Bridge Deformation Prediction with BGCO-PIC-DA-LSTM Based on Prior-Informed Multi-Source Fusion and Dual-Stream Residual Attention
Open Access
- 11 March 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (6) , 2681
Abstract
Accurate deflection prediction is vital for structural health monitoring of large-span bridges yet remains challenging due to complex nonlinear environmental couplings. This paper proposes a hybrid deep learning framework, BGCO-PIC-DA-LSTM, for precise bridge deflection prediction. First, a Prior-Informed Correlation (PIC) strategy incorporating temperature lag terms is introduced to enhance the statistical consistency of input features. Second, a dual-stream residual Bi-LSTM network integrating adaptive temporal attention is developed to simultaneously capture long-term evolutionary trends and instantaneous dynamic fluctuations. Furthermore, a Bayesian-Gradient Cooperative Optimization (BGCO) strategy is employed to automatically configure optimal hyperparameters. Validation using in situ data from a large-span cable-stayed bridge demonstrates that the proposed method significantly outperforms baseline algorithms in prediction accuracy and robustness. Additionally, the prediction residuals exhibit characteristics approximating zero-mean Gaussian white noise, establishing a reference baseline for structural state evolution and providing a certain basis for identifying potential performance shifts.Keywords
Funding Information
- National Natural Science Foundation of China (51778343)
- Yichang Bridge Group (SDHZ20240183)
This publication has 41 references indexed in Scilit:
- Bridge deformation quantiles prediction with MVO-CNN-BiLSTM based on mixed attention mechanism and periodic multi-source information fusionJournal of Civil Structural Health Monitoring, 2024
- Deep learning-based structural health monitoringAutomation in Construction, 2024
- Benchmarking physics-informed frameworks for data-driven hyperelasticityComputational Mechanics, 2023
- Prediction method of pipe joint opening-closing deformation of immersed tunnel based on singular spectrum analysis and SSA-SVRApplied Ocean Research, 2023
- Satellite-based interferometry for monitoring structural deformations of bridge portfoliosAutomation in Construction, 2022
- Attention-based LSTM (AttLSTM) neural network for Seismic Response Modeling of BridgesComputers & Structures, 2022
- Modelling and forecasting of SHM strain measurement for a large-scale suspension bridge during typhoon events using variational heteroscedastic Gaussian processEngineering Structures, 2022
- Physics-Informed Machine Learning for Structural Health Monitoring2021
- Nonlinear FE model updating and reconstruction of the response of an instrumented seismic isolated bridge to the 2010 Maule Chile earthquakeEarthquake Engineering & Structural Dynamics, 2017
- Multi-Verse Optimizer: a nature-inspired algorithm for global optimizationNeural Computing and Applications, 2015