|本期目录/Table of Contents|

[1]缪季,段立平,刘吉明,等.基于贝叶斯优化XGBoost的建筑施工事故类型预测*[J].中国安全生产科学技术,2024,20(5):57-63.[doi:10.11731/j.issn.1673-193x.2024.05.008]
　MIAO Ji,DUAN Liping,LIU Jiming,et al.Prediction on accident types of building construction based on Bayesian optimized XGBoost[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(5):57-63.[doi:10.11731/j.issn.1673-193x.2024.05.008]
点击复制

基于贝叶斯优化XGBoost的建筑施工事故类型预测*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
20
期数:
2024年5期
页码:
57-63
栏目:
学术论著
出版日期:
2024-05-31

文章信息/Info

Title:
Prediction on accident types of building construction based on Bayesian optimized XGBoost
文章编号:
1673-193X(2024)-05-0057-07
作者:
缪季; 段立平; 刘吉明; 林思伟; 赵金城
（1.上海交通大学 船舶海洋与建筑工程学院，上海 200240；
2.上海市公共建筑和基础设施数字化运维重点实验室，上海 200240）
Author(s):
MIAO Ji;  DUAN Liping;  LIU Jiming;  LIN Siwei;  ZHAO Jincheng
（1.School of Ocean and Civil Engineering,Shanghai Jiao Tong University,Shanghai 200240,China;
2.Shanghai Key Laboratory for Digital Maintenance of Buildings and Infrastructure,Shanghai 200240,China)
关键词:
建筑工程; 事故预测; 特征选择; 机器学习; 贝叶斯优化
Keywords:
construction engineering;  accident prediction;  feature selection;  machine learning;  Bayesian optimization
分类号:
X947
DOI:
10.11731/j.issn.1673-193x.2024.05.008
文献标志码:
A
摘要:
为探究建筑工程施工过程中不同风险特征与施工事故类型之间的关联性，提出1种融合特征选择算法和机器学习算法的建筑事故类型预测模型。基于619项国内建筑事故报告建立建筑施工风险特征体系，通过条件互信息最大化（CMIM）-Boruta方法筛选出26个关键风险特征，将其作为贝叶斯优化极限梯度提升（XGBoost）预测模型的输入变量并在测试集上评估该模型的预测精度。研究结果表明：XGBoost模型的预测性能优于其他机器学习模型；CMIM-Boruta方法和贝叶斯优化方法能够有效提升机器学习模型的预测性能；通过2个实际事故案例验证得到该模型具有一定实用性。研究结果对相关企业安全管理人员更准确地识别施工现场潜在危险、采取更具针对性的预防措施具有一定参考意义。
Abstract:
In order to explore the correlation between different risk characteristics and construction accident types in the construction process of construction engineering,a prediction model of construction accident types combining the feature selection algorithm and machine learning algorithm was proposed.Based on 619 domestic construction accident reports,a construction risk feature system was established,and 26 key risk features were screened out by the conditional mutual information maximization (CMIM)-Boruta method,which were used as the input variables of Bayesian optimized extreme gradient boosting (XGBoost) prediction model.The prediction accuracy of the proposed model was evaluated on the test sets.The results show that the XGBoost model has better prediction performance than other machining learning methods.Moreover,the CMIM-Boruta method and Bayesian optimization method can effectively improve the prediction performance of machine learning models.Through two actual accident cases,it is proved that the model has certain practicability.The research results have reference significance for the safety management personnel to more accurately identify the potential hazards at the construction site and then take more targeted prevention measures.

参考文献/References:

