An IIOT Approach for Prediction of Gas Leakage in Pipeline Using Edge Software via k means

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 12

Year of Publication : 2025

Authors : Rakesh Rajendran, Hamsadhwani Vivekanandan, Ilangovan Pandian, Shivakumar Natarajan, Sharmila Begum. M

10.14445/23488549/IJECE-V12I12P119

How to Cite?

Rakesh Rajendran, Hamsadhwani Vivekanandan, Ilangovan Pandian, Shivakumar Natarajan, Sharmila Begum. M, "An IIOT Approach for Prediction of Gas Leakage in Pipeline Using Edge Software via k means," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 12, pp. 230-240, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I12P119

Abstract:

In this rise in the technology era, many industrial revolutions have emerged in their routine functions. One such technology is the “Internet of Things”. This is further named as “Industrial Internet of Things (IIOT) “when this technology is purely applied across any application in industries. Here in this paper, one of the real-time challenges prevailing in the oil and gas refinery industry is taken, which is “oil or gas leakage along the pipeline”. The gas leakage is also meant as a loss of energy happening during transmission. As of now, such leakages are detected only by breakdown maintenance; the testing of the tube is done only after a huge loss has occurred. This traditional method can be replaced with a live detection mechanism employing the Internet of Things for monitoring the health condition of the pipe continuously. In other words, it means that the detection of leakage can be determined at the initial stage itself, rather than allowing it to result in a huge loss of energy. The audio signal of the gas flow in the healthy tube (without leakage) is trapped, and it is being considered as the train data. A similar audio signal of the gas flow in the leakage tube (i.e., the tube with leakage) is also captured and considered as test data. This test data and train data are fed to Edge Impulse Software for anomaly detection using the k-means algorithm. This method of predictive maintenance, using Edge Impulse, would convert the gas tube into a live detection mechanism throughout its length and alert with an early warning mechanism whenever gas leakage occurs.

Keywords:

Industrial Internet of Things, Edge Impulse, k-means algorithm, Anomaly detection, Gas leakage detection.

References:

[1] P. Naveen et al., “A Comprehensive Review on Gas Leakage Monitoring and Alerting System using IoT Devices,” 2022 International Conference on Computer, Power and Communications (ICCPC), Chennai, India, pp. 242-246, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] M. Pajany, and A. Hemalatha, “Pipeline Gas Leakage Detection and Location Identification System,” 2019 IEEE International Conference on System, Computation, Automation and Networking (ICSCAN), Pondicherry, India, pp. 1-6, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Siying Li et al., “Unsupervised Leak Detection of Natural Gas Pipe Based on Leak-free Flow Data and Deep Auto-Encoder,” 2022 China Automation Congress (CAC), Xiamen, China, pp. 678-683, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] K. Sheela Gnana, Mobile Robot for Gas Leakage Detection System in Pipelines, Handbook of Smart Materials, Technologies, and Devices, Springer Cham, pp. 1121-1135, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Anselemi B. Lukonge, and Xuewen Cao, “Leak Detection System for Long-Distance Onshore and Offshore Gas Pipeline Using Acoustic Emission Technology. A Review,” Transactions of the Indian Institute of Metals, vol. 73, pp. 1715-1727, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Bibekananda Jena et al., “LPG Gas Leakage Detection System Using IoT,” Materials Today: Proceedings, vol. 74, pp. 795-800, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] O.A. Tumshis, and L.V. Yakyavichyus, “System for Detection of the Location of Leaks in Gas Pipelines of Low Pressure,” Measurement Techniques, vol. 41, pp. 477-479, 1998.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Yan Shi et al., “Gas Leakage Detection and Pressure Difference Identification by Asymmetric Differential Pressure Method,” Chinese Journal of Mechanical Engineering, vol. 35, pp. 1-9, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Ignacio Barradas et al., “Leaks Detection in a Pipeline using Artificial Neural Networks,” 14th Iberoamerican Conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, Guadalajara, Jalisco, México, pp. 637-644, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Samer El-Zahab, and Tarek Zayed, “Leak Detection in Water Distribution Networks: An Introductory Overview,” Smart Water, vol. 4, pp. 1-23, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[11] J. Prem Chander et al., “Gas Leakage Detection and Shutoff System,” International Conference on Advances in Automation, Signal Processing, Instrumentation, and Control, pp. 785-793, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Chen Sun et al., “A CNN Model for Gas Pipeline Leakage Detection Based on MFCC Feature Extraction,” Proceedings of the 2023 12th International Conference on Networks, Communication and Computing, Osaka Japan, pp. 288-293, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Chunbao Xiong, Sida Lian, and Wen Chen, “An Ensemble Method for Automatic Real-Time Detection and Evaluation of Oil and Gas Leakage in Subsea Pipelines based on 3D Real-Time Sonar System,” Journal of Civil Structural Health Monitoringm, vol. 13, pp. 1313 1331, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Sumayh S. Aljameel et al., “Oil and Gas Pipelines Leakage Detection Approaches: A Systematic Review of Literature,” International Journal of Safety & Security Engineering, vol. 14, no. 3, pp. 773-786, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Ke Guo et al., “Gas Leakage Monitoring with Mobile Wireless Sensor Networks,” Procedia Computer Science, vol. 154, pp. 430-438, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Vasileios Tsoukas et al., “A Gas Leakage Detection Device Based on the Technology of TinyML,” Technologies, vol. 11, no. 2, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Yan Chen et al., “GasEdge-YOLO: Multi-scale Edge Generator and Star-shaped Branch Attention for Efficient Infrared Gas Detection,” Measurement Science and Technology, vol. 36, no. 10, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Jinhui Zuo et al., “Automated Detection of Methane Leaks by Combining Infrared Imaging and a Gas-Faster Region-Based Convolutional Neural Network Technique,” Sensors, vol. 25, no. 18, pp. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Minghe Wang et al., “Infrared Imaging Detection for Hazardous Gas Leakage Using Background Information and Improved YOLO Networks,” Remote Sensing, vol. 17, no. 6, pp. 1-21, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Jue Wang et al., “Invisible Gas Detection: An RGB-thermal Cross Attention Network and a New Benchmark,” Computer Vision and Image Understanding, vol. 248, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Jin-Hee Lee et al., “Vision-Ultrasound Robotic System based on Deep Learning for Gas and Arc Hazard Detection in Manufacturing,” arXiv preprint, pp. 1-24, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Wenqi Guo, Yiyang Du, Shan Du, “LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 4499-4509, 2025.
[Google Scholar] [Publisher Link]
[23] Edmilson Sanches et al., “Artificial Intelligence for Gas Leak Detection with Thermal Cameras and Metal Oxide Semiconductor Sensors,” Journal of Theoretical and Applied Informatics, vol. 32, no. 1, pp. 91-98, 2025.
[CrossRef] [Google Scholar] [Publisher Link]