Big Data Analytics Workflow to Safeguard ESP Operations in Real-Time

Abstract

Abstract The electrical submersible pump (ESP) is one of the most common forms of artificial lift pumping techniques used in the industry. ESP lift method helps maximize the production of recoverable oil by achieving higher drawdowns and larger fluid volume handling (Ratcliff, Gomez et al. 2013). Unpredictable and repeated ESP shutdowns often occur due to changes in well conditions, improper system design, and dynamic and changing operating environments (Takács 2009). Excessive shutdowns and trips greatly reduce the run-life of the ESP (El Gindy, Abdelmotaal et al. 2015). The associated equipment replacement or repair costs and related downtime and production losses are huge. E&P companies nowadays are deploying web-based monitoring platforms for real-time surveillance of essential ESP and well data. Acquiring and innovatively processing ESP operational data in real time using hybrid methods employing engineering principles and statistical methods can reveal patterns in data to distinguish between safe and unsafe operations, diagnostic measures to identify the issue and remedial actions to address the issue and take corrective action. In this manner, analytics based health monitoring platform can improve the way operators avoid ESP shutdowns which are commonly observed in remote well operations and help advance from supervised approach towards failure mitigation to a more practical approach by leveraging real time data. This paper presents a big data analytics workflow that would allow field personnel and production engineering teams to quickly interpret trends and patterns in ESP operations, diagnose problems and take remedial actions to monitor and safeguard ESP operations. Adoption and integration of this ESP health management workflow with the real-time monitoring system can maximize equipment availability and save millions of dollars in replacement, maintenance and deferred or lost production.