Previous Article in Journal
Energy Management and Power Distribution for Battery/Ultracapacitor Hybrid Energy Storage System in Electric Vehicles with Regenerative Braking Control
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Hybrid Deep Reinforcement Learning Architecture for Optimizing Concrete Mix Design Through Precision Strength Prediction

1
Department of Civil Engineering, College of Engineering, Yazd Branch, Islamic Azad University, Yazd 89168-71967, Iran
2
Department of Industrial Engineering, Ankara Yıldırım Beyazıt University, 06010 Ankara, Turkey
*
Author to whom correspondence should be addressed.
Math. Comput. Appl. 2025, 30(4), 83; https://doi.org/10.3390/mca30040083 (registering DOI)
Submission received: 29 June 2025 / Revised: 23 July 2025 / Accepted: 30 July 2025 / Published: 3 August 2025
(This article belongs to the Section Engineering)

Abstract

Concrete mix design plays a pivotal role in ensuring the mechanical performance, durability, and sustainability of construction projects. However, the nonlinear interactions among the mix components challenge traditional approaches in predicting compressive strength and optimizing proportions. This study presents a two-stage hybrid framework that integrates deep learning with reinforcement learning to overcome these limitations. First, a Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) model was developed to capture spatial–temporal patterns from a dataset of 1030 historical concrete samples. The extracted features were enhanced using an eXtreme Gradient Boosting (XGBoost) meta-model to improve generalizability and noise resistance. Then, a Dueling Double Deep Q-Network (Dueling DDQN) agent was used to iteratively identify optimal mix ratios that maximize the predicted compressive strength. The proposed framework outperformed ten benchmark models, achieving an MAE of 2.97, RMSE of 4.08, and R2 of 0.94. Feature attribution methods—including SHapley Additive exPlanations (SHAP), Elasticity-Based Feature Importance (EFI), and Permutation Feature Importance (PFI)—highlighted the dominant influence of cement content and curing age, as well as revealing non-intuitive effects such as the compensatory role of superplasticizers in low-water mixtures. These findings demonstrate the potential of the proposed approach to support intelligent concrete mix design and real-time optimization in smart construction environments.
Keywords: compressive strength prediction of concrete; optimal concrete mix selection; hybrid neural network; reinforcement learning; dueling double deep Q-network (dueling DDQN) compressive strength prediction of concrete; optimal concrete mix selection; hybrid neural network; reinforcement learning; dueling double deep Q-network (dueling DDQN)

Share and Cite

MDPI and ACS Style

Mirzaei, A.; Aghsami, A. A Hybrid Deep Reinforcement Learning Architecture for Optimizing Concrete Mix Design Through Precision Strength Prediction. Math. Comput. Appl. 2025, 30, 83. https://doi.org/10.3390/mca30040083

AMA Style

Mirzaei A, Aghsami A. A Hybrid Deep Reinforcement Learning Architecture for Optimizing Concrete Mix Design Through Precision Strength Prediction. Mathematical and Computational Applications. 2025; 30(4):83. https://doi.org/10.3390/mca30040083

Chicago/Turabian Style

Mirzaei, Ali, and Amir Aghsami. 2025. "A Hybrid Deep Reinforcement Learning Architecture for Optimizing Concrete Mix Design Through Precision Strength Prediction" Mathematical and Computational Applications 30, no. 4: 83. https://doi.org/10.3390/mca30040083

APA Style

Mirzaei, A., & Aghsami, A. (2025). A Hybrid Deep Reinforcement Learning Architecture for Optimizing Concrete Mix Design Through Precision Strength Prediction. Mathematical and Computational Applications, 30(4), 83. https://doi.org/10.3390/mca30040083

Article Metrics

Back to TopTop