Visualizing what’s missing: Using deep learning and Bow-Tie diagrams to identify and visualize missing leading indicators in industrial construction

IF 3.9 2区 工程技术 Q1 ERGONOMICS
Rose Marie Charuvil Elizabeth , Fereshteh Sattari , Lianne Lefsrud , Brian Gue
{"title":"Visualizing what’s missing: Using deep learning and Bow-Tie diagrams to identify and visualize missing leading indicators in industrial construction","authors":"Rose Marie Charuvil Elizabeth ,&nbsp;Fereshteh Sattari ,&nbsp;Lianne Lefsrud ,&nbsp;Brian Gue","doi":"10.1016/j.jsr.2025.02.007","DOIUrl":null,"url":null,"abstract":"<div><div><em>Introduction</em>: In the construction industry, where safety is paramount, the frequency and severity of workplace incidents remain critical concerns. Therefore, site safety inspections have become essential for health and safety programs. While incident data is frequently used to identify gaps in the safety management system, inspection reports are rarely analyzed to identify unsafe patterns on site and reveal measures for safety enhancement. This limitation can reduce the effectiveness of safety inspections, and therefore, this study aims to identify what safety leading indicators do not capture hazards during inspections. <em>Methods</em>: Natural language processing (NLP), text mining, and deep learning techniques such as sentence bidirectional encoder representations from transformers (SBERT) are used to generate embeddings and compute the similarity between 633 incidents and 9,681 inspection descriptions of a construction project from 2015 to 2018 in Canada. Root cause analysis is conducted on selected incidents with the slightest similarity with inspection descriptions using a customized human and organizational framework. Bow-tie and Sankey’s diagrams illustrate and visualize what leading indicators miss capturing hazards during inspections that lead to incidents. In addition, N-gram models are used for validation and co-occurrence networks to extract meaningful information and identify patterns from incident and inspection reports. <em>Results</em>: The results demonstrate that the indicators that cause incidents with the most severe consequences and are inadequately captured during inspections are: working at heights (81%), equipment handling/storage (17%), and ergonomics (0.4%). <em>Conclusion and practical application</em>: The findings provide insights for decision-makers on the strategies needed to enhance risk management, facilitating predictive and proactive approaches. By embracing a transdisciplinary approach, the research techniques applied in this study can be effectively used and transferred across various other industries.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"93 ","pages":"Pages 1-11"},"PeriodicalIF":3.9000,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Safety Research","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0022437525000106","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ERGONOMICS","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction: In the construction industry, where safety is paramount, the frequency and severity of workplace incidents remain critical concerns. Therefore, site safety inspections have become essential for health and safety programs. While incident data is frequently used to identify gaps in the safety management system, inspection reports are rarely analyzed to identify unsafe patterns on site and reveal measures for safety enhancement. This limitation can reduce the effectiveness of safety inspections, and therefore, this study aims to identify what safety leading indicators do not capture hazards during inspections. Methods: Natural language processing (NLP), text mining, and deep learning techniques such as sentence bidirectional encoder representations from transformers (SBERT) are used to generate embeddings and compute the similarity between 633 incidents and 9,681 inspection descriptions of a construction project from 2015 to 2018 in Canada. Root cause analysis is conducted on selected incidents with the slightest similarity with inspection descriptions using a customized human and organizational framework. Bow-tie and Sankey’s diagrams illustrate and visualize what leading indicators miss capturing hazards during inspections that lead to incidents. In addition, N-gram models are used for validation and co-occurrence networks to extract meaningful information and identify patterns from incident and inspection reports. Results: The results demonstrate that the indicators that cause incidents with the most severe consequences and are inadequately captured during inspections are: working at heights (81%), equipment handling/storage (17%), and ergonomics (0.4%). Conclusion and practical application: The findings provide insights for decision-makers on the strategies needed to enhance risk management, facilitating predictive and proactive approaches. By embracing a transdisciplinary approach, the research techniques applied in this study can be effectively used and transferred across various other industries.
可视化缺失:使用深度学习和领结图来识别和可视化工业建设中缺失的领先指标
导读:在建筑行业,安全是最重要的,工作场所事故的频率和严重程度仍然是关键问题。因此,现场安全检查已成为健康和安全计划必不可少的一部分。虽然事故数据经常用于识别安全管理系统中的漏洞,但很少分析检查报告以识别现场的不安全模式并提出加强安全的措施。这种限制会降低安全检查的有效性,因此,本研究旨在确定哪些安全领先指标在检查过程中没有捕捉到危险。方法:利用自然语言处理(NLP)、文本挖掘和深度学习技术(如来自变压器的句子双向编码器表示(SBERT))生成嵌入,并计算2015年至2018年加拿大建设项目的633个事件和9681个检查描述之间的相似性。使用定制的人员和组织框架,对与检查描述最相似的选定事件进行根本原因分析。Bow-tie和Sankey的图表说明并可视化了在导致事故的检查过程中,哪些领先指标没有捕捉到危险。此外,N-gram模型用于验证和共现网络,以从事件和检查报告中提取有意义的信息并识别模式。结果:结果表明,在检查过程中,导致最严重后果的事故的指标是:高空作业(81%)、设备搬运/存储(17%)和人体工程学(0.4%)。结论和实际应用:研究结果为决策者提供了加强风险管理所需的战略见解,促进了预测性和前瞻性的方法。通过采用跨学科的方法,本研究中应用的研究技术可以有效地应用和转移到其他各个行业。
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
CiteScore
6.40
自引率
4.90%
发文量
174
审稿时长
61 days
期刊介绍: Journal of Safety Research is an interdisciplinary publication that provides for the exchange of ideas and scientific evidence capturing studies through research in all areas of safety and health, including traffic, workplace, home, and community. This forum invites research using rigorous methodologies, encourages translational research, and engages the global scientific community through various partnerships (e.g., this outreach includes highlighting some of the latest findings from the U.S. Centers for Disease Control and Prevention).
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信