Acoustic Based Fire Event Detection System in Underground Utility Tunnels
Underground utility tunnels (UUTs) are convenient for the integrated management of various infrastructure facilities. They ensure effective control of underground facilities and reduce occupied space. However, aging UUTs require effective management and preventive measures for fire safety. The funda...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Fire |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-6255/6/5/211 |
| _version_ | 1797600145592811520 |
|---|---|
| author | Byung-Jin Lee Mi-Suk Lee Woo-Sug Jung |
| author_facet | Byung-Jin Lee Mi-Suk Lee Woo-Sug Jung |
| author_sort | Byung-Jin Lee |
| collection | DOAJ |
| description | Underground utility tunnels (UUTs) are convenient for the integrated management of various infrastructure facilities. They ensure effective control of underground facilities and reduce occupied space. However, aging UUTs require effective management and preventive measures for fire safety. The fundamental problems in operating UUTs are the frequent occurrence of mold, corrosion, and damage caused to finishing materials owing to inadequate waterproofing, dehumidification, and ventilation facilities, which result in corrosion-related electrical leakage in wiring and cables. To prevent this, an abnormal sound detection technology is developed in this study based on acoustic sensing. An acoustic sensor is used to detect electric sparks in the moldy environments of UUTs using a system to collect and analyze the sound generated in the UUTs. We targeted the sound that had the highest impact on detecting electric sparks and performed U-Net-based noise reduction and two-dimensional convolutional neural network-based abnormal sound detection. A mock experiment was conducted to verify the performance of the proposed model. The results indicated that local and spatial features could capture the internal characteristics of both abnormal and normal sounds. The superior performance of the proposed model verified that the local and spatial features of electric sparks are crucial for detecting abnormal sounds. |
| first_indexed | 2024-03-11T03:44:26Z |
| format | Article |
| id | doaj.art-29b3e30b701c4290a592dfe2d54b439c |
| institution | Directory Open Access Journal |
| issn | 2571-6255 |
| language | English |
| last_indexed | 2024-03-11T03:44:26Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fire |
| spelling | doaj.art-29b3e30b701c4290a592dfe2d54b439c2023-11-18T01:19:20ZengMDPI AGFire2571-62552023-05-016521110.3390/fire6050211Acoustic Based Fire Event Detection System in Underground Utility TunnelsByung-Jin Lee0Mi-Suk Lee1Woo-Sug Jung2Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of KoreaElectronics and Telecommunications Research Institute, Daejeon 34129, Republic of KoreaElectronics and Telecommunications Research Institute, Daejeon 34129, Republic of KoreaUnderground utility tunnels (UUTs) are convenient for the integrated management of various infrastructure facilities. They ensure effective control of underground facilities and reduce occupied space. However, aging UUTs require effective management and preventive measures for fire safety. The fundamental problems in operating UUTs are the frequent occurrence of mold, corrosion, and damage caused to finishing materials owing to inadequate waterproofing, dehumidification, and ventilation facilities, which result in corrosion-related electrical leakage in wiring and cables. To prevent this, an abnormal sound detection technology is developed in this study based on acoustic sensing. An acoustic sensor is used to detect electric sparks in the moldy environments of UUTs using a system to collect and analyze the sound generated in the UUTs. We targeted the sound that had the highest impact on detecting electric sparks and performed U-Net-based noise reduction and two-dimensional convolutional neural network-based abnormal sound detection. A mock experiment was conducted to verify the performance of the proposed model. The results indicated that local and spatial features could capture the internal characteristics of both abnormal and normal sounds. The superior performance of the proposed model verified that the local and spatial features of electric sparks are crucial for detecting abnormal sounds.https://www.mdpi.com/2571-6255/6/5/211anomaly detectionacoustic sensingdeep learningunderground utility tunnel |
| spellingShingle | Byung-Jin Lee Mi-Suk Lee Woo-Sug Jung Acoustic Based Fire Event Detection System in Underground Utility Tunnels Fire anomaly detection acoustic sensing deep learning underground utility tunnel |
| title | Acoustic Based Fire Event Detection System in Underground Utility Tunnels |
| title_full | Acoustic Based Fire Event Detection System in Underground Utility Tunnels |
| title_fullStr | Acoustic Based Fire Event Detection System in Underground Utility Tunnels |
| title_full_unstemmed | Acoustic Based Fire Event Detection System in Underground Utility Tunnels |
| title_short | Acoustic Based Fire Event Detection System in Underground Utility Tunnels |
| title_sort | acoustic based fire event detection system in underground utility tunnels |
| topic | anomaly detection acoustic sensing deep learning underground utility tunnel |
| url | https://www.mdpi.com/2571-6255/6/5/211 |
| work_keys_str_mv | AT byungjinlee acousticbasedfireeventdetectionsysteminundergroundutilitytunnels AT misuklee acousticbasedfireeventdetectionsysteminundergroundutilitytunnels AT woosugjung acousticbasedfireeventdetectionsysteminundergroundutilitytunnels |