TY - JOUR
T1 - Hybrid framework of penetration resistance analysis by machine learning and finite element simulation
AU - Long, Xu
AU - Ali, Irfan
AU - Maqbool, Khawaja Haseeb
AU - Khan, Muhammad Muaz
N1 - Publisher Copyright:
© 2025 Elsevier Ltd.
PY - 2026/1/1
Y1 - 2026/1/1
N2 - A comprehensive understanding of projectile penetration in reinforced concrete (RC) structures is essential for developing resilient defense and infrastructure systems. Such investigations provide valuable insights into the behavior of structural components under extreme loading conditions. However, accurately modeling penetration resistance remains challenging due to the complex interaction among projectile velocity, geometry, and the nonlinear behavior of concrete. To address this challenge, this study applies artificial intelligence (AI) techniques in combination with finite element (FE) simulations to enhance predictive modeling. The AI framework incorporates deep neural networks (DNN), support vector machines (SVM), and random forests (RF) for prediction and classification tasks, while Bayesian neural networks (BNN) are employed for uncertainty quantification, providing statistically reliable confidence bounds for the depth of penetration (DoP). Damage categorization is further optimized through K-means clustering, enabling clear differentiation between minor and severe damage states. The analysis is based on 540 data samples generated from a validated FE model calibrated with experimental results. The hybrid DNN–RF model achieved an R2 of 0.994 for DoP prediction, while the SVM attained 99.08 % precision in damage classification and the RF achieved 98.16 % accuracy in ballistic limit prediction. The BNN yielded a 95 % confidence interval, confirming the reliability of the AI-based predictions. Among various clustering algorithms, including Density-Based Spatial Clustering of Applications with Noise, Gaussian Mixture Models, and hierarchical clustering, K-means demonstrated the best performance. The proposed AI-driven framework provides a reliable and efficient tool for rapid RC design assessment and optimization, contributing to advancements in defense, infrastructure resilience, and high-performance structural engineering.
AB - A comprehensive understanding of projectile penetration in reinforced concrete (RC) structures is essential for developing resilient defense and infrastructure systems. Such investigations provide valuable insights into the behavior of structural components under extreme loading conditions. However, accurately modeling penetration resistance remains challenging due to the complex interaction among projectile velocity, geometry, and the nonlinear behavior of concrete. To address this challenge, this study applies artificial intelligence (AI) techniques in combination with finite element (FE) simulations to enhance predictive modeling. The AI framework incorporates deep neural networks (DNN), support vector machines (SVM), and random forests (RF) for prediction and classification tasks, while Bayesian neural networks (BNN) are employed for uncertainty quantification, providing statistically reliable confidence bounds for the depth of penetration (DoP). Damage categorization is further optimized through K-means clustering, enabling clear differentiation between minor and severe damage states. The analysis is based on 540 data samples generated from a validated FE model calibrated with experimental results. The hybrid DNN–RF model achieved an R2 of 0.994 for DoP prediction, while the SVM attained 99.08 % precision in damage classification and the RF achieved 98.16 % accuracy in ballistic limit prediction. The BNN yielded a 95 % confidence interval, confirming the reliability of the AI-based predictions. Among various clustering algorithms, including Density-Based Spatial Clustering of Applications with Noise, Gaussian Mixture Models, and hierarchical clustering, K-means demonstrated the best performance. The proposed AI-driven framework provides a reliable and efficient tool for rapid RC design assessment and optimization, contributing to advancements in defense, infrastructure resilience, and high-performance structural engineering.
KW - Artificial intelligence
KW - Ballistic limit
KW - Damage classification
KW - Depth of penetration
KW - Finite element simulation
KW - Hybrid machine learning
KW - Uncertainty quantification
UR - https://www.scopus.com/pages/publications/105020914723
U2 - 10.1016/j.engappai.2025.112868
DO - 10.1016/j.engappai.2025.112868
M3 - 文章
AN - SCOPUS:105020914723
SN - 0952-1976
VL - 163
JO - Engineering Applications of Artificial Intelligence
JF - Engineering Applications of Artificial Intelligence
M1 - 112868
ER -