Hao Pu , Ting Hu , Taoran Song , Paul Schonfeld , Wei Li , Lihui Peng
{"title":"Knowledge graph-driven mountain railway alignment optimization integrating karst hazard assessment","authors":"Hao Pu , Ting Hu , Taoran Song , Paul Schonfeld , Wei Li , Lihui Peng","doi":"10.1016/j.asoc.2024.112421","DOIUrl":null,"url":null,"abstract":"<div><div>Karst hazard is a considerable threat that should be considered in railway alignment design for mountainous regions with dense water systems. Nevertheless, alignment design principles in karst regions have not been systematically studied. Moreover, a quantitative karst hazard assessment model is currently lacking for automated alignment optimization. To solve the above problems, based on the analyses of karst inducing factors and hazard representation, the railway alignment design principles in karst regions are summarized through an event tree. A highly-coupled knowledge graph (called KaRAD-KG) modeling method is proposed. Then, a bi-objective alignment optimization model considering railway construction cost and karst hazard (mainly including hazard components of synclinal karst, anticlinal karst and karst depression) is constructed. To solve the optimization model, a knowledge-driven distance transform algorithm incorporating a karst hazard assessment method and a multicriteria tournament decision method is customized. Finally, the application in a real-world case indicates that the proposed method can generate an alignment which reduces construction cost by 3.39 % and karst hazard by 18.73 % compared to the best manually-designed alternative, which verifies the effectiveness of this method for assisting actual railway alignment design in a karst-dense mountainous region.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"167 ","pages":"Article 112421"},"PeriodicalIF":7.2000,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Soft Computing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1568494624011955","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Karst hazard is a considerable threat that should be considered in railway alignment design for mountainous regions with dense water systems. Nevertheless, alignment design principles in karst regions have not been systematically studied. Moreover, a quantitative karst hazard assessment model is currently lacking for automated alignment optimization. To solve the above problems, based on the analyses of karst inducing factors and hazard representation, the railway alignment design principles in karst regions are summarized through an event tree. A highly-coupled knowledge graph (called KaRAD-KG) modeling method is proposed. Then, a bi-objective alignment optimization model considering railway construction cost and karst hazard (mainly including hazard components of synclinal karst, anticlinal karst and karst depression) is constructed. To solve the optimization model, a knowledge-driven distance transform algorithm incorporating a karst hazard assessment method and a multicriteria tournament decision method is customized. Finally, the application in a real-world case indicates that the proposed method can generate an alignment which reduces construction cost by 3.39 % and karst hazard by 18.73 % compared to the best manually-designed alternative, which verifies the effectiveness of this method for assisting actual railway alignment design in a karst-dense mountainous region.
期刊介绍:
Applied Soft Computing is an international journal promoting an integrated view of soft computing to solve real life problems.The focus is to publish the highest quality research in application and convergence of the areas of Fuzzy Logic, Neural Networks, Evolutionary Computing, Rough Sets and other similar techniques to address real world complexities.
Applied Soft Computing is a rolling publication: articles are published as soon as the editor-in-chief has accepted them. Therefore, the web site will continuously be updated with new articles and the publication time will be short.