CORC  > 厦门大学  > 信息技术-已发表论文
Nonlinear Ship Motion Prediction Via a Novel High Precision RBF Neural Network
Jiehua, Zhou ; Xiafu, Peng ; Lisang, Liu ; Dongwei, He ; Peng XF(彭侠夫)
刊名http://dx.doi.org/10.4156/AISS.vol3.issue10.6
2011
关键词Forecasting Fuzzy clustering Radial basis function networks Ships Time series
英文摘要The ship swing motion has strong nonlinear and stochastic characteristics, so the ship swing motion prediction is very difficult. The paper designed a novel high precision RBF (radial basis function) neural network to predict the ship swing motion. In order to optimize the neural network structure, it used the embed dimension of time series to determine the number of input node and fuzzy clustering method to determine the initial number of hidden node for RBF neural network at first. Then it used the grey correlation analysis method to analyze the correlation degree between hidden node output and network output, and according to the size of correlation degree to delete the redundant hidden nodes. Meanwhile, in order to improve the prediction accuracy, it increased the direct connection between input layer and output layer in RBF neural network. Finally, the proposed model was tested with data from a real-world ship swing motion. Results show that the model maximum absolute error and mean squared error are respectively 0.2739 degree and 0.0110, so the proposed model is capable of prediction.
语种英语
出版者Advanced Institute of Convergence Information Technology
内容类型期刊论文
源URL[http://dspace.xmu.edu.cn/handle/2288/93014]  
专题信息技术-已发表论文
推荐引用方式
GB/T 7714
Jiehua, Zhou,Xiafu, Peng,Lisang, Liu,et al. Nonlinear Ship Motion Prediction Via a Novel High Precision RBF Neural Network[J]. http://dx.doi.org/10.4156/AISS.vol3.issue10.6,2011.
APA Jiehua, Zhou,Xiafu, Peng,Lisang, Liu,Dongwei, He,&彭侠夫.(2011).Nonlinear Ship Motion Prediction Via a Novel High Precision RBF Neural Network.http://dx.doi.org/10.4156/AISS.vol3.issue10.6.
MLA Jiehua, Zhou,et al."Nonlinear Ship Motion Prediction Via a Novel High Precision RBF Neural Network".http://dx.doi.org/10.4156/AISS.vol3.issue10.6 (2011).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace