What question did this study set out to answer?

This study aims to optimize the prediction of compressive strength in self-compacting concrete using hybrid machine learning techniques.

May 22, 2026Open Access

Hybrid machine learning for SCC strength prediction using metaheuristic optimization

ASAkhilendra SharmaVisvesvaraya National Institute of Technology RBRahul BiswasVisvesvaraya National Institute of Technology SSSharad SinghVisvesvaraya National Institute of Technology

Key Points

This study aims to optimize the prediction of compressive strength in self-compacting concrete using hybrid machine learning techniques.
Developed a hybrid Machine Learning framework integrating Gradient Boosting, Adaptive Boosting, and Random Forest models.
Utilized metaheuristic optimization with algorithms like Grey Wolf Optimizer and Brown Bear Optimizer for model enhancement.
Validated the model on a dataset of 691 SCC samples under various mix proportions and curing conditions.
BBOA-GB model achieved the highest predictive accuracy with R² values of 0.9955 in training and 0.9645 in testing.
Identified the significant factors for compressive strength as slag content, cement content, and curing age using SHAP analysis.
Hybrid approach outperformed baseline ensemble models, contributing a reliable framework for SCC design.

Abstract

Abstract Self-Compacting Concrete (SCC) represents a significant innovation in modern concrete technology owing to its excellent flowability, workability, and mechanical performance. Accurate prediction of SCC compressive strength is essential for optimizing mix design, minimizing experimental effort, and promoting sustainable material usage. In this study, a hybrid Machine Learning (ML) framework was developed by integrating Gradient Boosting (GB), Adaptive Boosting (ADA), and Random Forest (RF) models, optimized through metaheuristic algorithms such as Grey Wolf Optimizer (GWO), Mountain Gazelle Optimizer (MGO), Brown Bear Optimizer Algorithm (BBOA), and Fox Optimizer (FO). A dataset containing 691 SCC samples with varied mix proportions and curing conditions was utilized for model development and validation. Statistical analysis using the coefficient of determination (R 2 ), Root Mean Square Error (RMSE), Weighted Mean Absolute Percentage Error (WMAPE), and Willmott’s Index of Agreement (WI) revealed that the BBOA-GB model exhibited the highest predictive accuracy, with R 2 values of 0.9955 and 0.9645 for training and testing, respectively. SHapley Additive exPlanations (SHAP) analysis indicated that slag content, cement content and curing age were the most influential factors affecting compressive strength. The proposed hybrid approach demonstrated improved performance compared to the considered baseline ensemble models. The novelty of this research lies in the comparative benchmarking of multiple metaheuristic–ensemble integrations and the development of a Graphical User Interface (GUI) for practical SCC strength prediction. The study contributes a reliable and efficient data-driven framework that enhances decision-making in SCC design and supports the advancement of sustainable concrete technology. However, the study is limited by the use of literature-based datasets and a restricted range of mix compositions. Future research will focus on incorporating larger and real-time datasets, exploring deep learning approaches, and extending the framework toward sustainability-driven mix optimization.

KI fragen

Bookmark

View Full Paper