摘要
提出了基于单项模型可筛选的船舶横摇运动组合预测方法.运用协整理论方法和非负约束的冗余方法对模型进行筛选,将筛选出的单项模型进行组合,并将其用于对我国某型船舶横浪航行情况的预测.预测结果表明,在预测精度及预测时长方面均好于各单项模型和未经过单项模型筛选的组合预测模型,从而验证了所提出方法的有效性和可行性.
The combination prediction of ship rolling motion is proposed based on single model screening. Single model is selected by using co-integration theory and redundant method based on non-negative constraints, and the combination model is established by using the screened single models. The combination model is used to predict the situation of one certain type of ship sailing in the beam sea condition. Simulation results show that the model used in contrast to single model and combination model of single model non-screening can quickly and accurately predict the time series of ship rolling, and also show the feasibility and effectiveness of the proposed.
出处
《控制与决策》
EI
CSCD
北大核心
2014年第7期1306-1310,共5页
Control and Decision
基金
国家高技术研究发展计划项目(2008AA01Z148)
黑龙江省教育厅科学技术研究项目(12531528)
关键词
船舶横摇运动
组合预测
模型筛选
时间序列预测
神经网络
ship rolling motion
combination prediction
model screening
time series prediction
neural network