华中科技大学学报（自然科学版）2024，Vol.52Issue(4)：1-7,7.DOI:10.13245/j.hust.240700
基于耦合特征LSTM的船舶运动预报方法研究
Research on ship motion prediction method based on coupled feature LSTM
摘要
Abstract
Long short-term memory(LSTM)neural network model was used to predict the motion of ship advancing in waves under different sea states.Aiming at the characteristic that LSTM model was difficult to optimize,a coupled feature LSTM neural network model was proposed.First,the ship motion time series data were normalized.Then,the LSTM model with input layer,hidden layer and output layer was built based on the deep learning framework TensorFlow,and the original data were divided according to different features.Finally,LSTM models with different coupling features were used to predict the tested samples.Results show that the six-feature coupled LSTM neural network model has obvious advantages compared with other LSTM models for the prediction accuracy.The motion prediction error is decreased by 2.1%～12.9%in the level-4 sea state.In the level-5 sea state,the motion prediction error is decreased by 2.4%～12.3%.The six-feature coupled LSTM model can simultaneously output six degrees of freedom(six-DOF)motion with only one calculation,which can reduce the calculation time by 51.4%～82.7%and improve the calculation efficiency.关键词
六自由度运动/长短期记忆(LSTM)/时间序列/耦合特征/预报精度Key words
six degrees of freedom(six-DOF)motion/long short-term memory(LSTM)/time series/coupling features/prediction accuracy分类
交通工程引用本文复制引用
何国联,姚朝帮,孙小帅,孟凡亮..基于耦合特征LSTM的船舶运动预报方法研究[J].华中科技大学学报（自然科学版）,2024,52(4):1-7,7.基金项目
国家自然科学基金资助项目(52071148) （52071148）
工信部民机专项资助项目(2022KF0031). （2022KF0031）
