Predicting penetration depth in ultra-high-performance concrete targets under ballistic impact: An interpretable machine learning approach augmented by deep generative adversarial network
In recent decades, numerous explosions and ballistic attacks have caused significant global loss of life and property. Ultra-high-performance concrete (UHPC) minimizes blast and impact damage to structures and can be applied to protective walls and bunkers. Many researchers have proposed methods to...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123024021522 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553820703784960 |
|---|---|
| author | Majid Khan Muhammad Faisal Javed Nashwan Adnan Othman Sardar Kashif Ur Rehman Furqan Ahmad |
| author_facet | Majid Khan Muhammad Faisal Javed Nashwan Adnan Othman Sardar Kashif Ur Rehman Furqan Ahmad |
| author_sort | Majid Khan |
| collection | DOAJ |
| description | In recent decades, numerous explosions and ballistic attacks have caused significant global loss of life and property. Ultra-high-performance concrete (UHPC) minimizes blast and impact damage to structures and can be applied to protective walls and bunkers. Many researchers have proposed methods to estimate projectile penetration depth in concrete, but accurate estimation remains unresolved due to the phenomena's complexity. This paper explores interpretable machine learning (ML) methods to estimate penetration depth in UHPC targets under ballistic impact using 103 data points from the literature. To address the limited experimental data for assessing UHPC impact resistance, a deep generative adversarial network (DGAN) is used for data augmentation. The comparison of real and DGAN-generated data showed the DGAN's effectiveness in replicating the real data's probability distribution. The ML models exhibited excellent accuracy in estimating penetration depth in UHPC targets, with correlation (R) exceeding 0.855 for DGAN data and 0.954 for real data. The extreme gradient boosting (XGBoost) model achieved high accuracy with R and mean absolute error (MAE) values of 0.990 and 4.933, respectively. A comparison with existing empirical models indicated the superiority of the ML-based models. Interpretability techniques revealed that projectile features like impact energy, velocity, diameter, and mass, along with the target's compressive strength and fiber addition, significantly influence penetration depth. The study underscores the potential of explainable ML augmented by DGAN as a valuable tool for predicting penetration depth in UHPC targets under ballistic impact, particularly with limited data. |
| format | Article |
| id | doaj-art-6d7bec0891d944cb874ed2b08cdc5a6c |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-6d7bec0891d944cb874ed2b08cdc5a6c2025-01-09T06:14:31ZengElsevierResults in Engineering2590-12302025-03-0125103909Predicting penetration depth in ultra-high-performance concrete targets under ballistic impact: An interpretable machine learning approach augmented by deep generative adversarial networkMajid Khan0Muhammad Faisal Javed1Nashwan Adnan Othman2Sardar Kashif Ur Rehman3Furqan Ahmad4Department of Civil Engineering, Southern Illinois University, Edwardsville, IL 62026, USADepartment of Civil Engineering, GIK Institute of Engineering Sciences and Technology, Swabi 23640, PakistanDepartment of Computer Engineering, College of Engineering, Knowledge University, Erbil 44001, Iraq; Department of Computer Engineering, Al-Kitab University, Altun Kupri, IraqDepartment of Civil Engineering, COMSATS University Islamabad, Abbottabad Campus, Abbottabad 22060, PakistanUNHCR, Afghanistan; Corresponding author.In recent decades, numerous explosions and ballistic attacks have caused significant global loss of life and property. Ultra-high-performance concrete (UHPC) minimizes blast and impact damage to structures and can be applied to protective walls and bunkers. Many researchers have proposed methods to estimate projectile penetration depth in concrete, but accurate estimation remains unresolved due to the phenomena's complexity. This paper explores interpretable machine learning (ML) methods to estimate penetration depth in UHPC targets under ballistic impact using 103 data points from the literature. To address the limited experimental data for assessing UHPC impact resistance, a deep generative adversarial network (DGAN) is used for data augmentation. The comparison of real and DGAN-generated data showed the DGAN's effectiveness in replicating the real data's probability distribution. The ML models exhibited excellent accuracy in estimating penetration depth in UHPC targets, with correlation (R) exceeding 0.855 for DGAN data and 0.954 for real data. The extreme gradient boosting (XGBoost) model achieved high accuracy with R and mean absolute error (MAE) values of 0.990 and 4.933, respectively. A comparison with existing empirical models indicated the superiority of the ML-based models. Interpretability techniques revealed that projectile features like impact energy, velocity, diameter, and mass, along with the target's compressive strength and fiber addition, significantly influence penetration depth. The study underscores the potential of explainable ML augmented by DGAN as a valuable tool for predicting penetration depth in UHPC targets under ballistic impact, particularly with limited data.http://www.sciencedirect.com/science/article/pii/S2590123024021522Ultra-high-performance concretePenetration depthBallistic impactExplainable machine learningDeep generative adversarial network |
| spellingShingle | Majid Khan Muhammad Faisal Javed Nashwan Adnan Othman Sardar Kashif Ur Rehman Furqan Ahmad Predicting penetration depth in ultra-high-performance concrete targets under ballistic impact: An interpretable machine learning approach augmented by deep generative adversarial network Results in Engineering Ultra-high-performance concrete Penetration depth Ballistic impact Explainable machine learning Deep generative adversarial network |
| title | Predicting penetration depth in ultra-high-performance concrete targets under ballistic impact: An interpretable machine learning approach augmented by deep generative adversarial network |
| title_full | Predicting penetration depth in ultra-high-performance concrete targets under ballistic impact: An interpretable machine learning approach augmented by deep generative adversarial network |
| title_fullStr | Predicting penetration depth in ultra-high-performance concrete targets under ballistic impact: An interpretable machine learning approach augmented by deep generative adversarial network |
| title_full_unstemmed | Predicting penetration depth in ultra-high-performance concrete targets under ballistic impact: An interpretable machine learning approach augmented by deep generative adversarial network |
| title_short | Predicting penetration depth in ultra-high-performance concrete targets under ballistic impact: An interpretable machine learning approach augmented by deep generative adversarial network |
| title_sort | predicting penetration depth in ultra high performance concrete targets under ballistic impact an interpretable machine learning approach augmented by deep generative adversarial network |
| topic | Ultra-high-performance concrete Penetration depth Ballistic impact Explainable machine learning Deep generative adversarial network |
| url | http://www.sciencedirect.com/science/article/pii/S2590123024021522 |
| work_keys_str_mv | AT majidkhan predictingpenetrationdepthinultrahighperformanceconcretetargetsunderballisticimpactaninterpretablemachinelearningapproachaugmentedbydeepgenerativeadversarialnetwork AT muhammadfaisaljaved predictingpenetrationdepthinultrahighperformanceconcretetargetsunderballisticimpactaninterpretablemachinelearningapproachaugmentedbydeepgenerativeadversarialnetwork AT nashwanadnanothman predictingpenetrationdepthinultrahighperformanceconcretetargetsunderballisticimpactaninterpretablemachinelearningapproachaugmentedbydeepgenerativeadversarialnetwork AT sardarkashifurrehman predictingpenetrationdepthinultrahighperformanceconcretetargetsunderballisticimpactaninterpretablemachinelearningapproachaugmentedbydeepgenerativeadversarialnetwork AT furqanahmad predictingpenetrationdepthinultrahighperformanceconcretetargetsunderballisticimpactaninterpretablemachinelearningapproachaugmentedbydeepgenerativeadversarialnetwork |