Domain-Adaptive Graph Attention Semi-Supervised Network for Temperature-Resilient SHM of Composite Plates

Rezazadeh, Nima and De Luca, Alessandro and Perfetto, Donato and Lamanna, Giuseppe and Annaz, Fawaz and de Oliveira, Mario A. (2025) Domain-Adaptive Graph Attention Semi-Supervised Network for Temperature-Resilient SHM of Composite Plates. Sensors, 25 (22). p. 6847. ISSN 1424-8220

Preview

Text sensors-25-06847.pdf - Published Version Available under License Creative Commons Attribution. Download (6MB)

Abstract

This study introduces GAT-CAMDA, a novel framework for the structural health monitoring (SHM) of composite materials under temperature-induced variability, leveraging the powerful feature extraction capabilities of Graph Attention Networks (GATs) and advanced domain adaptation (DA) techniques. By combining Maximum Mean Discrepancy (MMD) and Correlation Alignment (CORAL) losses with a domain-discriminative adversarial model, the framework achieves scalable alignment of feature distributions across temperature domains, ensuring robust damage detection. A simple yet at the same time efficient data augmentation process extrapolates damage behaviour across unmeasured temperature conditions, addressing the scarcity of damaged-state observations. Hyperparameter optimisation via Optuna not only identifies the optimal settings to enhance model performance, achieving a classification accuracy of 95.83% on a benchmark dataset, but also illustrates hyperparameter significance for explainability. Additionally, the GAT architecture’s attention demonstrates the importance of various sensors, enhancing transparency and reliability in damage detection. The dual use of Optuna serves to refine model accuracy and elucidate parameter impacts, while GAT-CAMDA represents a significant advancement in SHM, enabling precise, interpretable, and scalable diagnostics across complex operational environments.

Item Type:	Article
Identification Number:	10.3390/s25226847
Dates:	Date Event 7 November 2025 Accepted 9 November 2025 Published Online
Uncontrolled Keywords:	structural health monitoring (SHM), composite materials, graph attention networks (GATs), domain adaptation (DA), temperature variability, explainability
Subjects:	CAH10 - engineering and technology > CAH10-01 - engineering > CAH10-01-02 - mechanical engineering
Divisions:	Architecture, Built Environment, Computing and Engineering > Engineering
Depositing User:	Gemma Tonks
Date Deposited:	19 Nov 2025 15:07
Last Modified:	19 Nov 2025 15:07
URI:	https://www.open-access.bcu.ac.uk/id/eprint/16728

Actions (login required)

View Item