The invention provides a real sea condition strong adaptation-based ship future motion attitude prediction method and system, and the method comprises the steps: carrying out the iterative training of an initial prediction model through the real-time data, obtained at different moments, of a real ship, and obtaining a real-time prediction model; the initial prediction model is obtained by training historical motion data of a ship; the real-time data of the real ship obtained at the current moment are input into the real-time prediction model for prediction, and the real-time motion prediction data of the real ship are obtained. The real-time data of the real ship obtained through continuous updating serve as training data to continuously train and optimize the model, so that the model can realize self-updating, the strong adaptability of the model to the real sea condition is realized, and the real-time motion prediction data of the real ship are obtained. The problem that prediction errors are caused due to the fact that prediction model parameters cannot adapt to the instantly changing sea wave environment in the prior art is solved.
本发明提供了一种基于真实海况强适应的船舶未来运动姿态预测方法及系统,方法包括:利用不同时刻获取到的实船实时数据对初始预测模型进行迭代训练,得到实时预测模型;所述初始预测模型是由船舶历史运动数据进行训练得到;将当前时刻获取到的实船实时数据输入至所述实时预测模型中进行预测,得到实船运动预测数据本发明不断更新得到的实船实时数据作为训练数据不断对模型进行训练优化,使模型能够实现自我更新,实现模型对真实海况的强适应性,解决了现有技术中预测模型参数无法适应瞬息万变的海浪环境所带来的预测误差。
Strong-adaptability ship future motion attitude prediction method and system based on real sea conditions
基于真实海况强适应的船舶未来运动姿态预测方法及系统
2023-11-14
Patent
Electronic Resource
Chinese
Ship motion attitude prediction method based on multiple combinations
European Patent Office | 2023
|Ship rolling motion attitude control system based on multiple learning algorithms
European Patent Office | 2020
|European Patent Office | 2022
|