Virtual Modelling Framework-Based Inverse Study for the Mechanical Metamaterials with Material Nonlinearity

Modelling—International Open Access Journal of Modelling in Engineering Science, Год журнала: 2025, Номер 6(1), С. 24 - 24

Опубликована: Март 20, 2025

Mechanical metamaterials have become a critical research focus across various engineering fields. Recent advancements pushed the development of reprogrammable mechanical to achieve adaptive behaviours against external stimuli. The relevant designs strongly depend on thorough understanding response spectrum original structure, where establishing an accurate virtual model is regarded as most efficient approach this end up now. By employing extended support vector regression (X-SVR), powerful machine learning algorithm model, study explores uncertainty and sensitivity analysis inverse re-entrant honeycombs under quasi-static compressive loads. proposed framework enables quantification, analysis, study, facilitating related design optimisation metastructures when responsive materials. considered effective tool for quantification enabling identification key parameters affecting performance. Finally, leverages X-SVR swiftly obtain required structural configurations based targeted responses.

Язык: Английский

Physics-Informed Neural Networks for the Structural Analysis and Monitoring of Railway Bridges: A Systematic Review

Mathematics, Год журнала: 2025, Номер 13(10), С. 1571 - 1571

Опубликована: Май 10, 2025

Physics-informed neural networks (PINNs) offer a mesh-free approach to solving partial differential equations (PDEs) with embedded physical constraints. Although PINNs have gained traction in various engineering fields, their adoption for railway bridge analysis remains under-explored. To address this gap, systematic review was conducted across Scopus and Web of Science (2020–2025), filtering records by relevance, journal impact, language. From an initial pool, 120 articles were selected categorised into nine thematic clusters that encompass computational frameworks, hybrid integration conventional solvers, domain decomposition strategies. Through natural language processing (NLP) trend mapping, evidences growing but fragmented research landscape. demonstrate promising capabilities load distribution modelling, structural health monitoring, failure prediction, particularly under dynamic train loads on multi-span bridges. However, methodological gaps persist large-scale simulations, plasticity experimental validation. Future work should focus scalable PINN architectures, refined modelling inelastic behaviours, real-time data assimilation, ensuring robustness generalisability through interdisciplinary collaboration.

Язык: Английский

Physics-Informed Neural Networks for Unmanned Aerial Vehicle System Estimation

Drones, Год журнала: 2024, Номер 8(12), С. 716 - 716

Опубликована: Ноя. 29, 2024

The dynamic nature of quadrotor flight introduces significant uncertainty in system parameters, such as thrust and drag factors. Consequently, operators grapple with escalating challenges implementing real-time control actions. This study presents an approach for estimating the model Unmanned Aerial Vehicles based on Physics-Informed Neural Networks (PINNs), which is paramount importance due to presence uncertain data since actions are required very short computation times. In this regard, by including physical laws into neural networks, PINNs offer potential tackle several issues, heightened non-linearities low-inertia systems, elevated measurement noise, constraints availability or uncertainties, while ensuring robustness solution, thus effective results time, once network training has been performed without need be retrained. effectiveness proposed method showcased a simulation environment real juxtaposed state-of-the-art technique, Extended Kalman Filter (EKF). show that estimator outperforms EKF both terms efficacy solution time.

Язык: Английский