基于OCSVM的隧道人员安全检测技术的研究与应用

荣明; 陈英杰; 黄超; 王大川; 原俊峰

doi:10.3973/j.issn.2096-4498.2021.12.013

隧道建设 >

2021 , Vol. 41 >Issue 12: 2122 - 2132

DOI: https://doi.org/10.3973/j.issn.2096-4498.2021.12.013

研究与探索

基于OCSVM的隧道人员安全检测技术的研究与应用

荣明 ,
陈英杰 ,
黄超 ,
王大川 ,
原俊峰

展开

（1. 新疆农业大学水利与土木工程学院，新疆乌鲁木齐 830052； 2. 新疆工程学院安全科学与工程学院， 新疆乌鲁木齐 830052； 3. 新疆兵团水利水电工程集团有限公司，新疆乌鲁木齐 830000）

荣明(1987—)，男，山西太原人，新疆农业大学工程管理专业在读硕士，研究方向为隧道施工人员安全管理。 E-mail： 515323151@qq.com。*通信作者：黄超， E-mail： 691911591@qq.com。

网络出版日期: 2022-01-05

基金资助

国家自然科学基金（51668063）；水利重点科学基金（SLXK2019-09）　

收起

Research and Application of Personnel Safety Detection Technology for Tunnels Based on One-Class Support Vector Machine

RONG Ming ,
CHEN Yingjie ,
HUANG Chao ,
WANG Dachuan ,
YUAN Junfeng

Expand

（1. College of Hydraulic and Civil Engineering, Xinjiang Agricultural University, Urumqi 830052, Xinjiang, China;
2. College of Safety Science and Engineering, Xinjiang Institute of Engineering, Urumqi 830052, Xinjiang, China;
3. Xinjiang Bingtuan Water Conservancy and Hydropower Construction Engineering Group Co., Ltd., Urumqi 830000, Xinjiang, China)

Online published: 2022-01-05

Fold

摘要

隧道人员安全状态的判断主要通过收集施工人员的体征和洞内环境数据，对异常状态的预警通常需要专业工作人员在短时间内迅速作出判断，运维成本高且工作效率较低。针对此现象，提出一种基于单分类支持向量机的人员安全状态检测以及预警模型。首先，通过在现场部署传感器设备，获取实际隧道施工场景安全状态下的数据，并构建OCSVM模型进行异常状态预测；接着，保留模型进行预警状态测试，从工程实例中收集相关环境数据以及施工人员体征数据，并进行横向不同参数模型试验和纵向不同预警状态比例数据试验；最后，评估模型对人员信息安全状态判断的性能。试验结果表明，人员安全状态预警准确率达到90%以上。

关键词： 单分类支持向量机; 人员安全状态检测; 隧道施工; OCSVM模型

本文引用格式

荣明 , 陈英杰 , 黄超 , 王大川 , 原俊峰 . 基于OCSVM的隧道人员安全检测技术的研究与应用[J]. 隧道建设, 2021 , 41(12) : 2122 -2132 . DOI: 10.3973/j.issn.2096-4498.2021.12.013

Abstract

The safety status of tunnel construction workers is mainly judged through workers′ physical signs and cave environment data, and the early warning of the abnormal status usually requires professional staff to make a rapid judgment in a short time, which is costly and inefficient in operation and maintenance. To address this issue, a oneclass support vector machinebased personnel safety status detection and early warning model is proposed. First, data from the actual tunnel construction scenario are collected using sensor devices deployed in the field, and a oneclass support vector machine model for abnormal state prediction is built. Second, the model is retained for early warning state testing, and relevant environmental data as well as construction personnel physical signs data are collected from engineering examples. In addition, horizontal different parameter model experiments and vertical different early warning state proportional data experiments are conducted to evaluate the model′s performance for personnel information security state judgment. The experimental results show that the accuracy rate of personnel security status early warning reaches more than 90%.

Key words： one-class support vector machine; personnel security status detection; tunnel construction; one-class support vector machine model

Options

文章导航

〈

〉

模态框（Modal）标题

摘要

本文引用格式

Abstract