Gas Leak Detection and Leakage Rate Identification in Underground Utility Tunnels Using a Convolutional Recurrent Neural Network

Jiang, Ziyang; Zhang, Canghai; Xu, Zhao; Song, Wenbin

doi:10.3390/app15148022

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Gas Leak Detection and Leakage Rate Identification in Underground Utility Tunnels Using a Convolutional Recurrent Neural Network

¹

School of Civil Engineering, Southeast University, 2 Dongnandaxue Rd., Nanjing 211189, China

²

School of Computer Science and Engineering, Southeast University, 2 Dongnandaxue Rd., Nanjing 211189, China

^*

Author to whom correspondence should be addressed.

Appl. Sci. 2025, 15(14), 8022; https://doi.org/10.3390/app15148022

Submission received: 19 June 2025 / Revised: 15 July 2025 / Accepted: 16 July 2025 / Published: 18 July 2025

(This article belongs to the Special Issue Applications of Artificial Intelligence in Industrial Engineering)

Download Versions Notes

Abstract

An underground utility tunnel (UUT) is essential for the efficient use of urban underground space. However, current maintenance systems rely on patrol personnel and professional equipment. This study explores industrial detection methods for identifying and monitoring natural gas leaks in UUTs. Via infrared thermal imaging gas experiments, data were acquired and a dataset established. To address the low-resolution problem of existing imaging devices, video super-resolution (VSR) was used to improve the data quality. Based on a convolutional recurrent neural network (CRNN), the image features at each moment were extracted, and the time series data were modeled to realize the risk-level classification mechanism based on the automatic classification of the leakage rate. The experimental results show that when the sliding window size was set to 10 frames, the classification accuracy of the CRNN was the highest, which could reach 0.98. This method improves early warning precision and response efficiency, offering practical technical support for UUT maintenance management.

Keywords: underground utility tunnel; natural gas leak detection; basic video super-resolution reconstruction; long short-term memory network; convolutional recurrent neural network

Share and Cite

MDPI and ACS Style

Jiang, Z.; Zhang, C.; Xu, Z.; Song, W. Gas Leak Detection and Leakage Rate Identification in Underground Utility Tunnels Using a Convolutional Recurrent Neural Network. Appl. Sci. 2025, 15, 8022. https://doi.org/10.3390/app15148022

AMA Style

Jiang Z, Zhang C, Xu Z, Song W. Gas Leak Detection and Leakage Rate Identification in Underground Utility Tunnels Using a Convolutional Recurrent Neural Network. Applied Sciences. 2025; 15(14):8022. https://doi.org/10.3390/app15148022

Chicago/Turabian Style

Jiang, Ziyang, Canghai Zhang, Zhao Xu, and Wenbin Song. 2025. "Gas Leak Detection and Leakage Rate Identification in Underground Utility Tunnels Using a Convolutional Recurrent Neural Network" Applied Sciences 15, no. 14: 8022. https://doi.org/10.3390/app15148022

APA Style

Jiang, Z., Zhang, C., Xu, Z., & Song, W. (2025). Gas Leak Detection and Leakage Rate Identification in Underground Utility Tunnels Using a Convolutional Recurrent Neural Network. Applied Sciences, 15(14), 8022. https://doi.org/10.3390/app15148022

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

Gas Leak Detection and Leakage Rate Identification in Underground Utility Tunnels Using a Convolutional Recurrent Neural Network

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI