摘要
实时准确地预报船舶横摇运动是目前船舶运动研究的一个重要课题,对于提高船舶的耐波性和适航性具有重要的意义.灰色GM(2,1)模型有2个指数分量,能反映出序列摆动的运动情况,但预测精度仍然不足.因此在GM(2,1)模型对非线性复杂横摇运动进行建模及预测的基础上,基于误差补偿的思想,用周期外延和神经网络2种方法分别对灰色模型进行改进.仿真结果表明,灰色-周期外延组合预测模型和灰色-BP神经网络组合预测模型均能准确有效地预报船舶横摇运动,进一步提高灰色模型的预测精度,为船舶减摇控制打下了良好基础,具有实用价值.
The study on forecasting rolling motion accurately is an important issue in shipping area.It is of great significance to enhance the ship′s seakeeping capacity and seaworthiness.Though GM（2,1） can model swing series,the accuracy is not high enough.In this paper,two improved model are proposed based on modeling and predicting on non-linear rolling motion by GM（2,1）.The two combined model are gray cycle extension and gray neural network respectively based on error compensation.The simulation results illustrate both two methods can forecast rolling motion efficiently,and have higher accuracy,which lay good foundation for ship rolling stabilization.
出处
《厦门大学学报（自然科学版）》
CAS
CSCD
北大核心
2011年第3期515-519,共5页
Journal of Xiamen University：Natural Science
基金
厦门大学985二期信息创新平台项目(0000-x07204)
