View in EDS

Artificial Intelligence for Dynamic Characterization of Composite Panel Structures: A Structured Review.

Saved in:
Bibliographic Details
Title: Artificial Intelligence for Dynamic Characterization of Composite Panel Structures: A Structured Review.
Authors: Sarfarazi, Sina1 (AUTHOR) Sina.sarfarazi@unina.it, Modano, Mariano1 (AUTHOR), Fulgione, Marcello1 (AUTHOR)
Source: Mechanics Research Communications. Feb2026, Vol. 151, pN.PAG-N.PAG. 1p.
Subjects: Artificial intelligence, Composite structures, Modular construction, Mathematical optimization, Dynamic models, Reduced-order models
Abstract: Dynamic characterisation of composite panels in modular construction requires approaches that can capture scale effects, variability in manufacturing, and uncertain restraints. To investigate how artificial intelligence (AI) contributes in this field, we compiled a dataset of 2,085 papers from Scopus (2001–2025) and classified them into five methodological families: surrogate models, sequence learning, physics-informed neural networks (PINNs), inverse and optimisation approaches, and explainable AI (XAI). The dataset shows strong growth after 2016. Inverse and metaheuristic optimisation are the most common, especially for laminate lay-up, core design, and finite-element (FE) model updating. Surrogate models are widely used to emulate FE runs and accelerate calibration. Sequence models and PINNs remain smaller but are expanding, supporting time-history prediction and physics-consistent parameter identification under sparse data. XAI is the least developed area and is mostly used for feature attribution in optimisation or health monitoring tasks. In addition to classification, the review presents a clear framework hat connects each method to specific dynamic tasks and provides an interactive web-based GUI where readers can filter, inspect, and export the screened corpus. This combination of systematic mapping and open access to the database creates a transparent reference point for further studies and supports the development of reliable and scalable dynamic analysis frameworks for modular composite panels. [ABSTRACT FROM AUTHOR]
Copyright of Mechanics Research Communications is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Dynamic characterisation of composite panels in modular construction requires approaches that can capture scale effects, variability in manufacturing, and uncertain restraints. To investigate how artificial intelligence (AI) contributes in this field, we compiled a dataset of 2,085 papers from Scopus (2001–2025) and classified them into five methodological families: surrogate models, sequence learning, physics-informed neural networks (PINNs), inverse and optimisation approaches, and explainable AI (XAI). The dataset shows strong growth after 2016. Inverse and metaheuristic optimisation are the most common, especially for laminate lay-up, core design, and finite-element (FE) model updating. Surrogate models are widely used to emulate FE runs and accelerate calibration. Sequence models and PINNs remain smaller but are expanding, supporting time-history prediction and physics-consistent parameter identification under sparse data. XAI is the least developed area and is mostly used for feature attribution in optimisation or health monitoring tasks. In addition to classification, the review presents a clear framework hat connects each method to specific dynamic tasks and provides an interactive web-based GUI where readers can filter, inspect, and export the screened corpus. This combination of systematic mapping and open access to the database creates a transparent reference point for further studies and supports the development of reliable and scalable dynamic analysis frameworks for modular composite panels. [ABSTRACT FROM AUTHOR]
ISSN:00936413
DOI:10.1016/j.mechrescom.2025.104607