［1］全国工程质量安全监管信息平台公共服务门户［EB/OL］.(2023-05-31)［2023-06-11］.https://zlaq.mohurd.gov.cn/fwmh/bjxcjgl/fwmh/pages/default/index.html.
［2］李政道,曾佳,吴恒钦.融合GWO和SVR的建筑安全事故预测模型［J/OL］.安全与环境学报:1-10［2024-03-12］.https://doi.org/10.13637/j.issn.1009-6094.2023.0503.
［3］李华,赵杰风,王藤.建筑施工高处吊篮作业安全防护预警模型研究［J］.中国安全生产科学技术,2019,15(10):146-151. LI Hua,ZHAO Jiefeng,WANG Teng.Research on early warning model of safety protection for high-hanging basket operation［J］.Journal of Safety Science and Technology,2019,15(10):146-151.
［4］张建荣,张伟,薛楠楠,等.基于随机森林算法的塔式起重机安全事故预测及致因分析［J］.安全与环境工程,2021,28(5):36-42. ZHANG Jianrong,ZHANG Wei,XUE Nannan,et al.Prediction and cause analysis of tower-crane safety accidents by using random forest algorithm［J］.Safety and Environmental Engineering,2021,28(5):36-42.
［5］CHOI J,GU B,CHIN S,et al.Machine learning predictive model based on national data for fatal accidents of construction workers［J］.Automation in Construction,Amsterdam:Elsevier,2020,110:102974.
［6］ZHU R C,HU X F,HOU J Q,et al.Application of machine learning techniques for predicting the consequences of construction accidents in China［J］.Process Safety and Environmental Protection,2021,145:293-302.
［7］KANNANGARA K K P M,ZHOU W H,DING Z,et al.Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method［J］.Journal of Rock Mechanics and Geotechnical Engineering,2022,14(4):1052-1063.
［8］FLEURET F.Fast binary feature selection with conditional mutual information［J］.Journal of Machine Learning Research,2004,5:1531-1555.
［9］SHUKLA J,BARREDA-ANGELES M,OLIVER J,et al.Feature extraction and selection for emotion recognition from electrodermal activity［J］.IEEE Transactions on Affective Computing,2021,12(4):857-869.
［10］KURSA M B,RUDNICKI W R.Feature selection with the boruta package［J］.Journal of Statistical Software,2010,36(11):1-13.
［11］许行,张凯,王文剑.一种小样本数据的特征选择方法［J］.计算机研究与发展,2018,55(10):2321-2330. XU Xing,ZHANG Kai,WANG Wenjian.A feature selection method for small samples［J］.Journal of Computer Research and Development,2018,55(10):2321-2330.
［12］CHEN T,GUESTRIN C.XGBoost:a scalable tree boosting system［C］//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco California.USA:ACM,2016:785-794.
［13］NGUYEN H,HOANG N D.Computer vision-based classification of concrete spall severity using metaheuristic-optimized extreme gradient boosting machine and deep convolutional neural network［J］.Automation in Construction,2022,140:104371.
［14］YANG B,LI X J,LIU Y H,et al.Comparison of models for predicting winter individual thermal comfort based on machine learning algorithms［J］.Building and Environment,2022,215:108970.
［15］ZHANG Q L,HU W F,LIU Z Y,et al.TBM performance prediction with Bayesian optimization and automated machine learning［J］.Tunnelling and Underground Space Technology,2020,103:103493.
［16］张化进,吴顺川,张中信,等.边坡稳定性自动机器学习预测方法研究［J］.中国安全生产科学技术,2023,19(1):35-40. ZHANG Huajin,WU Shunchuan,ZHANG Zhongxin,et al.Research on automatic machine learning prediction method of slope stability［J］.Journal of Safety Science and Technology,2023,19(1):35-40.
［17］ZHANG W,ZHU S N,ZHANG X,et al.Identification of critical causes of construction accidents in China using a model based on system thinking and case analysis［J］.Safety Science,2020,121:606-618.
［18］GAYDON C.Fast-CMIM［EB/OL］.(2023-04-08)［2023-05-08］.https://github.com/CharlesGaydon/Fast-CMIM.
［19］SALARIAN A A,ETEMADFARD H,RAHIMZADEGAN A,et al.Investigating the role of clustering in construction-accident severity prediction using a heterogeneous and imbalanced data set［J］.Journal of Construction Engineering and Management,2023,149(2):04022161.
［20］GHORBANI R,GHOUSI R.Comparing different resampling methods in predicting students performance using machine learning techniques［J］.IEEE Access,2020,8:67899-67911.
［21］MEGNIDIO T M,ADEDEJI J A.Machine learning for road traffic accident improvement and environmental resource management in the transportation sector［J］.Sustainability,2023,15(3):2014.
［22］湛江市遂溪县应急管理局.遂溪县乌塘镇浩发村“2·15”高处坠落伤亡事故调查报告［EB/OL］.(2023-06-06)［2023-06-09］.http://www.suixi.gov.cn/zjsxyjgl/gkmlpt/content/1/1769/post_1769794.html#5910.
［23］广西崇左市江州区人民政府.江州区驮卢镇连塘村安定屯“2·23”坍塌事故调查报告［EB/OL］.(2023-04-28)［2023-05-23］.http://www.czsjzq.gov.cn/xxfb/qtzdly0/aqsc/aqsgdcbg/t16484883.shtml.
［24］KOC K,EKMEKCIOGˇLU ,GURGUN A P.Developing a national data-driven construction safety management framework with interpretable fatal accident prediction［J］.Journal of Construction Engineering and Management,2023,149(4):04023010.
［25］成连华,曹东强,李欣.房屋建筑施工事故致因因素分类研究［J］.中国安全科学学报,2023,33(2):16-22. CHENG Lianhua,CAO Dongqiang,LI Xin.Research on cause factors classification of housing construction accidents［J］.China Safety Science Journal,2023,33(2):16-22.

