A CNN Based Anomaly Detection Network for Utility Tunnel Fire Protection
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 d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Fire |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-6255/5/6/212 |
| _version_ | 1797458970447708160 |
|---|---|
| author | Haitao Bian Zhichao Zhu Xiaowei Zang Xiaohan Luo Min Jiang |
| author_facet | Haitao Bian Zhichao Zhu Xiaowei Zang Xiaohan Luo Min Jiang |
| author_sort | Haitao Bian |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T16:44:47Z |
| format | Article |
| id | doaj.art-381e82189f8a499c9fcdd78d2dae4d91 |
| institution | Directory Open Access Journal |
| issn | 2571-6255 |
| language | English |
| last_indexed | 2024-03-09T16:44:47Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fire |
| spelling | doaj.art-381e82189f8a499c9fcdd78d2dae4d912023-11-24T14:47:13ZengMDPI AGFire2571-62552022-12-015621210.3390/fire5060212A CNN Based Anomaly Detection Network for Utility Tunnel Fire ProtectionHaitao Bian0Zhichao Zhu1Xiaowei Zang2Xiaohan Luo3Min Jiang4College of Safety Science and Engineering, Nanjing Tech University, Nanjing 211816, ChinaCollege of Safety Science and Engineering, Nanjing Tech University, Nanjing 211816, ChinaCollege of Safety Science and Engineering, Nanjing Tech University, Nanjing 211816, ChinaCollege of Safety Science and Engineering, Nanjing Tech University, Nanjing 211816, ChinaKLA Corporation, Milpitas, CA 95035, USAFire 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.https://www.mdpi.com/2571-6255/5/6/212intelligent fire detectionanomaly detectionCNNurban utility tunnel |
| spellingShingle | Haitao Bian Zhichao Zhu Xiaowei Zang Xiaohan Luo Min Jiang A CNN Based Anomaly Detection Network for Utility Tunnel Fire Protection Fire intelligent fire detection anomaly detection CNN urban utility tunnel |
| title | A CNN Based Anomaly Detection Network for Utility Tunnel Fire Protection |
| title_full | A CNN Based Anomaly Detection Network for Utility Tunnel Fire Protection |
| title_fullStr | A CNN Based Anomaly Detection Network for Utility Tunnel Fire Protection |
| title_full_unstemmed | A CNN Based Anomaly Detection Network for Utility Tunnel Fire Protection |
| title_short | A CNN Based Anomaly Detection Network for Utility Tunnel Fire Protection |
| title_sort | cnn based anomaly detection network for utility tunnel fire protection |
| topic | intelligent fire detection anomaly detection CNN urban utility tunnel |
| url | https://www.mdpi.com/2571-6255/5/6/212 |
| work_keys_str_mv | AT haitaobian acnnbasedanomalydetectionnetworkforutilitytunnelfireprotection AT zhichaozhu acnnbasedanomalydetectionnetworkforutilitytunnelfireprotection AT xiaoweizang acnnbasedanomalydetectionnetworkforutilitytunnelfireprotection AT xiaohanluo acnnbasedanomalydetectionnetworkforutilitytunnelfireprotection AT minjiang acnnbasedanomalydetectionnetworkforutilitytunnelfireprotection AT haitaobian cnnbasedanomalydetectionnetworkforutilitytunnelfireprotection AT zhichaozhu cnnbasedanomalydetectionnetworkforutilitytunnelfireprotection AT xiaoweizang cnnbasedanomalydetectionnetworkforutilitytunnelfireprotection AT xiaohanluo cnnbasedanomalydetectionnetworkforutilitytunnelfireprotection AT minjiang cnnbasedanomalydetectionnetworkforutilitytunnelfireprotection |