高斯混合模型下建筑工人高空作业失稳检测方法

doi:10.16265/j.cnki.issn1003-3033.2023.04.0697

中国安全科学学报 ›› 2023, Vol. 33 ›› Issue (4): 114-120.doi: 10.16265/j.cnki.issn1003-3033.2023.04.0697

高斯混合模型下建筑工人高空作业失稳检测方法

范文涵¹^,²(), 林欣燕¹, 左超³, 徐小媛¹, 周建亮¹^,⁴^,^**()

¹ 中国矿业大学力学与土木工程学院,江苏徐州 221116
² 山西财贸职业技术学院工程艺术设计系,山西太原 030602
³ 北京构力科技有限公司,北京,100084
⁴ 江苏数链建筑科学研究院有限公司,江苏徐州 221116

收稿日期:2022-11-13 修回日期:2023-02-09 出版日期:2023-04-28
通讯作者:
^** 周建亮(1975—),男,山东青州人,博士,教授,博士生导师,主要从事BIM、智慧城市及安全管理方面的研究。E-mail:zhoujianliang@cumt.edu.cn。
作者简介:
范文涵 (1980—),男,山西太原人,博士研究生,副教授,主要研究方向为BIM与智慧建造。E-mail:523709221@qq.com。
基金资助:
国家自然科学基金面上项目资助(72171224); 教育部人文社科规划基金资助(19YJAZH122); 中国建设教育协会教育教学科研重点课题(2021168)

Instability detection method for construction workers working at altitude based on Gaussian mixture model

FAN Wenhan¹^,²(), LIN Xinyan¹, ZUO Chao³, XU Xiaoyuan¹, ZHOU Jianliang¹^,⁴^,^**()

¹ School of Mechanics and Civil Engineering, China University of Mining and Technology, Xuzhou Jiangsu 221116,China
² Department of Engineering Art and Design,Shanxi Vocational and Technical College of Finance and Trade,Taiyuan Shanxi 030602,China
³ Beijing Glory PKPM Technology Co., Ltd., Beijing 100084,Chian
⁴ Jiangsu Shullian Building Science Research Institute Co., Ltd., Xuzhou Jiangsu 221116,China

Received:2022-11-13 Revised:2023-02-09 Published:2023-04-28

摘要/Abstract

摘要：

为防止施工现场高处坠落事故,实现个性化矫正管理,在考虑个体异质性对运动信号造成的差异化影响基础上,提出一种基于高斯混合模型(GMM)的实时检测方法,可及时识别建筑工人高空作业失稳状态。首先,采用姿态传感器实时采集加速度和角速度数据,以刻画建筑工人的高空作业姿态特征;然后,基于GMM算法,建立建筑工人高空作业的个性化失稳检测模型,获得个性化阈值,以判断姿势失稳状态;最后,通过试验对比基于个体数据集和公共数据集2种方式构建的模型。研究结果表明:生成的个性化检测模型在准确度P、召回率R和综合评价指标F₁值上,均远优于公共数据集模型,具有更好的个性化检测效果。该失稳检测方法能够从工人的作业姿态习惯探究个性化的高空失稳风险,促进差异化安全预控和精准化安全培训。

关键词: 高斯混合模型(GMM), 建筑工人, 高空作业, 失稳检测, 实时检测

Abstract:

In order to prevent the construction site high fall accident and achieve personalized correction management, based on considering the differentiation of motion signals caused by individual heterogeneity, a real-time detection method based on GMM was proposed, which can timely identify the instability state of construction workers working at height. This method used posture sensors to collect real-time acceleration and angular velocity data to describe the posture features of construction workers working at height. Based on GMM, it established a personalized instability detection method to obtain personalized thresholds for judging the instability state of construction workers working at heights. Finally, it compared two models constructed by individual and public data sets through experiments. The results show that the personalized detection model generated is far superior to the public data set model in accuracy (P), recall rate(R) and comprehensive evaluation value (F₁). It shows the better-personalized detection effect using the personalized detection model. This study can help identify personalized risks of instability working at height from workers' habitual working postures, provide new ideas and references for preventing falling accidents, and help realize personalized correction training for workers.

Key words: gaussian mixture model(GMM), construction worker, work at height, instability detection, real-time detection

范文涵, 林欣燕, 左超, 徐小媛, 周建亮. 高斯混合模型下建筑工人高空作业失稳检测方法[J]. 中国安全科学学报, 2023, 33(4): 114-120.

FAN Wenhan, LIN Xinyan, ZUO Chao, XU Xiaoyuan, ZHOU Jianliang. Instability detection method for construction workers working at altitude based on Gaussian mixture model[J]. China Safety Science Journal, 2023, 33(4): 114-120.

