混沌理论和神经网络相结合的舰船摇荡运动极短期预报  

Extreme short term prediction of ship swaying motions based on combination of chaos and neural network

作　　者：侯建军[1] 东昉[1] 蔡烽[2] 

机构地区：[1]大连海事大学航海学院,辽宁大连116026 [2]海军大连舰艇学院航海系,辽宁大连116018

出　　处：《舰船科学技术》2008年第1期67-70,共4页Ship Science and Technology

摘　　要：舰船摇荡运动具有混沌特性,因而可以应用混沌理论对其进行预报。介绍了混沌时间序列预测原理;建立了基于混沌理论相空间重构技术的RBF神经网络模型,并将其用于舰船摇荡运动预报;通过对某实船纵摇时历的预报计算,证明了采用混沌和神经网络相结合的预报方法,能有效提高预报精度和延长预报时长。Ship swaying motion can be predicted by the chaos theory due to its chaotic characteristic. So,the prediction principle of chaotic time series is introduced in this paper. The RBF neural network is presented based on phase-space reconstruction of chaos theory and is used to ship swaying motions＇ prediction. Prediction results on a ship＇s pitch time series show that the method based on combination of chaos and neural network can improve the prediction precision and extend the prediction term.

关 键 词：耐波性 混沌 神经网络 船舶运动 极短期预报 

分 类 号：U661.32[交通运输工程—船舶及航道工程]