Transferable and adaptable full-field structural response reconstruction from sparse sensors via GraphSAGE–LSTM neural networks
Authors:
- Keyu LaiKLKeyu Lai
- Xiaoyou WangXWXiaoyou Wang
- Yixian LiYLYixian Li
- Hong GuanHGHong Guan
- Yiming ZhangYZYiming Zhang
- Yong XiaYXYong Xia
- 8 April 2026
- journal article
- Published by Elsevier in Engineering Structures
- Vol. 359
Abstract
No abstract availableFunding Information
- Hong Kong Polytechnic University (P0049604)
This publication has 38 references indexed in Scilit:
- EKF–SINDy: Empowering the extended Kalman filter with sparse identification of nonlinear dynamicsComputer Methods in Applied Mechanics and Engineering, 2024
- Finite element model updating based on response reconstruction using a modified Kalman filterJournal of Mechanical Science and Technology, 2023
- A structural response reconstruction method based on a continuous-discrete state space modelJournal of Mechanical Science and Technology, 2023
- Multi‐channel response reconstruction using transformer based generative adversarial networkEarthquake Engineering & Structural Dynamics, 2023
- Structural dynamic response reconstruction using self-attention enhanced generative adversarial networksEngineering Structures, 2022
- Sensor placement and seismic response reconstruction for structural health monitoring using a deep neural networkBulletin of Earthquake Engineering, 2022
- Unsupervised learning-based damage assessment of full-scale civil structures under long-term and short-term monitoringEngineering Structures, 2022
- Permutation entropy-based 2D feature extraction for bearing fault diagnosisNonlinear Dynamics, 2020
- Physics-informed multi-LSTM networks for metamodeling of nonlinear structuresComputer Methods in Applied Mechanics and Engineering, 2020
- Structural response reconstruction in physical coordinate from deficient measurementsEngineering Structures, 2020