基于主动学习方法的随机波场中双浮体极端响应超越概率  

Study on Exceeding Probability of Extreme Dynamic Response of Adjacent Floating Bodies under Random Waves by Using Active Learning Method

作　　者：刘义 沈佳诚 柏小东 张伟[1,2] Liu Yi;Shen Jiacheng;Bai Xiaodong;Zhang Wei(Marine Design and Research Institute of China,Shanghai 200011,China;Key Laboratory of Water Jet Propulsion Technology,Shanghai 20001,China;School of Civil and Hydraulic Engineering,Hefei University of Technology,Hefei 230006,China)

机构地区：[1]中国船舶及海洋工程设计研究院,上海200011 [2]喷水推进技术重点实验室,上海200011 [3]合肥工业大学土木与水利工程学院,合肥230006

出　　处：《水动力学研究与进展（A辑）》2024年第1期17-21,共5页Chinese Journal of Hydrodynamics

摘　　要：海上作业过程中,经常存在两个浮体相邻的情况。真实海洋环境中,伴随着随机波浪的影响,相邻浮体可能会产生耦合运动。尤其是在恶劣海况下,浮体的极端运动响应可能导致其倾覆,对海上作业产生严重危害。基于波群参数化和次序采样,结合计算流体力学(computational fluid dynamics,CFD)模拟,该文研究和分析了在不规则波浪中相邻浮体的横摇运动特性,并基于主动学习方法,采用少量样本有效地预测了浮体随机波浪的极端响应超越概率。此外,还研究了相邻浮体的距离比G/D对运动响应的影响,通过不同G/D下相邻浮体的时间超越概率进行预测和比较,找出了最优的相邻浮体距离,为实际工程应用提供了理论依据。During offshore operations, there is often a situation where two floating bodies are adjacent. In the real marine environment, coupled motion may occur between adjacent floating bodies due to the influence of random waves. Especially in rough sea conditions, the extreme motion response of floating bodies can lead to accidents such as capsizing, which can cause serious hazards to offshore operations. Based on the wave group parameterization and sequential sampling, combining computational fluid dynamics(CFD) numerical simulation, the rolling motion characteristics of adjacent floating bodies in irregular waves is investigated and analyzed in this paper. The extreme response exceedance probability of floating bodies in random waves is efficiently predicted using a small number of samples based on the active learning method. Additionally, the effect of the distance ratio(G/D) between adjacent floating bodies on their motion response is studied. By predicting and comparing the time exceedance probability of adjacent floating bodies under different G/D ratios, the optimal distance between adjacent floating bodies is identified, providing a theoretical basis for practical engineering applications.

关 键 词：相邻浮体 极端运动响应 主动学习 CFD 次序采样 

分 类 号：U661.32[交通运输工程—船舶及航道工程]