Abstract
Abstract
This paper explains the development and implementation in the Schlumberger artificial lift real-time surveillance center of a workflow to track ESP alarms from their initial identification through their classification to the analysis of their root-cause. The workflow uses a QHSE database with Web access to enable collaboration between the surveillance center and field locations throughout Europe and Africa. Of more than 700 alarms which were substantiated over an 18 month period, over one third were classified as "critical", i.e. if no actions were taken, an Electric Submersible Pump (ESP) failure could potentially ensue. As such, real-time surveillance was seen to contribute to an increase in ESP run life, firstly, by preventing the ESP from being misoperated and experiencing excessive stress, and secondly, by using the alarm classification as the basis for service quality reviews to promptly identify remedial action items.
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Application of Artificial Neural Networks in Predicting Discharge Pressures of Electrical Submersible Pumps for Performance Optimization and Failure Prevention;Day 3 Wed, October 04, 2023;2023-10-02
2. Rapid Digital Oilfield Transformation Using Edge Computing and AI;Day 2 Tue, October 03, 2023;2023-10-02
3. How to Design a Modular, Effective, and Interpretable Machine Learning-Based Real-Time System: Lessons from Automated Electrical Submersible Pump Surveillance;Day 4 Thu, October 05, 2023;2023-10-02
4. Commingled Production, a New Era in Mature Fields. Lessons Learned and Practices in ESP Lifted Wells Achieved 29 % Incremental Production During Initial Implementation in Shaya Project;Day 1 Mon, October 31, 2022;2022-10-31
5. Production Life Cycle Management Service Eliminates 1,195 Wellsite Visits in South American Field, Saving a Total of 26,141 Miles;Day 2 Wed, October 26, 2022;2022-10-25