Safety early-warning model of prefabricated construction based on spatial cell analysis

doi:10.16265/j.cnki.issn1003-3033.2020.05.005

Abstract

Abstract: In order to improve safety performance of prefabricated construction, targeting at monitoring and early warning problems, analysis was conducted on unsafe behaviors, states and environment as well as cross correlation of these three hazard sources. Then, with unit space as research object, dynamic information of various hazard sources was extracted to construct hazard feature vector of spatial cell. Finally, a safety early warning model of spatial cells in prefabricated construction was constructed by using SVM classification algorithm. The results show that the model has good generalization ability, which can identify safety risks of space cells in practical construction sites.

Key words: prefabricated construction, spatial cell, dynamic hazard source, real-time monitoring, safety early-warning, support vector machine (SVM)

CLC Number:

X948

MA Hui, LYU Hang, LUAN Ruibin. Safety early-warning model of prefabricated construction based on spatial cell analysis[J]. China Safety Science Journal, 2020, 30(5): 27-32.

References

[1] 丁彦,田元福. 装配式建筑施工质量与安全风险评价研究[J].建筑经济,2019, 40(9): 80-84.
DING Yan, TIAN Yuanfu. Research on quality and safety risk evaluation of prefabricated building assessment[J]. Construction Economy,2019, 40(9): 80-84.
[2] 吴伟巍,PATRICK T I L,李启明,等. 施工现场安全危险源实时监控与安全风险预测方法研究[J].中国工程科学,2010, 12(3): 68-72.
WU Weiwei,PATRICK T I L, LI Qiming, et al. Tracking of safety hazards and real-time-prediction model of safety risks on construction sites[J]. Engineering Sciences,2010, 12(3): 68-72.
[3] AWOLUSI I, MARKS E, HALLOWELL M. Wearable technology for personalized construction safety monitoring and trending: review of applicable devices[J]. Automation in Construction, 2018, 85: 96-106.
[4] KIM H, LEE H, PARK M, et al. Automated hazardous area identification using laborers' actual and optimal routes[J]. Automation in Construction,2016, 65: 21-32.
[5] JIANG Wenbi, QU Fang, ZHANG Long.Quantitative identification and analysis on hazard sources of roof fall accident in coal mine[J]. Procedia Engineering,2012, 45: 83-88.
[6] LI Heng, LU Miaojia, HSU S,et al. Proactive behavior-based safety management for construction safety improvement[J]. Safety Science,2015, 75: 107-117.
[7] ISAAC S, EDREI T. A statistical model for dynamic safety risk control on construction sites[J]. Automation in Construction,2016, 63: 66-78.
[8] 郭红领,张知田,郁润. 基于危险系数的施工工人不安全行为评估[J].清华大学学报:自然科学版,2019, 59(11): 873-879.
GUO Hongling, ZHANG Zhitian, YU Run. Assessig construction workers' unsafe behavior using a danger coefficient[J]. Journal of Tsinghua University:Science and Technology,2019,59(11): 873-879.
[9] 侯茜,秦洁璇,李翠平. 安全生产预警综合分析与研究[J].中国安全科学学报, 2013, 23(6): 92-97.
HOU Qian, QIN Jiexuan, LI Cuiping. Comprehensive analysis and study of work safety early warning[J]. China Safety Science Journal,2013, 23(6): 92-97.
[10] 杨涛. 建筑工程高空作业安全预警与管理研究[D].南京:东南大学, 2016.
YANG Tao. Research on safety early-warning and management in works at heights of construction engineering [D]. Nanjing:Southeast University, 2016.
[11] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297.
[12] 宋鹏峰,叶庆卫,陆志华,等. 基于拟合型弱分类器的AdaBoost算法[J].电信科学,2019, 35(11): 1-15.
SONG Pengfeng, YE Qingwei, LU Zhihua,et al. AdaBoost algorithm based on fitted weak classifier[J]. Telecommunications Science,2019, 35(11): 1-15.
[13] 王玉银,王庆贺,耿悦. 建筑结构用再生混凝土水平受力构件研究进展[J].工程力学, 2018, 35(4): 1-15.
WANG Yuyin, WANG Qinghe, GENG Yue. State-of-the-art of horizontal structural members using recycled aggregate concrete[J]. Engineering Mechanics, 2018, 35(4): 1-15.