A Target Detection Algorithm for Marks Layout in Detail Drawings of Steel Structure

IF 1.1 4区工程技术 Q3 CONSTRUCTION & BUILDING TECHNOLOGY

International Journal of Steel Structures Pub Date : 2025-04-02 DOI:10.1007/s13296-025-00952-w

Yanlei Man, Qilin Zhang, Ying Cai, Zhiguo Chang

{"title":"A Target Detection Algorithm for Marks Layout in Detail Drawings of Steel Structure","authors":"Yanlei Man, Qilin Zhang, Ying Cai, Zhiguo Chang","doi":"10.1007/s13296-025-00952-w","DOIUrl":null,"url":null,"abstract":"<div><p>Detail drawings play an essential role in the steel structure manufacture as the basis for guiding manufacture and installation. Detail drawings are generally generated through software automatically nowadays. However, the current drawings created automatically by software are not of high quality, and the marks are overlapped, unattractive and unclear in the automatically generated drawings, which require considerable effort to manually adjust the position of the marks. In this paper, we developed an artificial intelligence algorithm for marks layout based on target detection algorithm. First, the marks layout problem is defined as the target detection problem. Then the Faster RCNN algorithm is refined on the basis of the unique characteristics of the marks layout problem, so that the algorithm is greatly strengthened in terms of accuracy and efficiency. It has been verified that after learning from the marks library, the marks generated by the proposed algorithm meet the requirements of manufacture. The aesthetics and clarity are significantly improved, and the workload of manual marks adjustment is dramatically reduced.</p></div>","PeriodicalId":596,"journal":{"name":"International Journal of Steel Structures","volume":"25 2","pages":"557 - 570"},"PeriodicalIF":1.1000,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Steel Structures","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s13296-025-00952-w","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Detail drawings play an essential role in the steel structure manufacture as the basis for guiding manufacture and installation. Detail drawings are generally generated through software automatically nowadays. However, the current drawings created automatically by software are not of high quality, and the marks are overlapped, unattractive and unclear in the automatically generated drawings, which require considerable effort to manually adjust the position of the marks. In this paper, we developed an artificial intelligence algorithm for marks layout based on target detection algorithm. First, the marks layout problem is defined as the target detection problem. Then the Faster RCNN algorithm is refined on the basis of the unique characteristics of the marks layout problem, so that the algorithm is greatly strengthened in terms of accuracy and efficiency. It has been verified that after learning from the marks library, the marks generated by the proposed algorithm meet the requirements of manufacture. The aesthetics and clarity are significantly improved, and the workload of manual marks adjustment is dramatically reduced.

查看原文本刊更多论文

钢结构详图中标记布局的目标检测算法

详细图作为指导钢结构制造和安装的依据，在钢结构制造中起着至关重要的作用。现在的详图一般都是通过软件自动生成的。但是，目前软件自动生成的图纸质量不高，自动生成的图纸中标记重叠，不美观，不清晰，需要人工调整标记的位置，这需要花费相当大的精力。本文提出了一种基于目标检测算法的标记布局人工智能算法。首先，将标记布局问题定义为目标检测问题。然后根据标记布局问题的独特特点对Faster RCNN算法进行了改进，使算法在精度和效率上得到了极大的加强。通过对标记库的学习，验证了该算法生成的标记满足制造要求。美观性和清晰度显著提高，大大减少了手动调整标记的工作量。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Steel Structures 工程技术-工程：土木

CiteScore

2.70

自引率

13.30%

发文量

122

审稿时长

12 months

期刊介绍： The International Journal of Steel Structures provides an international forum for a broad classification of technical papers in steel structural research and its applications. The journal aims to reach not only researchers, but also practicing engineers. Coverage encompasses such topics as stability, fatigue, non-linear behavior, dynamics, reliability, fire, design codes, computer-aided analysis and design, optimization, expert systems, connections, fabrications, maintenance, bridges, off-shore structures, jetties, stadiums, transmission towers, marine vessels, storage tanks, pressure vessels, aerospace, and pipelines and more.