摘要
船舶在航行的过程中,受到波浪的影响,会产生复杂的运动,这个运动具有随机性和非线性的特点。为保证船舶航行的安全性,要对摇荡运动实时、准确预测,尤其是横摇运动。这是因为横摇的幅度过大,极有可能引起翻船的情况发生,所以预测船舶的横摇运动显得尤为必要。为提高预测结果的准确性,可以基于DRNN神经网络构建预测模型。在模型的建立中,选用单项模型组合的方式,提高预报精度、增加预报时长,使船舶保持安全、稳定航行。
In the process of sailing,a ship is affected by waves and will produce complex motion.This motion has the characteristics of randomness and nonlinearity.To ensure the safety of ship navigation,it is necessary to predict the swaying motion in real time and accurately,especially Rolling motion.This is because the rolling amplitude is too large,which is very likely to cause the ship to capsize,so it is particularly necessary to predict the rolling motion of the ship.In order to improve the accuracy of the prediction results,a prediction model can be constructed based on the DRNN neural network.In the establishment of the model,a combination of single models is selected to improve the prediction accuracy and increase the prediction duration,so that the ship can maintain safe and stable navigation.
作者
李子梅
姜亦学
LI Zi-mei;JIANG Yi-xue(School of Computer Technology and Engineering,Changchun Institute of Technology,Changchun 130012,China)
出处
《舰船科学技术》
北大核心
2021年第16期19-21,共3页
Ship Science and Technology
基金
构建预测模型研究(120200047)
