EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accurate time-series forecasting of floating platform motion via a reinforced fusion CNN–BiLSTM–attention model

Huiyuan Zheng, Shicheng Wang, Shihua Li, Kuan Lu iD, Xin Wang, Yuzheng Liu, Xiao Wu

PLOS One · 02.02.2026 · 21 (2) · e0342081

DOI: 10.1371/journal.pone.0342081 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 02.02.2026. Verfasst von Huiyuan Zheng und 6 weiteren Autor:innen. Beteiligte Einrichtung: National Ocean Technology Center, Tianjin, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Models, Theoretical. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate motion prediction of floating platforms is critical for ensuring operational safety in offshore engineering applications or marine equipment testing. However, the strong nonlinearity and non-stationary characteristics induced by complex marine environments pose significant challenges to conventional prediction models. This study proposes a reinforced hybrid neural network (CNN-BiLSTM-Attention) integrated with advanced signal processing techniques to address these challenges. The methodology combines complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) for multi-scale signal analysis, coupled with temporal feature engineering through sliding window optimization. And the architecture innovatively integrates convolutional neural networks for spatial pattern extraction, bidirectional long short-term memory networks for temporal dependency modeling, and attention mechanisms for dynamic feature weighting. By analyzing datasets generated via hydrodynamic simulations, this study elucidates the model’s physical interpretability and establishes a closed-loop validation framework between data-driven methods and physics-based models. Finally, the predictive performance of the model is evaluated using motion datasets of the proportional platform in the water pool test under different working conditions, demonstrating its broad applicability and transferability by assessed using a dual-stage EWMA control line. Overall, the proposed CNN-BiLSTM-Attention model and its data-physics integrated validation method provide a reliable, interpretable and transferable solution for floating platform motion prediction, which can break through the limitations of single analysis methods, and provide a new research idea for integrating data-driven and physics-based methods in the field of ocean engineering.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerModels, TheoreticalConvolutional Neural NetworksLong Short Term MemoryForecastingPrediction AlgorithmsMotionHydrodynamicsSignal Processing, Computer-Assisted

Autor:innen und Institutionen

  • National Ocean Technology Center, Tianjin, China.
  • The Key Laboratory of Ocean Observation Technology of the Ministry of Natural Resources, Tianjin, China.

ORCID-Profile: Kuan Lu

Förderung

  • the National Key R&D Program of China

Zitieren

APA

Zheng, H., Wang, S., Li, S., Lu, K., Wang, X., Liu, Y., & Wu, X. (2026). Accurate time-series forecasting of floating platform motion via a reinforced fusion CNN–BiLSTM–attention model. PLOS One, 21(2), e0342081. https://doi.org/10.1371/journal.pone.0342081

Vancouver

Zheng H, Wang S, Li S, Lu K, Wang X, Liu Y, et al. Accurate time-series forecasting of floating platform motion via a reinforced fusion CNN–BiLSTM–attention model. PLOS One. 2026;21(2):e0342081. doi:10.1371/journal.pone.0342081

BibTeX
@article{Zheng2026,
  author = {Zheng, Huiyuan and Wang, Shicheng and Li, Shihua and Lu, Kuan and Wang, Xin and Liu, Yuzheng and Wu, Xiao},
  title = {Accurate time-series forecasting of floating platform motion via a reinforced fusion CNN–BiLSTM–attention model},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {2},
  pages = {e0342081},
  doi = {10.1371/journal.pone.0342081}
}
Kostenlos starten →