A novel framework for rapid short-term prediction of ship motions using an enhanced gradient boosting decision tree with dynamical evolution sequence
Abstract Accurate short-term prediction of ship motions is essential for selecting operational areas and time windows, which are critical for maritime safety and operational efficiency. Traditional physics-based methods provide high accuracy but are computationally expensive, limiting their use in onboard applications. To address this challenge, this study proposes a rapid short-term prediction method for ship motions. The method utilizes a dynamical evolution sequence (DES) to generate a more uniform sample set, replacing the conventional Latin hypercube sampling (LHS) in the gradient boosting decision tree (GBDT), thus enhancing model accuracy through improved input sampling. First, four test functions are used to validate and compare the original and improved GBDT models. Results show that the DES-based GBDT model consistently outperforms the traditional LHS-based GBDT model across all functions. Based on this, the enhanced model is used to develop a comprehensive set of surrogate models for all hydrodynamic coefficients required for six-degree-of-freedom (6-DOF) motion prediction, including added mass, radiation damping, and wave excitation force, comprising 84 submodels in total. This innovation reduces computation time from hours to approximately 10 s per operating condition. The feasibility of the proposed method is validated under two loading conditions for an offshore support vessel, with prediction results compared to those obtained from the commercial software Hydrostar. The validation demonstrates that the 6-DOF motion amplitudes predicted by the proposed method align closely with those from the commercial software, achieving both rapid and accurate predictions. This method provides a viable alternative for rapid short-term ship motion prediction in engineering practice.
Authors
- Kang Zou (ORCID: https://orcid.org/0000-0002-9916-8377)
- Hao Li
- Manhai Gui
- Li Zhu
- Feng Wu
Publication Details
- Journal
- Intelligent Marine Technology and Systems
- Published
- 2026-11-16
- DOI
- https://doi.org/10.1007/s44295-026-00119-1
- Primary Topic
- Ship Hydrodynamics and Maneuverability
- Type
- article
- Field-Weighted Citation Impact
- 0.00