A Novel CNN-LSTM Algorithm for Strain Time Series Prediction of Orthotropic Steel Bridge Decks
Sensors · 10.07.2026 · 26 (14) · 4399
DOI: 10.3390/s26144399 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.07.2026. Verfasst von Haiping Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Civil Engineering, Hunan University of Technology, Zhuzhou 412007, China. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Education Department of Hunan Province.
Abstract (Originalsprache)
Accurately predicting the strain time series of orthotropic steel bridge decks (OSBDs) is highly challenging due to their strong stochasticity and nonlinear characteristics. This paper proposes a hybrid prediction framework integrating wavelet decomposition with a cascaded Convolutional Neural Network and Long Short-Term Memory architecture. Initially, the raw strain signals are decoupled into temperature-dominated low-frequency trends and vehicle-induced high-frequency dynamic components using the 6-level Daubechies 10 wavelet transform. Subsequently, a deep architecture comprising three CNN layers and two LSTM layers is constructed to precisely extract and learn the local spatial features and long-term temporal dependencies of the decoupled signals. Based on real-world monitoring data, the proposed model is comparatively evaluated against baseline models, including CNN-GRU, LSTM, and Gated Recurrent Unit (GRU), across three time horizons: 24 h, 1 h, and 10 min. The results demonstrate that the proposed method consistently exhibits superior predictive performance across multiple scales. Specifically, the mean absolute percentage error (MAPE) is strictly maintained below 0.6% across all tested horizons, with an R2 reaching 0.961. Furthermore, the single-step inference latency is merely 0.63 milliseconds, which is significantly lower than conventional sensor acquisition intervals. This decouple-then-predict analytical framework effectively avoids the feature interference typically encountered when a single network directly processes complex mixed signals. Moreover, while strictly satisfying real-time computational constraints, it provides an undistorted, high-fidelity data foundation for future online fatigue evaluations and continuous state tracking of bridge structures.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Civil Engineering, Hunan University of Technology, Zhuzhou 412007, China.
ORCID-Profile: Miao Meng
Förderung
- Education Department of Hunan Province
Zitieren
APA
Zhang, H., Meng, M., & Zhao, L. (2026). A Novel CNN-LSTM Algorithm for Strain Time Series Prediction of Orthotropic Steel Bridge Decks. Sensors, 26(14), 4399. https://doi.org/10.3390/s26144399
Vancouver
Zhang H, Meng M, Zhao L. A Novel CNN-LSTM Algorithm for Strain Time Series Prediction of Orthotropic Steel Bridge Decks. Sensors. 2026;26(14):4399. doi:10.3390/s26144399
BibTeX
@article{Zhang2026,
author = {Zhang, Haiping and Meng, Miao and Zhao, Lei},
title = {A Novel CNN-LSTM Algorithm for Strain Time Series Prediction of Orthotropic Steel Bridge Decks},
journal = {Sensors},
year = {2026},
volume = {26},
number = {14},
pages = {4399},
doi = {10.3390/s26144399}
}
EUVIMED