Influence of prefabricated fissure angles on mechanical and infrared properties of red sandstone and failure prediction based on deep learning
Résumé fourni par la source
Understanding the influence of structural planes on rock failure is crucial for engineering safety. In this study, uniaxial compression tests combined with infrared thermography monitoring were conducted on red sandstone with prefabricated fissure of different inclinations to explore its mechanical and infrared thermal response characteristics. The results indicate that the fracture inclination angle determines the failure mode,transitioning from tension-dominated to shear-dominated.Furthermore,it influences the trend of peak strength variation, which exhibits an increase with higher inclination angles . During failure, all specimens exhibit a sudden temperature rise caused by frictional Heating. Key indicators such as the standard deviation of infrared radiation temperature can effectively quantify the thermal field inhomogeneity associated with shear crack propagation. To predict failure using thermal precursors, a 1D-CNN-Bi-LSTM-Attention hybrid deep learning model was developed, which predicts stress-time curves by capturing the spatiotemporal evolution dynamics of infrared data. Through fourfold cross-validation, the model achieves a coefficient of determination (R 2 ) greater than 0.99 and a root mean square error (RMSE) less than 1.0 for all fractured specimens, demonstrating excellent generalization ability and robustness. This study clarifies the link between the failure mechanism of fractured rocks and infrared energy release, providing a technical framework for the development of intelligent non-destructive early warning systems for rock mass stability.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- Influence of prefabricated fissure angles on mechanical and infrared properties of red sandstone and failure prediction based on deep learning
- Date Crossref
- 08/10/2025
- Éditeur
- Springer Science and Business Media LLC
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude et ne compte pas comme une seconde source scientifique indépendante.
Institutions déclarées
Une affiliation ne permet pas de déduire la nationalité d’un auteur.