基于BP神经网络的港内系泊船舶运动量预测方法  

Methods for predicting motion of mooring ships in port based on BP neural network

作　　者：耿宝磊[1] 孙潍 范一帆 沈文君 GENG Bao-lei;SUN Wei;FAN Yi-fan;SHEN Wen-jun(Tianjin Research Institute for Water Transport Engineering,M.O.T.,Tianjin 300456,China;Zhejiang Zhejiao Testing Technology Co.,Ltd.,Hangzhou,Zhejiang 310000,China;School of Marine Engineering Equipment,Zhejiang Ocean University,Zhoushan,Zhejiang 316022,China)

机构地区：[1]交通运输部天津水运工程科学研究所,天津300456 [2]浙江浙交检测技术有限公司,浙江杭州310000 [3]浙江海洋大学海洋工程装备学院,浙江舟山316022

出　　处：《中国港湾建设》2023年第6期29-35,共7页China Harbour Engineering

基　　金：国家自然科学基金联合基金项目(U2106223);温州鹿城区科技研究开发专项(G21011);中央级科研院所基本科研业务费资助项目(TKS20210108)。

摘　　要：针对港内系泊船舶不同系泊状态,利用水动力分析软件和时域分析方法进行数值建模,以26.6万m^(3)LNG船为例,构建了该船舶六自由度运动量的数据库。研究进一步基于BP神经网络方法搭建了港内系泊船舶运动量预测模型,该模型设计中隐含层节点数为26,输入层神经元数量为12,输出层神经元数量为6,学习率为0.0001,将训练结果和基础数据库进行了对比验证,结果表明预测结果与训练样本库、检验样本库的对比结果符合良好。文中以模型检验样本库为依据,将预测模型结果与物理模型试验数据进行了对比,验证了该方法的适用性,为快速预报港内系泊船舶运动提供了新思路。A numerical model is built using hydrodynamic analysis software and time domain analysis method according to the different mooring conditions of moored ships in port.Taking a 266000 m^(3) LNG ship as an example,a database of the ship's six degrees of freedom motion is built.Based on the BP neural network,a prediction model for the movement of moored ships in the harbor is established.In the model design,the number of hidden layer nodes is 26,the number of input layer neurons is 12,the number of output layer neurons is 6,and the learning rate is 0.0001.The training results are compared with the basic database,and the results show that the prediction results are in good agreement with the comparison results of the training sample database and the test sample database.Finally,based on the model test database,the prediction model results are compared with the test data of the physical model and the applicability of the method is verified,which provides a new idea for rapid prediction of the motions of moored ships in port.

关 键 词：BP神经网络 船舶运动量 预测模型 训练样本库 

分 类 号：U661.3[交通运输工程—船舶及航道工程]