基于聚类分析及灰色关联度的船舶系缆力影响因素分析  

Analysis of influencing factors of ship mooring forcebased on cluster analysis and grey relational degree

作　　者：麻云平 李楷[1] 郑奕 刘松[1] 王运龙[1] MA Yunping;LI Kai;ZHENG Yi;LIU Song;WANG Yunlong(School of Naval Architecture and Ocean Engineering,Dalian University of Technology,Dalian 116024,China)

机构地区：[1]大连理工大学船舶工程学院,辽宁大连116024

出　　处：《大连理工大学学报》2023年第4期377-384,共8页Journal of Dalian University of Technology

基　　金：国家自然科学基金资助项目(51509033);中央高校基本科研业务费专项资金资助项目(DUT19JC51)。

摘　　要：为研究风、浪、流、涌以及船舶装载状态等因素对码头系泊船舶缆绳受力影响的相对大小及线性关联程度,基于水动力计算软件AQWA计算获得400组不同影响因素组合下的缆绳受力数据,运用机器学习中常用的无监督学习算法k-means++算法以及灰色关联分析方法,分析缆绳受力与影响因素的内在联系.根据分析结果,获得了各因素对不同位置缆绳受力影响的相对大小及线性关联程度.该方法可用于优化系泊缆绳的布置方案.In order to study the relative magnitude and linear correlation degree of the influence of wind, wave, current, swell and ship loading state on the cable force of the mooring ship in the port, based on the 400 groups of cable force data calculated by hydrodynamic calculation software AQWA under different combinations of influencing factors, the internal relationship between the cable force and the influencing factors is analyzed by using the k -means++ algorithm, an unsupervised learning algorithm commonly used in machine learning, and the grey relational analysis method. According to the analysis results, the relative magnitude and linear correlation degree of each factor on the cable force at each position are obtained. The method can be used to optimize the mooring cable layout plan.

关 键 词：码头系泊 缆绳受力 无监督学习 聚类分析 灰色关联分析 

分 类 号：U662.3[交通运输工程—船舶及航道工程]