Article(id=1242141307330703510, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1242141288397615188, articleNumber=null, orderNo=null, doi=10.3981/j.issn.1000-7857.2023.06.00958, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1687622400000, receivedDateStr=2023-06-25, revisedDate=1713715200000, revisedDateStr=2024-04-22, acceptedDate=null, acceptedDateStr=null, onlineDate=1722441600000, onlineDateStr=2024-08-01, pubDate=1720800000000, pubDateStr=2024-07-13, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1722441600000, onlineIssueDateStr=2024-08-01, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774079165533, creator=sys-migrate, updateTime=1774079165533, updator=sys-migrate, issue=Issue{id=1242141288397615188, tenantId=1146029695717560320, journalId=1146031591421210625, year='2024', volume='42', issue='13', pageStart='1', pageEnd='140', issueExtLink='null', onlineDate='null', pubDate='1720800000000', pubDateStr='2024-07-13', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=null, issueType=-1, specialIssue=null, createTime=1774079161019, creator='sys-migrate', updateTime=1774079161019, updator='sys-migrate', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=95, endPage=104, ext={EN=ArticleExt(id=1242141320433705423, articleId=1242141307330703510, tenantId=1146029695717560320, journalId=1146031591421210625, language=EN, title=Deep learning based catenary single point mooring design parameters prediction, columnId=1242141297809629551, journalTitle=Science & Technology Review, columnName=Exclusive: Intelligent Development of Marine Engineering Equipment, runingTitle=null, highlight=null, articleAbstract=A catenary single-point mooring requires a simulation environment based on inputs such as basic conditions, operating conditions, self-storage conditions, motion and force requirements, and multi-point testing to find the optimal design. The paper uses deep learning method to solve the mooring system prediction problem. Firstly, two datasets, i.e., self dataset and operation dataset are acquired by simulation calculation. Then the self dataset is predicted and the data is divided into three categories: local, global, and global plus local for training and validation, and a two-layer full-connected neural network is used to predict the regression problem with an accuracy of over 90%. As the results are not satisfactory when the model is applied to more complex operation datasets, a self-built model DBRNet12 complex network using DNN+BN+ReLU as the minimum component is added to handle more operation data, thus obtaining an average accuracy of 86%. The self-built RNet40 network based on the idea of residuals on DBRNet12 achieves a 90% average accuracy. In terms of network architecture, a deep neural network is built to predict parameters through fully connected layers, and the network structure is continuously optimized. Finally, the evaluation of relative error is used to evaluate the effectiveness of the prediction and the residual network is used for optimization. Through this procedure, the application effect of deep learning methods in mooring system prediction problems is achieved, and the ideas provide references for further research and practice in this field., authors=SUN Qiang1,2 , LI Yan3 , PENG Dongsheng2 , WANG Yuxin3 , YAN Jun1 , YUE Qianjin1 , ZHONG Wanxie1 , authorsList=SUN Qiang, LI Yan, PENG Dongsheng, WANG Yuxin, YAN Jun, YUE Qianjin, ZHONG Wanxie, authorCompany=1. Faculty of Vehicle Engineering and Mechanics, Dalian University of Technology, Dalian 116024, China;1,2 , 李颜3 , 彭东升2 , 王宇新3 , 阎军1 , 岳前进1 , 钟万勰1 , authorsList=孙强, 李颜, 彭东升, 王宇新, 阎军, 岳前进, 钟万勰, authorCompany=1. 大连理工大学运载工程与力学学部, 大连 116024;