图/表 5

参考文献 17

[1]	安慧, 黄艾, 安敏, 等. 基于模糊故障树的建筑施工高处坠落全面风险评估[J]. 科学技术与工程, 2022, 22(19): 8568-8576.
	AN Hui, HUANG Ai, AN Min, et al. Comprehensive risk assessment of building construction falling from height based on fuzzy fault tree[J]. Science Technology and Engineering, 2022, 22(19) : 8568-8576.
[2]	孙世梅, 赵金坤, 傅贵. 基于“2-4”模型的高处坠落事故行为原因研究[J]. 中国安全科学学报, 2019, 29(8): 23-28. doi: 10.16265/j.cnki.issn1003-3033.2019.08.004
	SUN Shimei, ZHAO Jinkun, FU Gui. Study on behavioral causes of falling accidents based on "2-4" model[J]. China Safety Science Journal, 2019, 29(8) : 23-28. doi: 10.16265/j.cnki.issn1003-3033.2019.08.004
[3]	王军武, 王梦雨, 刘登辉, 等. 基于HFACS-BN的地铁车站施工高处坠落可能性评价[J]. 中国安全科学学报, 2021, 31(6): 90-98. doi: 10.16265/j.cnki.issn 1003-3033.2021.06.012
	WANG Junwu, WANG Mengyu, LIU Denghui, et al. Evaluation of falling possibility at height in subway station construction based on HFACS-BN[J]. China Safety Science Journal, 2021, 31(6):90-98. doi: 10.16265/j.cnki.issn 1003-3033.2021.06.012
[4]	JEBELLI H, AHN C R, STENTZ T L. Fall risk analysis of construction workers using inertial measurement units: validating the usefulness of the postural stability metrics in construction[J]. Safety Science, 2016, 84: 161-170. doi: 10.1016/j.ssci.2015.12.012
[5]	KUSMAKAR S, MUTHUGANAPATHY R, YAN B, et al. Gaussian mixture model for the identification of psychogenic non-epileptic seizures using a wearable accelerometer sensor[C]. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2016:1006-1009.
[6]	麻文刚, 王小鹏, 吴作鹏. 基于人体姿态的PSO-SVM特征向量跌倒检测方法[J]. 传感技术学报, 2017, 30(10): 1504-1511.
	MA Wengang, WANG Xiaopeng, WU Zuopeng. PSO-SVM feature vector fall detection algorithm based on human postures[J]. Chinese Journal of Sensors and Actuators, 2017, 30(10): 1504-1511.
[7]	马英楠, 吕子阳, 高星, 等. 基于SVM的居家老人跌倒预测方法研究[J]. 中国安全科学学报, 2019, 29(6): 43-48. doi: 10.16265/j.cnki.issn1003-3033.2019.06.008
	MA Yingnan, LYU Ziyang, GAO Xing, et al. Research on fall prediction method for elderly at home based on SVM[J]. China Safety Science Journal, 2019, 29(6):43-48. doi: 10.16265/j.cnki.issn1003-3033.2019.06.008
[8]	YAN Xuzhong, LI Heng, ZHANG Hong, et al. Personalized method for self-management of trunk postural ergonomic hazards in construction rebar ironwork[J]. Advanced Engineering Informatics, 2018, 37: 31-41. doi: 10.1016/j.aei.2018.04.013
[9]	白正宗, 袁永博, 张明媛. 基于智能手机的建筑工人躯干姿势危险评估方法[J]. 中国安全科学学报, 2018, 28(1): 81-86. doi: 10.16265/j.cnki.issn1003-3033.2018.01.014
	BAI Zhengzong, YUAN Yongbo, ZHANG Mingyuan. Assessment of risk in construction workers' trunk posture using mobile sensor[J]. China Safety Science Journal, 2018, 28(1):81-86. doi: 10.16265/j.cnki.issn1003-3033.2018.01.014
[10]	YANG K, AHN C R, VURAN M C, et al. Semi-supervised near-miss fall detection for ironworkers with a wearable inertial measurement unit[J]. Automation in Construction, 2016, 68:194-202. doi: 10.1016/j.autcon.2016.04.007
[11]	FANG Yicho, DZENG Renjye. Accelerometer-based fall-portent detection algorithm for construction tiling operation[J]. Automation in Construction, 2017, 84: 214-230. doi: 10.1016/j.autcon.2017.09.015
[12]	ANTWI-AFARI M F, LI Heng. Fall risk assessment of construction workers based on biomechanical gait stability parameters using wearable insole pressure system[J]. Advanced Engineering Informatics, 2018, 38: 683-694. doi: 10.1016/j.aei.2018.10.002
[13]	ZHANG Mingyuan, CAO Tianzhuo, ZHAO Xuefeng. Using smartphones to detect and identify construction workers' near-miss falls based on ANN[J]. Journal of Construction Engineering and Management, 2019, 145(1):1-13.
[14]	ANTWI-AFARI M F, LI Heng, SEO J, et al. Automated detection and classification of construction workers' loss of balance events using wearable insole pressure sensors[J]. Automation in Construction, 2018, 96:189-199. doi: 10.1016/j.autcon.2018.09.010
[15]	DZENG Renjye, FANG Yicho, CHEN Ichung. A feasibility study of using smartphone built-in accelerometers to detect fall portents[J]. Automation in Construction, 2014, 38: 74-86. doi: 10.1016/j.autcon.2013.11.004
[16]	李文锋, 姚丙盟. 基于单三轴加速度传感器的人体活动状态识别[J]. 华中科技大学学报:自然科学版, 2016, 44(4):58-62.
	LI Wengfeng, YAO Bingmeng. Recognition of human activities based on single triaxial accelerometer[J]. Journal of Huazhong University of Science and Technology:Natural Science Edition, 2016, 44(4):58-62.
[17]	朱壮壮, 周治平. 高斯混合生成模型检测健康数据异常[J]. 计算机科学与探索, 2021(3):1-8.
	ZHU Zhuangzhuang, ZHOU Zhiping. Detection of health data based on gaussian mixture Generative model[J]. Journal of Frontiers of Computer Science and Technology, 2021(3):1-8.

