Gas station unsafe behavior detection based on YOLO-V3 algorithm

doi:10.16265/j.cnki.issn1003-3033.2023.02.0298

Abstract

Abstract:

In order to control the fire and explosion risk target of gas station, an unsafe behavior detection model of gas station based on YOLO-V3 algorithm was proposed by combining accident statistics and fault tree analysis,. Firstly, on the basis of collecting 90 gas station fire and explosion accidents, the ignition sources of gas station fire and explosion accidents were statistically analyzed. Secondly,. the fire and explosion fault tree of gas station was constructed, the structural importance of each basic event was calculated, and the unsafe behavior with high risk of gas station was determined. Then, the image data of unsafe behavior of gas stations were collected by field collection and simulation, and the image data set of unsafe behavior of gas stations was constructed by data enhancement method. Finally, based on the deep learning method, the unsafe behavior detection model of gas station was constructed, and the final model was obtained after 1000 training iterations. The results show that the unsafe behaviors that cause fire and explosion accidents in gas stations mainly include smoking, calling and so on. The average detection accuracy of the trained detection model for smoking, calling and normal behavior detection categories on the test set is 67%, 85% and 77%, respectively, and the average detection accuracy of the model is 84%.

Key words: YOLO-V3 algorithm, gas station, fault tree, unsafe behavior, fire and explosion, target detection

CHANG Jie, ZHANG Guowei, CHEN Wenjiang, YUAN Diping, WANG Yongsheng. Gas station unsafe behavior detection based on YOLO-V3 algorithm[J]. China Safety Science Journal, 2023, 33(2): 31-37.

Figures/Tables 9

Tab.1

Tab.2

Fig.1

Tab.3

Basic event structure importance

结构重要度等级	基本事件	结构重要度系数
I	X₉, X₁₀, $X 1 1$ , X₁₂, X₁₃, X₁₄, X₁₅, X₁₆, X₁₇, X₂₀, X₂₁, X₂₂, X₃	0.035~0.043
II	X₁, X₄, X₈, X₂₃, X₂₄, X₂₅, X₂₆, X₂₇, X₂₈, X₂, X₅, X₆, X₇, X₃₁, X₃₂	0.022~0.035
III	X₁₈, X₁₉, X₂₉, X₃₀	0~0.022

Tab.3

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

References 17

[1]	吴耀男, 林雷, 任新温, 等. 一种基于逻辑结构数的改进型FMEA方法[J]. 中国安全科学学报, 2021, 31(10):97-104. doi: 10.16265/j.cnki.issn1003-3033.2021.10.014
	WU Yaonan, LIN Lei, REN Xinwen, et al. An improved FMEA method based on logical structure number[J]. China Safety Science Journal, 2021, 31(10):97-104. doi: 10.16265/j.cnki.issn1003-3033.2021.10.014
[2]	CASAMIRRA M, CASTIGLIA F, GIARDINA M, et al. Safety studies of a hydrogen refuelling station: determination of the occurrence frequency of the accidental scenarios[J]. International Journal of Hydrogen Energy, 2009, 34(14):5846-5854. doi: 10.1016/j.ijhydene.2009.01.096
[3]	桑海泉, 谷海波, 康荣学. 加油站安全监控预警与应急管理系统[J]. 中国公共安全:学术版, 2010(4):55-60.
	SANG Haiquan, GU Haibo, KANG Rongxue. Safety monitoring and early-warning and emergency management system of petrol station[J]. China Public Security, 2010(4):55-60.
[4]	HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507. doi: 10.1126/science.1127647 pmid: 16873662
[5]	HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554. doi: 10.1162/neco.2006.18.7.1527 pmid: 16764513
[6]	LIN Tsungyi, MAIRE M, BELONGIE S, et al. Microsoft coco: common objects in context[C]. Proceeding in European Conference on Computer Vision, 2014:740-755.
[7]	DENG Jia, DONG Wei, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2009: 248-255.
[8]	林俊, 党伟超, 潘理虎, 等. 基于YOLO的安全帽检测方法[J]. 计算机系统应用, 2019, 28(9):174-179.
	LIN Jun, DANG Weichao, PAN Lihu, et al. Safety helmet detection based on YOLO[J]. Computer Systems & Applications, 2019, 28(9):174-179.
[9]	LI Yange, WEI Han, HAN Zheng, et al. Deep learning-based safety helmet detection in engineering management based on convolutional neural networks[J]. Advances in Civil Engineering, 2020:DOI: 10.1155/2020/9703560.
[10]	张明媛, 曹天卓, 赵雪峰. 基于ANN识别施工人员跌落险兆事故的研究[J]. 安全与环境学报, 2018, 18(5):1703-1710.
	ZHANG Mingyuan, CAO Tianzhuo, ZHAO Xuefeng. Approach to detecting and identifying the near-miss falls of the construction workers via the ANN system[J]. Journal of Safety and Environment, 2018, 18(5):1703-1710.
[11]	ZHAO Rentao, WANG Mengyi, ZHAI Zilong, et al. Indoor smoking behavior detection based on YOLO-V3-tiny[C]. 2019 Chinese Automation Congress, 2019:3477-3481.
[12]	郑志强. 基于卷积神经网络的目标检测算法研究与应用[D]. 长春: 长春理工大学, 2019.
	ZHENG Zhiqiang. Research and application of target detection algorithms based on convolutional neural network[D]. Changchun: Changchun University of Science and Technology, 2019.
[13]	REDMON J, FARHADI A. YOLO-V3: an incremental improvement[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2018:89-95.
[14]	WANG Haikuan, HU Zhaoyan, GUO Yuanjun, et al. A real-time safety helmet wearing detection approach based on CSYOLO-V3[J]. Applied Sciences, 2020, 10(19):6732-6746. doi: 10.3390/app10196732
[15]	林柏泉, 周延, 刘贞堂. 安全系统工程[M].徐州. 中国矿业大学出版社, 2005:23-24.
[16]	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]. IEEE Conference on Computer Vision and Pattern Recognition, 2016:779-788.
[17]	EVERINGHAM M, ESLAMI S M A, VAN G L, et al. The pascal visual object classes challenge: a retrospective[J]. International Journal of Computer Vision, 2015, 111(1):98-136. doi: 10.1007/s11263-014-0733-5

点火源	事故起数
违章爆炸物爆炸	1
继电器漏电	1
使用明火	2
车辆撞向加油站产生火源	3
加油时启动汽车产生火源	3
打电话产生火源	3
静电	7
拉断油管产生火源	8
违章操作产生火源	17
抽烟产生火源	17
车辆自燃	28
合计	90

符号	事件名称	符号	事件名称	符号	事件名称
T	火灾爆炸事故	M₁₈	人体产生静电	X₁₆	油品摩擦容器
M₁	火源	M₁₉	拉断油管产生火花	X₁₇	油品搅动产生静电
M₂	燃爆物	M₂₀	车辆失控撞向加油站产生火花	X₁₈	化纤衣物摩擦
M₃	明火	X₁	抽烟	X₁₉	作业中接触导体
M₄	电火花	X₂	车辆中爆炸物爆炸	X₂₀	加油时油品喷溅
M₅	撞击火花	X₃	油罐区漏油	X₂₁	加油时油箱满溢
M₆	静电火花	X₄	打电话	X₂₂	车辆油管渗漏油品
M₇	油品	X₅	加油站电路漏电	X₂₃	车辆内可燃装饰物
M₈	油蒸气	X₆	加油时启动车辆产生火花	X₂₄	车辆内油品
M₉	车辆自燃	X₇	使用非防爆工具	X₂₅	油蒸气浓度较高
M₁₀	设备静电放电	X₈	接触其他可燃物	X₂₆	没有静电接地装置
M₁₁	人体静电放电	X₉	加油机管路漏油	X₂₇	静电接地装置损坏
M₁₂	加油机加油时泄漏油品	X₁₀	加油机油枪漏油	X₂₈	静电接地不符合
M₁₃	车辆加油时泄漏油品	X₁₁	加油机泄漏油气	X₂₉	加油结束后未拔油枪
M₁₄	点火源	X₁₂	汽车泄漏油气	X₃₀	启动车辆前未检查油枪状态
M₁₅	可燃物	X₁₃	储罐泄漏油气	X₃₁	刹车失灵
M₁₆	静电聚集	X₁₄	车辆电路老化	X₃₂	司机误操作
M₁₇	设备接地不良	X₁₅	加油时车辆开启