Author:
P Srinithi,S Sree Varshini,G Dhanush,S Gokulavaasan,K Gowtham
Abstract
The oil and gas industry face significant risks of explosions, often due to factors like gas and oil leakage as well as external corrosion. These substances are highly flammable, and even minor leaks can create volatile environments where the smallest spark can lead to catastrophic explosions. While internal corrosion in pipelines receives attention, external corrosion is often overlooked. Over time, pipeline coatings deteriorate, leaving them susceptible to external corrosion, which can result in leaks, endangering workers and the environment. Detecting and addressing corrosion promptly is crucial for preventing accidents and environmental harm. To address these challenges, a pipeline monitoring system has been developed using a Raspberry Pi Model 3B+ and advanced sensors. This system continuously monitors temperature, pressure, and external corrosion along pipeline routes. It utilizes a K-type thermocouple and a 1.2MPa pressure transducer for real-time data collection. Additionally, a laptop camera integrated with YOLOv8 enables visual inspection for detecting corrosion. The Raspberry Pi processes sensor data and images, triggering alerts for anomalies like temperature or pressure drops indicating leaks, or corrosion spots identified by YOLOv8. The system interfaces with ThingSpeak for remote data visualization and analysis, empowering operators to make informed decisions and take prompt corrective actions.
Publisher
Inventive Research Organization
Reference15 articles.
1. [1] Nagalakshmi, T. & A. Ph.D., Sivasakthi. (2019). Corrosion Control, Prevention and Mitigation in Oil & Gas Industry. International Journal of Innovative Technology and Exploring Engineering. 9. 1568-1572. 10.35940/ijitee.B7272.129219
2. [2] Chandran and S. Kavitha, "A Smart Gas Stove with Gas Leakage Detection and Multistage Prevention System Using IoT," International Journal of Mechanical and Design Engineering (IJMDES), vol. 1, no. 9, pp. 5–9, Sep. 2022.
3. [3] L. B. Coelho, D. Zhang, Y. Van Ingelgem, D. Steckelmacher, A. Nowé, and H. Terryn "Reviewing machine learning of corrosion prediction in a data-oriented perspective," npj Materials Degradation, vol. 6, pp. 1-16, 2022.
4. [4] D. Ma, H. Fang, N. Wang, C. Zhang, J. Dong and H. Hu, "Automatic Detection and Counting System for Pavement Cracks Based on PCGAN and YOLO-MF," in IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 11, pp. 22166-22178, Nov. 2022,
5. [5] P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, "A Review of YOLO Algorithm Developments," Procedia Computer Science, vol. 199, pp. 1066-1073, ISSN: 1877-0509, 2022.