高斯混合模型下建筑工人高空作业失稳检测方法

Instability detection method for construction workers working at altitude based on Gaussian mixture model

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 17

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王军武, 何娟娟, 宋盈辉, 刘一鹏, 陈兆, 郭婧怡. 基于RF-SFLA-SVM的装配式建筑高空作业工人不安全行为预警[J]. 中国安全科学学报, 2024, 34(3): 1-8.
[2]	倪国栋, 杨栎, 安瑶瑶, 郑雨茁. 不安全行为信息在建筑工人群体中的传染机制[J]. 中国安全科学学报, 2024, 34(1): 43-52.
[3]	倪国栋, 方亚琦, 张琦, 丁志华. 风险倾向对新生代建筑工人危险感知的影响机制[J]. 中国安全科学学报, 2023, 33(5): 221-229.
[4]	成连华, 赵旭东, 郝杰. 集成ISM与G1的建筑工人安全能力影响因素研究[J]. 中国安全科学学报, 2023, 33(4): 61-68.
[5]	胡飞翔, 周建亮, 林欣燕, 张家琪, 戴可欣. 情绪对建筑工人不安全行为影响的认知试验[J]. 中国安全科学学报, 2023, 33(4): 75-83.
[6]	赵航, 刘红勇, 郑俊巍. 非正式群体安全氛围对建筑工人安全行为的影响[J]. 中国安全科学学报, 2023, 33(10): 30-38.
[7]	刘素霞, 唐帅帅. 基于CA的建筑工人不安全行为传染机制[J]. 中国安全科学学报, 2023, 33(1): 24-31.
[8]	康梦月, 祁神军, 张云波, 陈梅. 精神支持对建筑工人消极情绪的干预机制[J]. 中国安全科学学报, 2023, 33(1): 56-63.
[9]	张萌, 韩豫, 刘泽锋. 深度学习下建筑工人高空安全防护装备检测方法[J]. 中国安全科学学报, 2022, 32(5): 140-146.
[10]	刘耀, 焦双健. ST-GCN在建筑工人不安全动作识别中的应用[J]. 中国安全科学学报, 2022, 32(4): 30-35.
[11]	王丹, 何洋. 群体视角下安全氛围对安全行为的跨层次影响[J]. 中国安全科学学报, 2022, 32(12): 25-31.
[12]	孙瑞山, 刘胤甫. 基于QAR数据的飞行员飞行操作风格研究[J]. 中国安全科学学报, 2022, 32(12): 63-69.
[13]	周建亮, 胡飞翔, 邢艳冬, 高嘉瑞. 工作压力、职业倦怠对建筑工人不安全行为的影响[J]. 中国安全科学学报, 2022, 32(11): 14-22.
[14]	刘晋, 沈浩, 刘卓慧, 陈思同, 熊志向, 潘川. 风险态度量表的中文版修订及应用[J]. 中国安全科学学报, 2022, 32(10): 25-30.
[15]	石娟, 常丁懿, 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型[J]. 中国安全科学学报, 2022, 32(1): 27-33.