基于消防大数据的电气火灾风险预测预警方法

贺胜; 疏学明; 胡俊; 张雷; 张伽; 张嘉乐; 周扬

doi:10.16511/j.cnki.qhdxxb.2024.26.002

清华大学学报（自然科学版） >

2024 , Vol. 64 >Issue 3: 478 - 491

DOI: https://doi.org/10.16511/j.cnki.qhdxxb.2024.26.002

公共安全科学与技术

基于消防大数据的电气火灾风险预测预警方法

贺胜 ,
疏学明 ,
胡俊 ,
张雷 ,
张伽 ,
张嘉乐 ,
周扬

展开

1. 清华大学安全科学学院, 北京 100084;
2. 清华大学城市综合应急科学北京市重点实验室, 北京 100084;
3. 北京师范大学教育部巨灾模拟与系统性风险应对国际合作联合实验室, 珠海 519087;
4. 北京师范大学国家安全与应急管理学院, 珠海 519087

贺胜(1995—),男,博士研究生。

收稿日期: 2023-07-22

网络出版日期: 2024-03-06

基金资助

国家电网公司总部科技项目(5400-202118164A-0-0-00)

收起

Prediction and early-warning method of electrical fire risk based on fire-fighting big data

HE Sheng ,
SHU Xueming ,
HU Jun ,
ZHANG Lei ,
ZHANG Jia ,
ZHANG Jiale ,
ZHOU Yang

Expand

1. School of Safety Science, Tsinghua University, Beijing 100084, China;
2. Beijing Key Laboratory of City Integrated Emergency Response Science, Tsinghua University, Beijing 100084, China;
3. Joint International Research Laboratory of Catastrophe Simulation and Systemic Risk Governance of Ministry of Education, Beijing Normal University, Zhuhai 519087, China;
4. School of National Safety and Emergency Management, Beijing Normal University, Zhuhai 519087, China

Received date: 2023-07-22

Online published: 2024-03-06

Fold

摘要

为实现电气火灾风险提前动态感知,该文以渐变态电气火灾为例,研究了基于循环神经网络(recurrent neural network,RNN)模型的电气线路超温故障火灾风险预警方法,采用真实电气火灾案例数据对模型进行训练,通过挖掘电气线路温度变化的周期特性和瞬时温升故障特征对线路温度进行预测。采用温度二阶残差正态分布模型对温度预测结果进行概率分布范围修正。基于温度预测的累积概率分布提出预警分位,通过比较实际温度与预警分位的关系发现电气线路火灾风险定量表征的依据,实现电气线路火灾风险提前动态感知,最后提出采用“前端探测+算法牵引”的模式解决当前电气火灾防控技术难题。

关键词： 电气火灾; 温度预测; 概率分布; 风险预警; 预警分位; 数据挖掘

本文引用格式

贺胜 , 疏学明 , 胡俊 , 张雷 , 张伽 , 张嘉乐 , 周扬 . 基于消防大数据的电气火灾风险预测预警方法[J]. 清华大学学报（自然科学版）, 2024 , 64(3) : 478 -491 . DOI: 10.16511/j.cnki.qhdxxb.2024.26.002

