Optimizing concrete strength: How nanomaterials and AI redefine mix design
Nanomaterials and supplementary cementitious materials (SCMs) are typically used together in efforts to enhance the performance of concrete and mitigate the environmental impact of concrete construction. However, the complex interactions between nanomaterials, SCMs, and cement make concrete mix desi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Case Studies in Construction Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214509525006369 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850122204846489600 |
|---|---|
| author | Dan Huang Guangshuai Han Ziyang Tang |
| author_facet | Dan Huang Guangshuai Han Ziyang Tang |
| author_sort | Dan Huang |
| collection | DOAJ |
| description | Nanomaterials and supplementary cementitious materials (SCMs) are typically used together in efforts to enhance the performance of concrete and mitigate the environmental impact of concrete construction. However, the complex interactions between nanomaterials, SCMs, and cement make concrete mix design a challenging, iterative, and labor-intensive process, often relying on trial-and-error experimentation. Machine learning (ML) offers an opportunity to better understand the influence of input parameters and to accelerate the optimization of mix designs through data-driven insights. This study proposes an open-source and easy-to-access framework, Canopy, to support the concrete research community in optimizing mix design. Using a dataset collected from the literature, detailed analyses were conducted using Ridge Regression (RR), Artificial Neural Network (ANN), Random Forest (RF), and Extreme Gradient Boosting (XGB). Model performances were evaluated using metrics including Root Mean Square Errors (RMSE), Mean Absolute Error (MAE), R-squared (R2), Normalized Mean Bias Error (NMBE), and Mean Absolute Percentage Error (MAPE). XGB was identified as the most effective ML algorithm for predicting compressive strength among others in this study (R2=0.974). Furthermore, the framework incorporates post-analysis tools, such as Shapley Additive exPlanations (SHAP), to provide interpretable insights into the importance of various input parameters. The findings highlight the critical role of nanomaterials, contributing 7.8 % to the overall improvement in compressive strength, underscoring their significance in concrete performance modification. By combining predictive modeling with interpretability, this framework aims to streamline the design process and reduce experimental workload. Beyond its technical contributions, this study emphasizes the broader impact of integrating machine learning into concrete research, paving the way for more sustainable, efficient, and data-driven approaches in the development of advanced construction materials. |
| format | Article |
| id | doaj-art-aabf3297aec640c6829147ff7ad344eb |
| institution | OA Journals |
| issn | 2214-5095 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Construction Materials |
| spelling | doaj-art-aabf3297aec640c6829147ff7ad344eb2025-08-20T02:34:53ZengElsevierCase Studies in Construction Materials2214-50952025-07-0122e0483810.1016/j.cscm.2025.e04838Optimizing concrete strength: How nanomaterials and AI redefine mix designDan Huang0Guangshuai Han1Ziyang Tang2Department of Physics and Engineering Science, Coastal Carolina University, Conway, SC 29528, United States; Corresponding author.Lyles School of Civil and Construction Engineering, Purdue University, West Lafayette, IN 47906, United StatesSchool of Engineering Technology, Purdue University, West Lafayette, IN 47906, United StatesNanomaterials and supplementary cementitious materials (SCMs) are typically used together in efforts to enhance the performance of concrete and mitigate the environmental impact of concrete construction. However, the complex interactions between nanomaterials, SCMs, and cement make concrete mix design a challenging, iterative, and labor-intensive process, often relying on trial-and-error experimentation. Machine learning (ML) offers an opportunity to better understand the influence of input parameters and to accelerate the optimization of mix designs through data-driven insights. This study proposes an open-source and easy-to-access framework, Canopy, to support the concrete research community in optimizing mix design. Using a dataset collected from the literature, detailed analyses were conducted using Ridge Regression (RR), Artificial Neural Network (ANN), Random Forest (RF), and Extreme Gradient Boosting (XGB). Model performances were evaluated using metrics including Root Mean Square Errors (RMSE), Mean Absolute Error (MAE), R-squared (R2), Normalized Mean Bias Error (NMBE), and Mean Absolute Percentage Error (MAPE). XGB was identified as the most effective ML algorithm for predicting compressive strength among others in this study (R2=0.974). Furthermore, the framework incorporates post-analysis tools, such as Shapley Additive exPlanations (SHAP), to provide interpretable insights into the importance of various input parameters. The findings highlight the critical role of nanomaterials, contributing 7.8 % to the overall improvement in compressive strength, underscoring their significance in concrete performance modification. By combining predictive modeling with interpretability, this framework aims to streamline the design process and reduce experimental workload. Beyond its technical contributions, this study emphasizes the broader impact of integrating machine learning into concrete research, paving the way for more sustainable, efficient, and data-driven approaches in the development of advanced construction materials.http://www.sciencedirect.com/science/article/pii/S2214509525006369ConcreteMachine learningNanoparticlesSupplementary cementitious materialsK-fold cross-validationCompressive strength |
| spellingShingle | Dan Huang Guangshuai Han Ziyang Tang Optimizing concrete strength: How nanomaterials and AI redefine mix design Case Studies in Construction Materials Concrete Machine learning Nanoparticles Supplementary cementitious materials K-fold cross-validation Compressive strength |
| title | Optimizing concrete strength: How nanomaterials and AI redefine mix design |
| title_full | Optimizing concrete strength: How nanomaterials and AI redefine mix design |
| title_fullStr | Optimizing concrete strength: How nanomaterials and AI redefine mix design |
| title_full_unstemmed | Optimizing concrete strength: How nanomaterials and AI redefine mix design |
| title_short | Optimizing concrete strength: How nanomaterials and AI redefine mix design |
| title_sort | optimizing concrete strength how nanomaterials and ai redefine mix design |
| topic | Concrete Machine learning Nanoparticles Supplementary cementitious materials K-fold cross-validation Compressive strength |
| url | http://www.sciencedirect.com/science/article/pii/S2214509525006369 |
| work_keys_str_mv | AT danhuang optimizingconcretestrengthhownanomaterialsandairedefinemixdesign AT guangshuaihan optimizingconcretestrengthhownanomaterialsandairedefinemixdesign AT ziyangtang optimizingconcretestrengthhownanomaterialsandairedefinemixdesign |