相似文献/References:

[1]朱庆明,张浩.三次指数平滑法在煤矿事故预测中的应用研究[J].中国安全生产科学技术,2012,8(4):103.
　ZHU Qing ming,ZHANG Hao.Study on the application of cubic exponential smoothing method in coal mine accidents forecasting[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(5):103.
[2]张悦,李峰,石超,等.改进GM(1,1)模型在我国危险化学品 事故预测中的应用[J].中国安全生产科学技术,2012,8(5):96.
　ZHANG Yue,LI Feng,SHI Chao,et al.Application of improved GM (1,1) model for prediction of hazardous chemical accidents in China[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(5):96.
[3]李明洋,姜福川,陈思帆.改进欧拉法的GM(1,1)模型及其在非煤矿山事故预测中的应用[J].中国安全生产科学技术,2013,9(8):188.[doi:10.11731/j.issn.1673-193x.2013.08.035]
　LI Ming yang,JIANG Fu chuan,CHEN Si fan.The improved euler method GM(1,1) model and its application in the accident prediction of noncoal mine[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(5):188.[doi:10.11731/j.issn.1673-193x.2013.08.035]
[4]李明洋,姜福川.基于最小二乘法的灰色GM(1,1)改进模型在非煤矿山事故预测中的应用[J].中国安全生产科学技术,2013,9(11):83.[doi:10.11731/j.issn.1673-193x.2013.11.014]
　LI Ming yang,JIANG Fu chuan.Inproved gray GM(1,1) model in the noncoal mine accident prediction based on the methed of least square[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(5):83.[doi:10.11731/j.issn.1673-193x.2013.11.014]
[5]郑霞忠,王晓宇,陈述,等.高处坠落事故的人因失误与干预策略研究[J].中国安全生产科学技术,2017,13(6):139.[doi:10.11731/j.issn.1673-193x.2017.06.023]
　ZHENG Xiazhong,WANG Xiaoyu,CHEN Shu,et al.Study on human error and intervention strategies of high falling accidents[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2017,13(5):139.[doi:10.11731/j.issn.1673-193x.2017.06.023]
[6]孟庆森,韩皓,李易.基于贝叶斯优化随机森林的高速公路二次事故预测研究[J].中国安全生产科学技术,2023,19(7):205.[doi:10.11731/j.issn.1673-193x.2023.07.030]
　MENG Qingsen,HAN Hao,LI Yi.Research on secondary accident prediction of expressway based on Bayesian optimization random forest[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(5):205.[doi:10.11731/j.issn.1673-193x.2023.07.030]
[7]白金花,刘勇,程智慧,等.基于ARMA-SSESM组合模型的危险品道路运输泄漏事故预测研究*[J].中国安全生产科学技术,2023,19(10):171.[doi:10.11731/j.issn.1673-193x.2023.10.024]
　BAI Jinhua,LIU Yong,CHENG Zhihui,et al.Research on prediction of hazardous materials road transportation leakage accident based on ARMA-SSESM combination model[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(5):171.[doi:10.11731/j.issn.1673-193x.2023.10.024]

备注/Memo

备注/Memo:
收稿日期： 2023-11-07
* 基金项目： 上海市社会发展科技攻关项目（21DZ1204600）
作者简介： 缪季，硕士研究生，主要研究方向为建筑施工风险分析。
通信作者： 段立平，博士，助理研究员，主要研究方向为计算结构力学。
更新日期/Last Update: 2024-05-30