Abstract

[Objective] Risk quantification is crucial in risk assessment of accidents or disasters. This study aims to investigate the risk quantification method utilized in over-temperature faults in electrical circuits. The existing technologies of the abovementioned method are summarized in electrical and fire signals of disaster early warning. Thus, a new method based on the fire big data is proposed. [Methods] Different frequency electrical parameters are collected by the detector arranged at the front end and transmitted in real time to the fire big data to mine the influencing factors and changing patterns of electrical circuit temperature based on the deep-learning method. Subsequently, the probability distribution of temperature is determined statically, and risk is described by comparison of prediction temperature in different cumulative probabilities with actual temperature. To predict the electrical circuit temperature, a recurrent neural network (RNN) is utilized to model temperature prediction. The input parameters are voltage, current, temperature, and residual current. Among the parameters, there are two data sources for the model: one is real electrical fire data, 6 min^-1, used to learn the periodic law of temperature increase in electrical circuits of RNN for low-frequency data (LF-RNN), and the other is experimental data based on simulated fault of the temperature increase in electrical circuits. This experiment is implemented in three-phase resistive electrical circuits. Exceeding rated current is utilized to produce temperature rising. Meanwhile, electrical parameters are collected to study the law of temperature oscillation of RNN for high-frequency data (HF-RNN). Among these electrical parameters, the sampling frequency of voltage, current, and residual current is 50 kHz, but 1 Hz for temperature exceptionally. The optimization method, hyperparameter traversal, aims to minimize the loss function and root mean square error; thus, temperature prediction in electrical circuits is preliminarily applied. To increase the accuracy of the prediction model and elucidate the relationship between fire risk and prediction result, a temperature probability prediction model is established based on its second-order residual normal distribution. The error and its reducing methods are analyzed, and the relationship between prediction error and temperature mutation is determined. [Results] The results demonstrated that temperature mutation within three window lengths had a remarkable linear correction effect with temperature prediction error; moreover, the second-order residual approximately followed a normal distribution. The upper and lower limited of temperature prediction confidence intervals with different significant levels (α=0.02, 0.04, 0.06,…, 0.98) can be computed by interval estimation, which had a one-to-one correspondence with temperature prediction accumulate probability (1-α/2) and (α/2). The results revealed that the cumulative distribution probability 1% prediction curve and 99% prediction curve appeared to have a fine coverage effect on the actual temperature. With the aim of measuring temperature prediction probability distribution with electrical fire risk, the concept of “early-warning quantile” similar to cumulative distribution probability, was proposed. The ability to predict temperature was established using different “early-warning quantile curves” and confirmed through 2 943 sets of real electrical fire scene data. The results demonstrated that early-warning quantiles in the range of 10%-30% could overlap the majority of the actual temperature data, and the higher the quantile of the curve was, the higher the frequency of overestimating the temperature was. [Conclusions] To summarize, when the temperature in electrical circuits suddenly increases, there is a substantial upward trend in the early-warning quantile of the actual temperature. Thus, the use of LF-RNN and HF-RNN can timely and accurately predict the temperature probability distribution to characterize fire risks in electrical circuits so that early dynamic perception of fire risk is realized.

Key words： electrical fire; temperature prediction; probability distribution; risk early-warning; early-warning quantile; data mining

