Prognosticating fabric-reinforced cementitious matrix-to-masonry bond and failure mechanisms using novel tabular variational autoencoder-augmented probabilistic model

Fabric-reinforced cementitious matrix (FRCM) composite strengthening has emerged as an environmentally friendly and less invasive solution, and entails material compatibility with masonry substrates, and hence emerges as the sustainable solution for structural restoration. But the performance of the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Engineering applications of artificial intelligence Jg. 163; S. 113059
Hauptverfasser: Kumar, Aman, Marani, Afshin, Abbas, Asim, Nehdi, Moncef L.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.01.2026
Schlagworte:
Bayesian neural network
Bond strength
Fiber-reinforced cementitious matrix
Masonry
Natural gradient boosting
Probabilistic learning
Synthetic data
Tabular variational autoencoder
Fiber-reinforced cementitious matrix
Bond strength
Natural gradient boosting
Tabular variational autoencoder
Masonry
Probabilistic learning
Bayesian neural network
Synthetic data
ISSN:0952-1976
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Fabric-reinforced cementitious matrix (FRCM) composite strengthening has emerged as an environmentally friendly and less invasive solution, and entails material compatibility with masonry substrates, and hence emerges as the sustainable solution for structural restoration. But the performance of the FRCM system primarily depends on the bond behaviour between the masonry and composite interface, which governs stress transfer and failure mode. However, the available experimental datasets lack diversity, especially with respect to categorical characteristics, limiting predictive capability and extrapolation potential of data-driven models. Therefore, in this study, a tabular variational autoencoder model was implemented to synthetically augment the experimental database to capture a higher range of input variability. Using this enriched dataset, probabilistic modelling techniques have been utilized, including Gaussian process, Bayesian neural network, and natural gradient boosting (NGB) in predicting critical FRCM-to-masonry bond behaviour that includes bond strength, slip, and respective failure modes. Among these developed probabilistic models, the NGB model performed both better in terms of accuracy as well as uncertainty quantification and gave interpretable results on the importance of features. Mean absolute percentage error value of the testing set of the NGB model using the synthetic dataset approach was 22.72% and 23.83% for bond strength and slip, respectively. For failure modes, the accuracy of the NGB model for the testing set was 84% with the synthetic dataset. The proposed hybrid method enhances predictability and aids in formulating more precise and uncertainty-based design strategies for the sustainable rehabilitation of deteriorated masonry infrastructure. •First study to fuse generative AI with probabilistic deep learning for predicting FRCM–masonry bond behaviour.•Synthetic data augmentation tackles data scarcity, boosting model robustness and generalizability.•NGB model delivers superior accuracy, uncertainty quantification, and interpretable feature relevance.•Novel framework enables more reliable predictions and uncertainty-informed design for sustainable masonry retrofitting.
ISSN:0952-1976
DOI:10.1016/j.engappai.2025.113059