Mariano Marcos-Pérez , Javier Jiménez de la Jara , Daniel Precioso , Aurelio Muñoz , M. Victoria Redondo-Neble , David Gómez-Ullate
{"title":"New analysis in the preliminary design for LNG and LPG ships","authors":"Mariano Marcos-Pérez , Javier Jiménez de la Jara , Daniel Precioso , Aurelio Muñoz , M. Victoria Redondo-Neble , David Gómez-Ullate","doi":"10.1016/j.marstruc.2025.103863","DOIUrl":null,"url":null,"abstract":"<div><div>In recent years, the production of LNG and LPG ships has increased, driven by the increasing demand for natural and petroleum gases. To meet this demand, ship designs must be optimized at all stages, requiring designers to have advanced, efficient and accurate design tools. This study presents new statistical and regression analyses of data extracted from the Hyundai Heavy Industries Shipbuilding Group catalogue which includes information on LNG and LPG ships built between 1979 and 2023. The database includes 145 LNG carriers and 322 LPG carriers, representing approximately 20% of the global gas carrier fleet. Simple and multiple regression analyses were used to estimate dependent variables and their correlation to other ship parameters. In addition, Machine Learning algorithms were trained and compared against these traditional methods. This study provides updated tools to support the preliminary design of LNG and LPG ships, enhancing the understanding and accuracy of early-stage design decisions.</div></div>","PeriodicalId":49879,"journal":{"name":"Marine Structures","volume":"104 ","pages":"Article 103863"},"PeriodicalIF":4.0000,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Marine Structures","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0951833925000863","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0
Abstract
In recent years, the production of LNG and LPG ships has increased, driven by the increasing demand for natural and petroleum gases. To meet this demand, ship designs must be optimized at all stages, requiring designers to have advanced, efficient and accurate design tools. This study presents new statistical and regression analyses of data extracted from the Hyundai Heavy Industries Shipbuilding Group catalogue which includes information on LNG and LPG ships built between 1979 and 2023. The database includes 145 LNG carriers and 322 LPG carriers, representing approximately 20% of the global gas carrier fleet. Simple and multiple regression analyses were used to estimate dependent variables and their correlation to other ship parameters. In addition, Machine Learning algorithms were trained and compared against these traditional methods. This study provides updated tools to support the preliminary design of LNG and LPG ships, enhancing the understanding and accuracy of early-stage design decisions.
期刊介绍:
This journal aims to provide a medium for presentation and discussion of the latest developments in research, design, fabrication and in-service experience relating to marine structures, i.e., all structures of steel, concrete, light alloy or composite construction having an interface with the sea, including ships, fixed and mobile offshore platforms, submarine and submersibles, pipelines, subsea systems for shallow and deep ocean operations and coastal structures such as piers.