科技导报
| 专题：海洋工程装备智能化 2024, 42(13): 95-104
基于深度学习的悬链式单点系泊设计指标预测
全屏
孙强1,2 , 李颜3 , 彭东升2 , 王宇新3 , 阎军1 , 岳前进1 , 钟万勰1
作者信息
1. 大连理工大学运载工程与力学学部, 大连 116024;
Deep learning based catenary single point mooring design parameters prediction
Affiliations
出版时间: 2024-07-13
doi: 10.3981/j.issn.1000-7857.2023.06.00958
文章导航
悬链式单点系泊需要建立基于基础条件、工作条件、自存条件、运动和力要求等输入的模拟环境，并进行多点测试来寻找最佳设计。通过仿真计算构建2个主要数据集，即oper-ation数据集和self数据集。对self数据集进行预测，并将数据分为局部、全局和全局加局部3类进行训练和验证，使用4层全连接神经网络来预测回归问题，准确率可达90%以上。将该模型应用于更复杂的operation数据集时的效果并不理想。采用DNN+BN+ReLU作为最小分量自建模型DBRNet12复杂网络处理operation的数据得到86%的平均准确率。依据残差思想在DBRNet12基础上自建RNet40网络取得了90%的平均准确率。在网络架构方面，搭建了深度神经网络，通过全连接层进行预测，并对网络结构进行了持续的优化。最后，通过相对误差的评估来衡量预测效果的优劣，并利用残差网络进行优化。
多元回归
/
单点系泊
/
深度学习
/
残差网络
A catenary single-point mooring requires a simulation environment based on inputs such as basic conditions, operating conditions, self-storage conditions, motion and force requirements, and multi-point testing to find the optimal design. The paper uses deep learning method to solve the mooring system prediction problem. Firstly, two datasets, i.e., self dataset and operation dataset are acquired by simulation calculation. Then the self dataset is predicted and the data is divided into three categories: local, global, and global plus local for training and validation, and a two-layer full-connected neural network is used to predict the regression problem with an accuracy of over 90%. As the results are not satisfactory when the model is applied to more complex operation datasets, a self-built model DBRNet12 complex network using DNN+BN+ReLU as the minimum component is added to handle more operation data, thus obtaining an average accuracy of 86%. The self-built RNet40 network based on the idea of residuals on DBRNet12 achieves a 90% average accuracy. In terms of network architecture, a deep neural network is built to predict parameters through fully connected layers, and the network structure is continuously optimized. Finally, the evaluation of relative error is used to evaluate the effectiveness of the prediction and the residual network is used for optimization. Through this procedure, the application effect of deep learning methods in mooring system prediction problems is achieved, and the ideas provide references for further research and practice in this field.
multiple regression
/
single point mooring
/
deep learning
/
residual network
孙强, 李颜, 彭东升, 王宇新, 阎军, 岳前进, 钟万勰.
基于深度学习的悬链式单点系泊设计指标预测.
科技导报,
2024
, 42
(13)
: 95
-104
.
DOI: 10.3981/j.issn.1000-7857.2023.06.00958
SUN Qiang, LI Yan, PENG Dongsheng, WANG Yuxin, YAN Jun, YUE Qianjin, ZHONG Wanxie.
Deep learning based catenary single point mooring design parameters prediction[J].
Science & Technology Review ,
2024
, 42
(13)
: 95
-104
.
DOI: 10.3981/j.issn.1000-7857.2023.06.00958
2024年第42卷第13期
PDF下载
229
25
引用本文
BibTeX
文章信息
doi: 10.3981/j.issn.1000-7857.2023.06.00958
接收时间：2023-06-25
首发时间：2024-08-01
出版时间：2024-07-13
收稿日期：2023-06-25
修回日期：2024-04-22
https://castjournals.cast.org.cn/joweb/kjdb/CN/10.3981/j.issn.1000-7857.2023.06.00958
引用本文
BibTeX
2种不同金属材料的力学参数
科 属数 种数 占总种数比例 属 种数 占总种数比例 鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78 小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39 多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39 红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87 小菇属 Mycena 11 5.26 光柄菇属 Pluteus 5 2.39 红菇属 Russula 17 8.13 栓菌属 Trametes 5 2.39
关闭全屏
BibTeX
EndNote
RefWorks
TxT
PDF下载
全屏
229
25
关闭全屏
北京市海淀区学院南路86号
010-62199257
qkjq@cast.org.cn
