Dynamic Strength Prediction of Brittle Engineering Materials via Stacked Multi-Model Ensemble Learning and Interpretability-Driven Feature Analysis
Materials · 27.06.2025 · 18 (13) · 3054
DOI: 10.3390/ma18133054 ↗Kurz gefasst
Fachartikel in der Zeitschrift Materials, online erschienen am 27.06.2025. Verfasst von Xin Cai und 6 weiteren Autor:innen. Beteiligte Einrichtung: Sinosteel Maanshan General Institute of Mining Research Co., Ltd., Maanshan 243000, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Hunan Natural Science Foundation for Outstanding Youth Program, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Accurate prediction of the dynamic compressive strength of brittle engineering materials is of significant theoretical and engineering importance for underground engineering design, safety assessment, and dynamic hazard prevention. To enhance prediction accuracy and model interpretability, this study proposes a novel framework integrating stacking ensemble learning with SHapley Additive exPlanations (SHAP) for dynamic strength prediction. Leveraging multidimensional input variables, including static strength, strain rate, P-wave velocity, bulk density, and specimen geometry parameters, we constructed six machine learning regression models: K-Nearest Neighbors (KNN), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), LightGBM, XGBoost, and Multilayer Perceptron Neural Network (MLPNN). Through comparative performance evaluation, optimal base models were selected for stacking ensemble training. Results demonstrate that the proposed stacking model outperforms individual models in prediction accuracy, stability, and generalization capability. Further SHAP-based interpretability analysis reveals that strain rate dominates the prediction outcomes, with its SHAP values exhibiting a characteristic nonlinear response trend. Additionally, structural and mechanical variables such as static strength, P-wave velocity, and bulk density demonstrate significant positive contributions to model outputs. This framework provides a robust tool for intelligent prediction and mechanistic interpretation of the dynamic strength of brittle materials.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Sinosteel Maanshan General Institute of Mining Research Co., Ltd., Maanshan 243000, China.
- School of Resources and Safety Engineering, Central South University, Changsha 410083, China.
- PowerChina Zhongnan Engineering Co., Ltd., Changsha 410014, China.
- Changsha Nonferrous Metallurgical Design and Research Institute Co., Ltd., Changsha 410007, China.
- Zijin Mining Group Co. Ltd., Longyan 364024, China.
- Hunan Nuclear Geological Survey Institute, Changsha 410114, China.
ORCID-Profile: Xin Cai
Förderung
- National Natural Science Foundation of China
- Hunan Natural Science Foundation for Outstanding Youth Program
- China Postdoctoral Science Foundation
- Co-development Project of Central South University and Zijin Mining Group
Zitieren
APA
Cai, X., Wang, Y., Zhao, Y., Chen, L., Wang, P., Wang, Z., & Li, J. (2025). Dynamic Strength Prediction of Brittle Engineering Materials via Stacked Multi-Model Ensemble Learning and Interpretability-Driven Feature Analysis. Materials, 18(13), 3054. https://doi.org/10.3390/ma18133054
Vancouver
Cai X, Wang Y, Zhao Y, Chen L, Wang P, Wang Z, et al. Dynamic Strength Prediction of Brittle Engineering Materials via Stacked Multi-Model Ensemble Learning and Interpretability-Driven Feature Analysis. Materials. 2025;18(13):3054. doi:10.3390/ma18133054
BibTeX
@article{Cai2025,
author = {Cai, Xin and Wang, Yunmin and Zhao, Yihan and Chen, Liye and Wang, Peiyu and Wang, Zhongkang and Li, Jianguo},
title = {Dynamic Strength Prediction of Brittle Engineering Materials via Stacked Multi-Model Ensemble Learning and Interpretability-Driven Feature Analysis},
journal = {Materials},
year = {2025},
volume = {18},
number = {13},
pages = {3054},
doi = {10.3390/ma18133054}
}
EUVIMED