Evaluating the strength properties of high-performance concrete in the form of ensemble and hybrid models using deep learning techniques
Abstract In the behavior of concrete, factors such as particle types, water content, aggregates, additives, and binders significantly influence its Compressive Strength (CS) properties. This study develops hybrid and ensemble models to predict compressive CS and slump flow of high-performance concre...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-10860-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849237798362546176 |
|---|---|
| author | Zhe Wang Tao Sun Yan Sun Na Liu |
| author_facet | Zhe Wang Tao Sun Yan Sun Na Liu |
| author_sort | Zhe Wang |
| collection | DOAJ |
| description | Abstract In the behavior of concrete, factors such as particle types, water content, aggregates, additives, and binders significantly influence its Compressive Strength (CS) properties. This study develops hybrid and ensemble models to predict compressive CS and slump flow of high-performance concrete (HPC) using a dataset of 191 mixtures. Admixtures like fly ash and silica fume enhance HPC through hydraulic or pozzolanic activity. Understanding the relationships between HPC components is crucial for computational analysis of CS properties. Deep learning techniques, including hybrid and ensemble methods, were developed to predict these properties with high accuracy. This paper focuses on forecasting models using T-SFIS, GBMBoost, and Decision Tree, combined with metaheuristic algorithms (GWO, QPSO) in hybrid and ensemble frameworks. Sensitivity analysis via SHAP and tenfold cross-validation evaluated model performance. Results showed that the GWO-based GBQP model achieved superior performance ( $${\text{R}}^{2}$$ =0.998, RMSE = 1.216 MPa for compressive CS). The ensemble DGT model ranked second, while T-SFIS performed lowest. For slump flow, TSQP excelled ( $${\text{R}}^{2}$$ =0.984, RMSE = 3.233 mm), closely followed by GBQP. These advanced techniques significantly enhance the efficiency and accuracy of predicting HPC CS properties. |
| format | Article |
| id | doaj-art-c4ae7bd8cf6546f4a67140e242bf69fb |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-c4ae7bd8cf6546f4a67140e242bf69fb2025-08-20T04:01:51ZengNature PortfolioScientific Reports2045-23222025-07-0115113110.1038/s41598-025-10860-yEvaluating the strength properties of high-performance concrete in the form of ensemble and hybrid models using deep learning techniquesZhe Wang0Tao Sun1Yan Sun2Na Liu3National Center for Nanoscience and TechnologyTianjin University Research Institute of Architectural Design and Urban Planning Co., Ltd.Guangzhou Changdi Spatial Information Technology Co., Ltd.Beijing GrandTrend International Economic and Technical Consulting Co., Ltd. Abstract In the behavior of concrete, factors such as particle types, water content, aggregates, additives, and binders significantly influence its Compressive Strength (CS) properties. This study develops hybrid and ensemble models to predict compressive CS and slump flow of high-performance concrete (HPC) using a dataset of 191 mixtures. Admixtures like fly ash and silica fume enhance HPC through hydraulic or pozzolanic activity. Understanding the relationships between HPC components is crucial for computational analysis of CS properties. Deep learning techniques, including hybrid and ensemble methods, were developed to predict these properties with high accuracy. This paper focuses on forecasting models using T-SFIS, GBMBoost, and Decision Tree, combined with metaheuristic algorithms (GWO, QPSO) in hybrid and ensemble frameworks. Sensitivity analysis via SHAP and tenfold cross-validation evaluated model performance. Results showed that the GWO-based GBQP model achieved superior performance ( $${\text{R}}^{2}$$ =0.998, RMSE = 1.216 MPa for compressive CS). The ensemble DGT model ranked second, while T-SFIS performed lowest. For slump flow, TSQP excelled ( $${\text{R}}^{2}$$ =0.984, RMSE = 3.233 mm), closely followed by GBQP. These advanced techniques significantly enhance the efficiency and accuracy of predicting HPC CS properties.https://doi.org/10.1038/s41598-025-10860-ySlump flowCompressive CST-S fuzzy inference systemGradient boosting machinesDecision treeGrey wolf optimizer |
| spellingShingle | Zhe Wang Tao Sun Yan Sun Na Liu Evaluating the strength properties of high-performance concrete in the form of ensemble and hybrid models using deep learning techniques Scientific Reports Slump flow Compressive CS T-S fuzzy inference system Gradient boosting machines Decision tree Grey wolf optimizer |
| title | Evaluating the strength properties of high-performance concrete in the form of ensemble and hybrid models using deep learning techniques |
| title_full | Evaluating the strength properties of high-performance concrete in the form of ensemble and hybrid models using deep learning techniques |
| title_fullStr | Evaluating the strength properties of high-performance concrete in the form of ensemble and hybrid models using deep learning techniques |
| title_full_unstemmed | Evaluating the strength properties of high-performance concrete in the form of ensemble and hybrid models using deep learning techniques |
| title_short | Evaluating the strength properties of high-performance concrete in the form of ensemble and hybrid models using deep learning techniques |
| title_sort | evaluating the strength properties of high performance concrete in the form of ensemble and hybrid models using deep learning techniques |
| topic | Slump flow Compressive CS T-S fuzzy inference system Gradient boosting machines Decision tree Grey wolf optimizer |
| url | https://doi.org/10.1038/s41598-025-10860-y |
| work_keys_str_mv | AT zhewang evaluatingthestrengthpropertiesofhighperformanceconcreteintheformofensembleandhybridmodelsusingdeeplearningtechniques AT taosun evaluatingthestrengthpropertiesofhighperformanceconcreteintheformofensembleandhybridmodelsusingdeeplearningtechniques AT yansun evaluatingthestrengthpropertiesofhighperformanceconcreteintheformofensembleandhybridmodelsusingdeeplearningtechniques AT naliu evaluatingthestrengthpropertiesofhighperformanceconcreteintheformofensembleandhybridmodelsusingdeeplearningtechniques |