This study represents a significant advancement in structural health monitoring by integrating infrared thermography (IRT) with cutting-edge deep learning techniques, specifically through the use of the Mask R-CNN neural network. This approach targets the precise detection and segmentation of hidden defects within the interfacial layers of Fiber-Reinforced Polymer (FRP)-reinforced concrete structures. Employing a dual RGB and thermal camera setup, we captured and meticulously aligned image data, which were then annotated for semantic segmentation to train the deep learning model. The fusion of the RGB and thermal imaging significantly enhanced the model’s capabilities, achieving an average accuracy of 96.28% across a 5-fold cross-validation. The model demonstrated robust performance, consistently identifying true negatives with an average specificity of 96.78% and maintaining high precision at 96.42% in accurately delineating damaged areas. It also showed a high recall rate of 96.91%, effectively recognizing almost all actual cases of damage, which is crucial for the maintenance of structural integrity. The balanced precision and recall culminated in an average F1-score of 96.78%, highlighting the model’s effectiveness in comprehensive damage assessment. Overall, this synergistic approach of combining IRT and deep learning provides a powerful tool for the automated inspection and preservation of critical infrastructure components.

The integrity of Concrete-Filled Steel Tubular (CFST) columns can be significantly compromised by subsurface voids or defects, which pose substantial safety risks. This study proposes a novel Dual-Branch Convolutional Neural Network (CNN) Framework with Multi-modal Feature Fusion for detecting subsurface defects in CFST columns. The proposed method leverages the strengths of CNNs in feature extraction and combines multiple modalities of data, such as time-domain and Gramian Angular Field (GAF) image features, to enhance detection performance. By employing a dual-branch structure, the model can capture both temporal and spectral characteristics of percussion signals, leading to more accurate and robust predictions. Field experiments on high-rise building CFST columns demonstrate that the percussion method, validated by thermal imaging, effectively identifies void locations with an accuracy of 94.5%. The results indicate that the proposed method outperforms traditional techniques, providing a reliable solution for structural health monitoring and ensuring the safety and longevity of CFST columns.

This study investigates a neural network model regularized by the Maxwell–Eucken formulation for predicting the thermal conductivity of foamed concrete. Backed by experimental measurements, the modeling workflow incorporates augmented samples derived from the empirical dataset. A total of 30 experimental records, categorized into five distinct mixture groups, provide the foundational data basis. Bulk density and density-derived porosity serve as model inputs, both reflecting the same underlying variation in material density. Evaluation results demonstrate that the proposed hybrid model achieves a coefficient of determination (R²) of 0.7701, substantially outperforming the standalone Maxwell–Eucken model (R² = 0.4546) and the effective medium theory (R² = 0.3041). Although these indicators reflect an improved in-sample fit, they neither isolate the explicit contribution of the physics-informed penalty nor establish the model’s predictive capability for unseen mixtures. The Maxwell–Eucken term functions as an approximate constitutive regularizer, whereas the clustered residuals highlight specific boundary conditions where further model refinement is warranted. Overall, this study validates the feasibility of the hybrid modeling approach within the tested material domain; group-separated validation and comparative benchmarks against purely data-driven models are required to assess its broader generalizability.