参考文献

[1] 张玉涛, 马婷, 林姣, 等. 2007-2016年全国重特大火灾事故分析及时空分布规律[J]. 西安科技大学学报, 2017, 37(6):829-836. ZHANG Y T, MA T, LIN J, et al. Analysis of fire incidents and characteristics of spatio-temporal distributions for serious fires from 2007 to 2016 in China[J]. Journal of Xi'an University of Science and Technology, 2017, 37(6):829-836. (in Chinese)
[2] 杨凯, 张认成, 杨建红, 等. 基于分形维数和支持向量机的串联电弧故障诊断方法[J]. 电工技术学报, 2016, 31(2):70-77. YANG K, ZHANG R C, YANG J H, et al. Series arc fault diagnostic method based on fractal dimension and support vector machine[J]. Transactions of China Electrotechnical Society, 2016, 31(2):70-77. (in Chinese)
[3] 郑天芳, 曲娜, 张帅, 等. 基于AHP-熵权法的高层建筑电气火灾风险评价[J]. 沈阳航空航天大学学报, 2022, 39(1):69-76. ZHENG T F, QU N, ZHANG S, et al. Electrical fire risk assessment of high-rise buildings based on AHP-entropy weight method[J]. Journal of Shenyang Aerospace University, 2022, 39(1):69-76. (in Chinese)
[4] 疏学明, 颜峻, 胡俊, 等. 基于Bayes网络的建筑火灾风险评估模型[J]. 清华大学学报(自然科学版), 2020, 60(4):321-327. SHU X M, YAN J, HU J, et al. Risk assessment model for building fires based on a Bayesian network[J]. Journal of Tsinghua University (Science and Technology), 2020, 60(4):321-327. (in Chinese)
[5] 疏学明, 贺胜, 胡俊, 等. 电气火灾预警系统、方法、电子设备及存储介质:CN115171319A[P]. 2022-10-11. SHU X M, HE S, HU J, et al. Electrical fire warning systems, methods, electronic devices, and storage media:CN115171319A[P]. 2022-10-11. (in Chinese)
[6] SU L, YANG F, SHEN Y, et al. Electrical fire risk assessment of high-rise buildings based on hybrid decision model considering asymmetric proximity[J]. Fire and Materials, 2023, 47(3):285-293.
[7] 昝浩, 王欣, 刘故帅, 等. 以智能预警为导向的变电站电气火灾防控管理[J]. 山东电力技术, 2020, 47(5):51-55. ZAN H, WANG X, LIU G S, et al. Intelligent fire prevention and control for substation electrical fire prevention and control[J]. Shandong Electric Power, 2020, 47(5):51-55. (in Chinese)
[8] 孙世梅, 耿晓帅, 傅贵. 基于"2-4"模型的建筑电气火灾事故直接原因研究[J]. 中国安全科学学报, 2020, 30(4):93-99. SUN S M, GENG X S, FU G. Study on direct causes of electrical fire accidents in buildings based on "2-4" model[J]. China Safety Science Journal, 2020, 30(4):93-99. (in Chinese)
[9] LEE M. Subjective response to the conditions of audible fire alarm signals through a jury evaluation test[J]. Fire Technology, 2022, 58(2):1039-1060.
[10] 季力. 基于STM32芯片的电参数测量与数据传输[J]. 自动化与仪器仪表, 2010(3):137-139. JI L. Power measurement and data transmission based on STM32 chip[J]. Automation & Instrumentation, 2010(3):137-139. (in Chinese)
[11] 谢春红. 火灾自动报警系统中的探测器分析[J]. 电子技术, 2022, 51(10):216-217. XIE C H. Analysis of detector in automatic fire alarm system[J]. Electronic Technology, 2022, 51(10):216-217. (in Chinese)
[12] GOTTUK D T, PEATROSS M J, ROBY R J, et al. Advanced fire detection using multi-signature alarm algorithms[J]. Fire Safety Journal, 2002, 37(4):381-394.
[13] 陈涛, 袁宏永, 苏国锋, 等. 基于CCD图像的火灾空间定位方法[J]. 光学技术, 2003, 29(3):292-294. CHEN T, YUAN H Y, SU G F, et al. Automatic fire location by CCD images in big space[J]. Optical Technology, 2003, 29(3):292-294. (in Chinese)
[14] 王振宇. 电气火灾短路故障点与起火点分析[J]. 数字通信世界, 2021(6):263-264. WANG Z Y. Analysis of short-circuit fault points and ignition points in electrical fires[J]. Digital Communication World, 2021(6):263-264. (in Chinese)
[15] ZHANG J, HUANG L D, CHEN T, et al. Simulation based analysis of electrical fire risks caused by poor electric contact between plug and receptacle[J]. Fire Safety Journal, 2021, 126:103434.
[16] 邓文东, 袁凡宁, 李均, 等. 核磁共振原理的交联聚乙烯电缆热老化行为分析[J]. 重庆大学学报, 2014, 37(8):41-45. DENG W D, YUAN F N, LI J, et al. Thermal aging behavior of XLPE cable based on the nuclear magnetic resonance theory[J]. Journal of Chongqing University, 2014, 37(8):41-45. (in Chinese)
[17] 雷鸣, 刘刚, 邱景生, 等. 单芯电缆线芯温度的非线性有限元法实时计算[J]. 电网技术, 2011, 35(11):163-168. LEI M, LIU G, QIU J S, et al. Real-time core temperature calculation of single-core cable by nonlinear finite element method[J]. Power System Technology, 2011, 35(11):163-168. (in Chinese)
[18] 黄雄峰, 徐彬昭, 张宇娇, 等. 基于参数拟合技术直埋电缆的缆芯暂态温度计算[J]. 中国电力, 2016, 49(10):60-66. HUANG X F, XU B Z, ZHANG Y J, et al. Transient temperature calculation of buried cable core based on parameter fitting of thermal circuit[J]. Electric Power, 2016, 49(10):60-66. (in Chinese)
