conference paper · SPE Nigeria Annual International Conference and Exhibition
Oil and gas pipeline leaks cause product loss, environmental damage, and infrastructure destruction, while conventional pressure and flow sensors suffer from latency, false alarms, and hardware complexity. An artificial intelligence monitoring framework addresses these challenges by combining visual leak detection with automated response guidance. The system employs a YOLO11 model trained on a curated pipeline image dataset to detect leak regions and estimate severity and risk scores based on bounding boxes. Detections are subsequently evaluated by a vision language model, Gemini 2.5 Flash, which generates structured, actionable corrective recommendations delivered in text and audio formats. Experimental evaluation shows that the system provides accurate visual detection and practical decision support, functioning as a scalable, low-cost visual alternative to sensor-heavy monitoring setups.
Pipeline failures risk catastrophic environmental contamination, financial loss, and severe safety hazards. Traditional sensor networks can be prone to delays and false alarms. Providing real-time visual detection along with clear, automated guidance helps maintenance teams identify and mitigate damage quickly, reducing the impact of hazardous spills without relying entirely on complex, expensive downhole and surface sensor infrastructure.
The framework is designed for oil and gas operators and pipeline surveillance contractors seeking lower-cost visual inspection tools. It could enable camera-based automated monitoring platforms that generate instant response directives for repair crews. Based on experimental evaluation using curated image data, the system appears to be an applied and tested laboratory prototype, requiring further field validation and integration with existing industrial camera networks before reaching operational deployment.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Pipeline leakage presents a significant operational, environmental, and safety challenge in the oil and gas industry, with undetected failures leading to catastrophic consequences, including product loss, environmental contamination, and infrastructure damage. Traditional detection methods, such as pressure and flow monitoring or sensor networks, are limited by latency, false alarms, and the need for complex hardware integration. Recent advances in computer vision have demonstrated the potential for automated visual leak detection using deep learning models, particularly real-time object detectors that identify leak signatures in image data from monitoring cameras. This work proposed an AI-based pipeline monitoring system that integrates real-time leak detection with severity estimation, risk scoring, and structured corrective guidance. A YOLO11 model, trained on a curated pipeline image dataset, identifies leak regions and calculates bounding-box-derived severity and risk scores. Detected leaks are analysed using a Vision Language model (Gemini 2.5 flash) to generate actionable, professionally formatted recommendations, delivered via text and audio. Experimental evaluation demonstrates that the proposed system provides accurate visual leak detection and practical decision support, offering a scalable, low-cost alternative to conventional sensing-heavy systems and establishing a framework for enhanced AI-assisted pipeline monitoring.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.2118/234818-ms
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
