A CNN Based Anomaly Detection Network for Utility Tunnel Fire Protection

被引:19
作者
Bian, Haitao [1 ,2 ]
Zhu, Zhichao [1 ]
Zang, Xiaowei [1 ,2 ]
Luo, Xiaohan [1 ]
Jiang, Min [3 ]
机构
[1] Nanjing Tech Univ, Coll Safety Sci & Engn, Nanjing 211816, Peoples R China
[2] Jiangsu Key Lab Hazardous Chem Safety & Control, Nanjing 211816, Peoples R China
[3] KLA Corp, Milpitas, CA 95035 USA
来源
FIRE-SWITZERLAND | 2022年 / 5卷 / 06期
基金
中国国家自然科学基金;
关键词
intelligent fire detection; anomaly detection; CNN; urban utility tunnel;
D O I
10.3390/fire5060212
中图分类号
Q14 [生态学(生物生态学)];
学科分类号
071012 ; 0713 ;
摘要
Fire accident is one of the significant threats to the urban utility tunnel (UUT) during operation, and the emergency response is challenging due to the compact tunnel structure and potential hazard sources involved. Traditional fire detection techniques are reviewed in this study, and it has been determined that their performance cannot satisfy the requirements for early fire incident detection. Integrating advanced sensing technologies and data-driven anomaly detection has recently been regarded as a feasible solution for intelligent safety system implementation. This article proposed an approach that utilized a fiber-optic distributed temperature sensing (FO-DTS) system and deep anomaly detection models to monitor the fire exotherm during the early stages of accidents. The variable fire exotherm is simulated with an embedded-system controlled electrical heating platform. Moreover, autoencoder (AE) based and convolutional neural network (CNN) based methods have been designed for anomaly detection. The temperature data collected from the FO-DTS in the experiment was employed as the training set for the data-driven models. Furthermore, the anomaly detection models were tested, and the results showed that the proposed CNN model can achieve a higher accuracy rate in detecting the simulated fire exotherm.
引用
收藏
页数:12
相关论文
共 32 条
[1]   Distributed temperature measurements using optical fibre technology in an underground mine environment [J].
Aminossadati, Sailed M. ;
Mohammed, Nayeemuddin M. ;
Shemshad, Javad .
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY, 2010, 25 (03) :220-229
[2]   OPTICAL-TIME DOMAIN REFLECTOMETRY IN A SINGLE-MODE FIBER [J].
AOYAMA, KI ;
NAKAGAWA, K ;
ITOH, T .
IEEE JOURNAL OF QUANTUM ELECTRONICS, 1981, 17 (06) :862-868
[3]   Rule extraction in unsupervised anomaly detection for model explainability: Application to OneClass SVM [J].
Barbado, Alberto ;
Corcho, Oscar ;
Benjamins, Richard .
EXPERT SYSTEMS WITH APPLICATIONS, 2022, 189
[4]   Intelligent and vision-based fire detection systems: A survey [J].
Bu, Fengju ;
Gharajeh, Mohammad Samadi .
IMAGE AND VISION COMPUTING, 2019, 91
[5]   PCA-based multivariate statistical network monitoring for anomaly detection [J].
Camacho, Jose ;
Perez-Villegas, Alejandro ;
Garcia-Teodoro, Pedro ;
Macia-Fernandez, Gabriel .
COMPUTERS & SECURITY, 2016, 59 :118-137
[6]   Development of a machine-learning approach for identifying the stages of fire development in residential room fires [J].
Fang, Hongqiang ;
Lo, S. M. ;
Zhang, Yunjie ;
Shen, Yixin .
FIRE SAFETY JOURNAL, 2021, 126
[7]   Detection of coal fire by deep learning using ground penetrating radar [J].
Gao, Rongxiang ;
Zhu, Hongqing ;
Liao, Qi ;
Qu, Baolin ;
Hu, Lintao ;
Wang, Haoran .
MEASUREMENT, 2022, 201
[8]  
Geetha S., 2021, MACHINE VISION BASED, V57
[9]   Flame and smoke detection method for early real-time detection of a tunnel fire [J].
Han, Dongil ;
Lee, Byoungmoo .
FIRE SAFETY JOURNAL, 2009, 44 (07) :951-961
[10]  
Ioffe Sergey, 2015, Proceedings of Machine Learning Research, V37, P448, DOI DOI 10.48550/ARXIV.1502.03167