Technology Category
Machine Learning: Time-Series/Data StreamsKnowledge Representation and Reasoning: Diagnosis and Abductive ReasoningData Mining & Knowledge Management: Anomaly/Outlier Detection
Identifying Slug Formation in Oil Well Pipelines: A Use Case from Industrial Analytics
🤖 AI Summary
Slug flow in oil and gas pipelines poses significant safety risks, yet conventional detection methods rely on offline analysis and expert knowledge, lacking real-time capability and interpretability.
Method: This paper proposes an end-to-end, interactive, data-driven system supporting a full closed-loop workflow—from CSV data ingestion and interactive visualization-based labeling to snapshot-persistent model training and real-time inference. It innovatively integrates time-series superposition visualization, persistent alerting mechanisms, and configurable multi-classifiers to enable human-in-the-loop modeling and transparent, explainable diagnostics.
Contribution/Results: The lightweight, plug-and-play system demonstrates high detection accuracy and robustness in real industrial deployments. Its modular architecture ensures seamless adaptability to other time-series fault diagnosis tasks, offering strong generalizability and practical scalability.
Technology Category
Application Category
📝 Abstract
Slug formation in oil and gas pipelines poses significant challenges to operational safety and efficiency, yet existing detection approaches are often offline, require domain expertise, and lack real-time interpretability. We present an interactive application that enables end-to-end data-driven slug detection through a compact and user-friendly interface. The system integrates data exploration and labeling, configurable model training and evaluation with multiple classifiers, visualization of classification results with time-series overlays, and a real-time inference module that generates persistence-based alerts when slug events are detected. The demo supports seamless workflows from labeled CSV uploads to live inference on unseen datasets, making it lightweight, portable, and easily deployable. By combining domain-relevant analytics with novel UI/UX features such as snapshot persistence, visual labeling, and real-time alerting, our tool adds significant dissemination value as both a research prototype and a practical industrial application. The demo showcases how interactive human-in-the-loop ML systems can bridge the gap between data science methods and real-world decision-making in critical process industries, with broader applicability to time-series fault diagnosis tasks beyond oil and gas.
Problem
Research questions and friction points this paper is trying to address.
Detects slug formation in oil pipelines in real-time
Overcomes limitations of offline detection requiring expert knowledge
Bridges gap between data science and industrial decision-making
Innovation
Methods, ideas, or system contributions that make the work stand out.
Interactive application for end-to-end slug detection
Configurable model training with multiple classifiers
Real-time inference module with persistence-based alerts
🔎 Similar Papers
No similar papers found.
