摘要
针对MOSES软件对导管架滑移下水进行数值模拟所需时间较长、修改工况参数较为繁琐的问题,提出了一种基于径向基(RBF)神经网络和反向传播(BP)神经网络的导管架滑移下水快速预报模型。以南海珠江口盆地某导管架滑移下水实例为研究对象,构建了不同工况下导管架滑移下水终止时刻数据集和驳船与导管架重心六自由度运动量数据集。在两类数据集基础上分别建立了RBF神经网络和BP神经网络。将两类神经网络进行结合得到导管架滑移下水快速预报模型。选择典型工况对导管架滑移下水快速预报模型准确性进行验证。结果表明,该模型不仅在数据集范围内预报效果较好,在数据集外一定范围内仍能对导管架滑移下水终止时刻和姿态进行有效预报。
Addressing the challenges of prolonged numerical simulation time and complex parameter adjustments in the MOSES software for jacket launching,this study proposes a rapid prediction model for jacket launching based on radial basis function(RBF)neural networks and back propagation(BP)neural networks.Using a jacket launching case study in the Pearl River Mouth Basin of the South China Sea,datasets were constructed for the termination time of jacket launching and the six degrees of freedom(6-DOF)motion data of the barge and the jacket's center of gravity under various conditions.RBF and BP neural networks were respectively established based on these datasets.By combining the two neural networks,a rapid prediction model for jacket launching was developed.The accuracy of the model was validated under typical conditions,and the results show that the model performs well not only within the range of the datasets but also in predicting the termination time and attitude of the jacket launching beyond the dataset range.
作者
刘延昆
白旭
魏佳广
昝英飞
LIU Yankun;BAI Xu;WEI Jiaguang;ZAN Yingfei(School of Naval Architecture&Ocean Engineering,Jiangsu University of Science and Technology,Zhenjiang 212100,China;Offshore Oil Engineering Co.,Ltd.,Tianjin 300461,China;College of Shipbuilding Engineering,Harbin Engineering University,Harbin 150001,China)
出处
《海洋工程》
北大核心
2025年第1期139-148,共10页
The Ocean Engineering
基金
国家自然科学基金面上项目(42276225)。
关键词
导管架滑移下水
神经网络
快速预报
数据集
六自由度运动量
jacket launching
neural networks
rapid prediction
datasets
six degrees of freedom motion quantities
