector regression is prioritized for thermal properties. Decision Tree Regression is recommended as a general-purpose model. The predictive model used in this study provides reliable technical support for the optimization and engineering application of foam concrete, enhancing both prediction accuracy and practical efficiency. |
| format | Article |
| id | doaj-art-e0f092be82924e6fb4cd6b6bcc6ab36c |
| institution | Matheson Library |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-e0f092be82924e6fb4cd6b6bcc6ab36c2025-07-11T14:35:45ZengMDPI AGApplied Sciences2076-34172025-06-011513712510.3390/app15137125Machine Learning Modeling of Foam Concrete Performance: Predicting Mechanical Strength and Thermal Conductivity from Material CompositionsLeifa Li0Wangwen Sun1Askar Ayti2Wangping Chen3Zhuangzhuang Liu4Lauren Y. Gómez-Zamorano5Xinjiang Jiaotou Construction Management Co., Ltd., Urumchi 830000, ChinaSchool of Highway, Chang’an University, Xi’an 710064, ChinaXinjiang Jiaotou Construction Management Co., Ltd., Urumchi 830000, ChinaXinjiang Jiaotou Construction Management Co., Ltd., Urumchi 830000, ChinaSchool of Highway, Chang’an University, Xi’an 710064, ChinaPrograma Doctoral en Ingeniería de Materiales, Facultad de Ingeniería Mecánica y Eléctrica, Universidad Autónoma de Nuevo León, Ave. Universidad s/n, Ciudad Universitaria, San Nicolás de los Garza 66455, Nuevo León, MexicoThis study investigates the quantitative relationship between material composition and the performance of foam concrete based on 170 validated experimental datasets extracted from the existing literature. The statistical approach combined with machine learning modeling was employed to systematically analyze and predict key performance indicators. Pearson correlation analysis was used to identify the parameters affecting mechanical and thermal properties. The analysis revealed that the water-to-cement ratio (W/C) and cement content were the most influential factors for mechanical properties, while density and the coarse-to-fine aggregate ratio (Cag/Fag) had the greatest impact on thermal conductivity. To overcome the limitations of traditional empirical models in capturing complex nonlinear relationships, a predictive framework with eight machine learning algorithms was established. Among these, Neural Network Regression exhibited the highest accuracy for mechanical property prediction, with a coefficient of determination of R<sup>2</sup> = 0.987 for compressive strength and R<sup>2</sup> = 0.932 for flexural strength. For thermal conductivity, support vector regression achieved the best predictive performance with R<sup>2</sup> = 0.933. Error analysis demonstrated significant differences in prediction accuracy across performance indicators: compressive strength was the easiest to predict, followed by flexural strength, while thermal conductivity was the most challenging. Based on practical engineering requirements, a hierarchical model selection strategy was proposed. Specifically, Neural Network Regression is prioritized for mechanical properties, and support vector regression is prioritized for thermal properties. Decision Tree Regression is recommended as a general-purpose model. The predictive model used in this study provides reliable technical support for the optimization and engineering application of foam concrete, enhancing both prediction accuracy and practical efficiency.https://www.mdpi.com/2076-3417/15/13/7125foam concretesustainabilitydata analysismechanical strengththermal conductivitypredictive model |
| spellingShingle | Leifa Li Wangwen Sun Askar Ayti Wangping Chen Zhuangzhuang Liu Lauren Y. Gómez-Zamorano Machine Learning Modeling of Foam Concrete Performance: Predicting Mechanical Strength and Thermal Conductivity from Material Compositions Applied Sciences foam concrete sustainability data analysis mechanical strength thermal conductivity predictive model |
| title | Machine Learning Modeling of Foam Concrete Performance: Predicting Mechanical Strength and Thermal Conductivity from Material Compositions |
| title_full | Machine Learning Modeling of Foam Concrete Performance: Predicting Mechanical Strength and Thermal Conductivity from Material Compositions |
| title_fullStr | Machine Learning Modeling of Foam Concrete Performance: Predicting Mechanical Strength and Thermal Conductivity from Material Compositions |
| title_full_unstemmed | Machine Learning Modeling of Foam Concrete Performance: Predicting Mechanical Strength and Thermal Conductivity from Material Compositions |
| title_short | Machine Learning Modeling of Foam Concrete Performance: Predicting Mechanical Strength and Thermal Conductivity from Material Compositions |
| title_sort | machine learning modeling of foam concrete performance predicting mechanical strength and thermal conductivity from material compositions |
| topic | foam concrete sustainability data analysis mechanical strength thermal conductivity predictive model |
| url | https://www.mdpi.com/2076-3417/15/13/7125 |
| work_keys_str_mv | AT leifali machinelearningmodelingoffoamconcreteperformancepredictingmechanicalstrengthandthermalconductivityfrommaterialcompositions AT wangwensun machinelearningmodelingoffoamconcreteperformancepredictingmechanicalstrengthandthermalconductivityfrommaterialcompositions AT askarayti machinelearningmodelingoffoamconcreteperformancepredictingmechanicalstrengthandthermalconductivityfrommaterialcompositions AT wangpingchen machinelearningmodelingoffoamconcreteperformancepredictingmechanicalstrengthandthermalconductivityfrommaterialcompositions AT zhuangzhuangliu machinelearningmodelingoffoamconcreteperformancepredictingmechanicalstrengthandthermalconductivityfrommaterialcompositions AT laurenygomezzamorano machinelearningmodelingoffoamconcreteperformancepredictingmechanicalstrengthandthermalconductivityfrommaterialcompositions |