A Physics-Constrained Hybrid Deep Learning Model for State Prediction in Shipboard Power Systems
Modelling · 26.03.2026 · 7 (2) · 65
DOI: 10.3390/modelling7020065 ↗Kurz gefasst
Fachartikel in der Zeitschrift Modelling, online erschienen am 26.03.2026. Verfasst von Jiahao Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang Provincial Science and Technology Plan Project.
Abstract (Originalsprache)
Accurate and physically consistent state prediction is essential for shipboard power systems (SPS) operating under dynamic conditions. However, purely data-driven models often exhibit degraded robustness and physically inconsistent outputs when exposed to transient disturbances or limited data coverage. To address these limitations, this paper proposes a physics-constrained hybrid prediction model that integrates a convolutional neural network–bidirectional long short-term memory (CNN–BiLSTM) architecture with wide residual connections (WRC) and a physics-constrained loss (PCL). The proposed modeling approach combines real operational measurement data with high-resolution simulation data to enhance data diversity and improve generalization capability. The CNN–BiLSTM structure captures nonlinear temporal dependencies, while the WRC preserves critical low-level transient electrical features during deep temporal modeling. In addition, multiple physical constraints, including power balance, voltage conversion relationships, and battery state-of-charge (SOC) dynamics, are incorporated into the training process to enforce physically consistent predictions. The model is validated using charging and discharging experiments on a laboratory-scale SPS under both steady-state and transient conditions. Comparative results demonstrate that the proposed approach achieves higher prediction accuracy, improved dynamic stability, and faster recovery following disturbances compared with conventional data-driven models. These results indicate that physics-constrained deep learning provides an effective and interpretable modeling framework for SPS state prediction, supporting digital twin-oriented monitoring and real-time prediction applications.
Förderung
- Zhejiang Provincial Science and Technology Plan Project
Zitieren
APA
Wang, J., Dai, X., Zhang, M., You, K., & Liu, J. (2026). A Physics-Constrained Hybrid Deep Learning Model for State Prediction in Shipboard Power Systems. Modelling, 7(2), 65. https://doi.org/10.3390/modelling7020065
Vancouver
Wang J, Dai X, Zhang M, You K, Liu J. A Physics-Constrained Hybrid Deep Learning Model for State Prediction in Shipboard Power Systems. Modelling. 2026;7(2):65. doi:10.3390/modelling7020065
BibTeX
@article{Wang2026,
author = {Wang, Jiahao and Dai, Xiaoqiang and Zhang, Mingyu and You, Kaikai and Liu, Jinxing},
title = {A Physics-Constrained Hybrid Deep Learning Model for State Prediction in Shipboard Power Systems},
journal = {Modelling},
year = {2026},
volume = {7},
number = {2},
pages = {65},
doi = {10.3390/modelling7020065}
}
EUVIMED