In composite structures, the precise identification and localization of damage is necessary to preserve structural integrity in applications across such fields as aeronautical, civil, and mechanical engineering. This study presents a deep learning (DL)-assisted framework for simultaneous damage localization and severity assessment in composite structures using Lamb waves (LWs). Previous studies have often focused on either damage detection or localization in composite structures. In contrast, this study aims to perform damage detection, severity assessment, and localization using independent DL models. Three DL models, namely the artificial neural network (ANN), convolutional neural network (CNN), and gated recurrent unit (GRU), are compared. To assess their damage detection and localization capabilities. Moreover, zero-mean Gaussian noise is introduced as a data augmentation technique to address the variability and noise inherent in LW signals, improving the generalization capability of the DL models. The proposed framework is validated on a composite plate with four piezoelectric transducers, one at each corner, and achieves high accuracy in both damage localization and severity assessment, offering an effective solution for real-time structural health monitoring. This dual-function approach provides a scalable data-driven method to evaluate composite structures, with applications in predictive maintenance and reliability assurance in critical engineering systems.

An enhanced Lo–Christensen–Wu (LCW) theory is defined in the Laplace domain to predict the thermo-mechanical-viscoelastic behavior of long-term composite structures. The primary objective herein is to systematically extract the computational benefits of the conventional LCW and fifth-order zigzag model via the mixed variational theorem (MVT). Furthermore, the Laplace transform is employed to circumvent the numerical complexity of viscoelastic analysis. The relationships between the two fields were derived using the MVT constraint equations in the Laplace domain. Consequently, the proposed theory has the C⁰-based computational benefits as the conventional LCW, while improving the solution accuracy for long-term thermo-mechanical-viscoelastic behaviors.

This paper proposes a simple yet accurate finite element (FE) formulation for the thermomechanical analysis of laminated composites and sandwich plates. To this end, an enhanced first-order shear deformation theory including the transverse normal effect based on the mixed variational theorem (EFSDTM_TN) was employed in the FE implementation. The primary objective of the FE formulation was to systematically interconnect the displacement and transverse stress fields using the mixed variational theorem (MVT). In the MVT, the transverse stress field is derived from the efficient higher-order plate theory including the transverse normal effect (EHOPT_TN), to enhance the solution accuracy, whereas the displacement field is defined by the first-order shear deformation theory including the transverse normal effect (FSDT_TN), to amplify the numerical efficiency. Furthermore, the transverse displacement field is modified by incorporating the components of the external temperature loading, enabling the consideration of the transverse normal strain effect without introducing additional unknown variables. Based on the predefined relationships, the proposed FE formulation can extract the C0-based computational benefits of FSDT_TN, while improving the solution accuracy for thermomechanical analysis. The numerical performance of the proposed FE formulation was demonstrated by comparing the obtained solutions with those available in the literature, including 3-D exact solutions.