[19] 余琼芳, 胡亚倩, 杨艺. 低压交流串联故障电弧检测概述[J]. 电器与能效管理技术, 2020(1):24-30.YU Q F, HU Y Q, YANG Y. A review of low voltage AC series arc fault detection[J]. Electrical & Energy Management Technology, 2020(1):24-30. (in Chinese)
[20] ROSE-PEHRSSON S L, SHAFFER R E, HART S J, et al. Multi-criteria fire detection systems using a probabilistic neural network[J]. Sensors and Actuators B:Chemical, 2000, 69(3):325-335.
[21] 张刚, 张岳, 黄国平, 等. 基于多传感器信息融合的电气火灾预警研究[J]. 能源与环保, 2017, 39(10):80-85. ZHANG G, ZHANG Y, HUANG G P, et al. Research on electrical fire alarm based on multi-sensor information fusion[J]. China Energy and Environmental Protection, 2017, 39(10):80-85. (in Chinese)
[22] 范维澄, 刘奕, 翁文国. 公共安全科技的"三角形"框架与"4+1"方法学[J]. 科技导报, 2009, 27(6):3. FAN W C, LIU Y, WENG W G. Triangular framework and "4+1" methodology for public security science and technology[J]. Science & Technology Review, 2009, 27(6):3. (in Chinese)
[23] 罗东豪, 龚仕伟. 基于模糊分析法的住宅建筑电气安全评估探究[J]. 建筑电气, 2021, 40(7):29-32. LUO D H, GONG S W. Study on fuzzy AHP based electric safety evaluation for residential buildings[J]. Building Electricity, 2021, 40(7):29-32. (in Chinese)
[24] 余琼芳. 基于小波分析及数据融合的电气火灾预报系统及应用研究[D]. 秦皇岛:燕山大学, 2013. YU Q F. Research on electrical fire forecast system and its application based on wavelet analysis and data fusion[D]. Qinhuangdao:Yanshan University, 2013. (in Chinese)
[25] 赵月爱, 郭兴原. 基于多源数据协同感知的电气火灾预警算法研究[J]. 太原理工大学学报, 2021, 52(6):907-912. ZHAO Y A, GUO X Y. Research on electrical fire warning algorithm based on multi-source data collaborative sensing[J]. Journal of Taiyuan University of Technology, 2021, 52(6):907-912. (in Chinese)
[26] 谢正荣, 单立辉, 时庆兵, 等. 电气火灾早期预警及监测前沿技术探讨[J]. 建筑电气, 2019, 38(8):39-44. XIE Z R, SHAN L H, SHI Q B, et al. Discussion on advance technology of early warning and monitoring for electrical fire[J]. Building Electricity, 2019, 38(8):39-44. (in Chinese)
[27] 周克良, 郭金妹, 聂磊. 基于STM32F电气火灾无线红外测温系统的设计与实现[J]. 计算机测量与控制, 2014, 22(10):3108-3110. ZHOU K L, GUO J M, NIE L. Design and implementation of electrical fire wireless infrared temperature measurement system based on STM32F[J]. Computer Measurement & Control, 2014, 22(10):3108-3110. (in Chinese)
[28] PENG T, KE W. Urban fire emergency management based on big data intelligent processing system and Internet of Things[J]. Optik, 2023, 273:170433.
[29] YUDAEV I V. Analysis of variation in circuit parameters for substitution of weed plant tissue under electric impulse action[J]. Surface Engineering and Applied Electrochemistry, 2019, 55(2):219-224.
[30] NAN Z J, ORABI M A, HUANG X Y, et al. Structural-fire responses forecasting via modular AI[J]. Fire Safety Journal, 2023, 140:103863.
[31] LI Y X, HE B B. A semi-empirical retrieval method of above-ground live forest fuel loads by combining SAR and optical data[J]. Remote Sensing, 2023, 15(1):5.
[32] YANG Q S, HUANG G Q, LI T, et al. A novel short-term wind speed prediction method based on hybrid statistical-artificial intelligence model with empirical wavelet transform and hyperparameter optimization[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2023, 240:105499.
[33] YU F, CHEN M H. Second-order error analysis for fractal mobile/immobile allen-cahn equation on graded meshes[J]. Journal of Scientific Computing, 2023, 96(2):49.
[34] 邓雪, 李家铭, 曾浩健, 等. 层次分析法权重计算方法分析及其应用研究[J]. 数学的实践与认识, 2012, 42(7):93-100. DENG X, LI J M, ZENG H J, et al. Research on computation methods of AHP wight vector and its applications[J]. Mathematics in Practice and Theory, 2012, 42(7):93-100. (in Chinese)
[35] 邓建国, 张素兰, 张继福, 等. 监督学习中的损失函数及应用研究[J]. 大数据, 2020, 6(1):60-80. DENG J G, ZHANG S L, ZHANG J F, et al. Loss function and application research in supervised learning[J]. Big Data Research, 2020, 6(1):60-80. (in Chinese)
[36] TANG W H, LI W W, ZHENG J H, et al. A composite voltage stability index for integrated energy systems based on L-index and the minimum eigenvalue of reduced Jacobian matrix[J]. International Journal of Electrical Power & Energy Systems, 2022, 141:108136.
[37] XU B, WANG D, QI H. Comparative studies between the Bayesian estimation and the maximum likelihood estimation of the parameter of the uniform distribution[J]. International Journal of Modelling, Identification and Control, 2021, 35(3):211-216.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献

访问统计