Intelligent warning of risk during maintenance operations based on deep learning

doi:10.16265/j.cnki.issn1003-3033.2023.10.1744

Abstract

Abstract:

In order to improve the safety of the inspection and maintenance operation process in refining and chemical enterprises, a deep learning-based intelligent risk identification model was constructed by using the target detection technology. Firstly, a dynamic risk assessment model was established by combining the BN and fuzzy set theory. Secondly, a hierarchical dynamic early warning method was adopted to realize the intelligent monitoring and warning of the risk elements of the overhauling operation process; then the compressor overhauling operation process was taken as an example to identify the operation process risks by means of Failure Mode and Effect Analysis (FMEA) and hazard analysis of operation conditions, and then the intelligent identification model of risk based on deep learning was used for on-site monitoring of the operation process and identification of risk. Finally, the dynamic risk assessment of the operation process was carried out by using the method of combining the BN and the fuzzy set theory, and the grading warning method was used to realize intelligent monitoring and early warning of the risk of the operation process. The results show that the method effectively identify the risk factors in the compressor overhauling operation process, with an identification accuracy rate of 93%. Based on this, a dynamic risk assessment is carried out. When the probability of the event changed and exceeded the corresponding warning thresholds, alarms are issued based on the risk level to realize the intelligent monitoring of the risk elements.

Key words: deep learning, inspection operations, process risk, intelligent warning, Bayesian network(BN)

WANG Jinjiang, GUAN Pengting, CHEN Zhuo, GE Weifeng, JU Qian. Intelligent warning of risk during maintenance operations based on deep learning[J]. China Safety Science Journal, 2023, 33(10): 16-22.

Figures/Tables 9

Fig.1

Fig.2

Tab.1

Object detection model performance evaluation index system

指标体系	名称	公式
精度	P	P= $T P T P + F P$
精度	R	R= $T P T P + F N$
速度	每秒帧数(Frames Per Second, FPS)	—
速度	浮点运算量(Floating-point Operations Per Second, FLOPS)	—

Tab.1

Tab.2

Tab.3

Fig.3

Fig.4

Fig.5

Tab.4

References 16

[1]	刁俊武, 乔志强. 炼化企业生产智能化规划与实施路径[J]. 智能制造, 2021(3):66-69,74.
[2]	FIROOZSHAHI A, KIM S. Intelligent and innovative monitoring of water treatment plant in large gas refinery[C]. 2010 IEEE International Conference on Control Applications, 2010:269-273.
[3]	BRAGATTO P, ANSALDI S M, MENNUTI C. Improving safety of process plants, through smart systems for critical equipment monitoring[J]. Chemical Engineering Transactions (CET Journal), 2018, 67: 49-54.
[4]	李永帅, 陈庚晓. 控制阀智能诊断功能在炼化企业中的应用[J]. 仪器仪表用户, 2021, 28(7): 46-48, 34.
	LI Yongshuai, CHEN Gengxiao. Application of intelligent diagnosis function of control valve in refining and chemical enterprises[J]. Instrumentation, 2021, 28(7): 46-48, 34.
[5]	石凤勇, 党晓峰, 于彦明, 等. 智能模拟工厂技术在炼化装置建设阶段的应用[J]. 石油化工自动化, 2018, 54(2): 6-10.
	SHI Fengyong, DANG Xiaofeng, YU Yanming, et al. Application of intelligent simulated factory technology in the construction stage of refining and chemical plants[J]. Automation in Petro-Chemical Industry, 2018, 54(2): 6-10.
[6]	西门子(中国)有限公司. 西门子阀门状态监测 App助力中石化青岛炼化打造智能工厂[J]. 自动化博览, 2021, 38(12): 16-17.
[7]	郭鹏. 如何有效开展风险识别和控制[J]. 中国安全生产科学技术, 2009, 5(增1):163-164.
	GUO Peng. How to effectively carry out risk identification and control[J]. Journal of Safety Science and Technology, 2009, 5(S1):163-164.
[8]	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
[9]	范宗平. 浅析失效模式和影响分析(FMEA)在石油化工产品质量风险管理中的应用[J]. 当代化工研究, 2022(10):107-109.
	FAN Zongping. Application of failure mode and effects analysis(FMEA) in quality risk management of petrochemical products[J]. Modern Chemical Research, 2022(10):107-109.
[10]	殷勇. 石油炼化关键装置风险预警分级方法研究[D]. 北京: 中国地质大学(北京), 2009.
	YIN Yong. The study of grading methods of the risk of the key device of oil refining and chemical for early-warning system[D]. Beijing: China University of Geosciences (Beijing), 2009.
[11]	王孟飞, 屈英杰, 刘振乾. LEC法在建筑施工企业安全评价中的应用[J]. 安全, 2018, 39(8):31-33.
	WANG Mengfei, QU Yingjie, LIU Zhenqian. Application of LEC method in safety evaluation of construction enterprises[J]. Safety & Security, 2018, 39(8):31-33.
[12]	赵广玉. 石油化工装置检修施工安全管理措施[J]. 化工安全与环境, 2022, 35(30):18-21.
[13]	付苗苗, 邓淼磊, 张德贤. 深度神经网络图像目标检测算法综述[J]. 计算机系统应用, 2022, 31(7):35-45.
	FU Miaomiao, DENG Miaolei, ZHANG Dexian. Survey on deep neural network image target detection algorithms[J]. Computer Systems & Applications, 2022, 31(7):35-45.
[14]	陈科圻, 朱志亮, 邓小明, 等. 多尺度目标检测的深度学习研究综述[J]. 软件学报, 2021, 32(4):1201-1227.
	CHEN Keqi, ZHU Zhiliang, DENG Xiaoming, et al. Deep learning for multi-scale object detection: a survey[J]. Journal of Software, 2021, 32(4): 1201-1227.
[15]	KHAN A, SOHAIL A, ZAHOORA U, et al. A survey of the recent architectures of deep convolutional neural networks[J]. Artificial Intelligence Review, 2020, 53(8): 5455-5516. doi: 10.1007/s10462-020-09825-6
[16]	屈静, 张建彬, 李旭芳, 等. 基于贝叶斯网络的输油管道泄漏事故情景推演[J]. 中国安全科学学报, 2021, 31(1): 192-198. doi: 10.16265/j.cnki.issn1003-3033.2021.01.028
	QU Jing, ZHANG Jianbin, LI Xufang, et al. Deduction of leakage accident scenarios of oil pipelines based on Bayesian network[J]. China Safety Science Journal, 2021, 31(1): 192-198. doi: 10.16265/j.cnki.issn1003-3033.2021.01.028

序号	对象	标注	说明	应用
1	安全帽	helmet	穿戴规范	作业区域
2	吸烟	smoke	文明作业	作业区域
3	烟雾	smog	作业安全	作业区域
4	火焰	fire	作业安全	作业区域

对象	安全帽	吸烟	火焰	烟雾	总计
训练集	7 225	2 396	1 589	887	12 475
验证集	2 879	758	436	236	4 431
测试集	358	166	233	55	847
总计	10 462	3 320	2 258	1 178	17 753