Case Study: Predicting Electrical Submersible Pump Failures Using Artificial Intelligence

Abstract

Abstract Unplanned Electrical Submersible Pump (ESP) failures can have a profound impact on well production and overall field economics; therefore, it is important to reliably predict the onset of damaging operating conditions and take proactive action to prevent early failure of an ESP. Most operators rely on production engineers to monitor and optimize equipment performance with remote monitoring and surveillance technologies that provide threshold-based diagnostics to detect electrical or mechanical problems. Due to inherent limitations in exception-based monitoring, it is extremely difficult to reliably predict the root cause of equipment failure and remaining useful life (RUL) of an ESP. A major operator in the Americas was experiencing similar operational challenges in three of its producing assets. Unplanned failures happen frequently since they are hard to predict ahead of time with the data available to production engineers. This case study demonstrates how Advanced ESP Predictive Failure Analytics (PFA) technology has helped this operator to detect such events and extend ESP run life. Methods, Procedures, Process PFA is an innovative technique that leverages artificial intelligence (AI), life data analysis, physics, and knowledge-based methods to predict electrical and mechanical events and provides an estimate of RUL of an ESP. The data-driven models are trained using sensor time-series of historical failures and entail advanced data processing, interpolation, quality evaluation and feature engineering. The trained models are deployed to predict short term damage events that may lead to immediate failure, such as broken shaft, short-circuit, grounded downhole sensor failure, as well as long term events which build up over time, such as sand, and scale deposition. Results, Observations, Conclusions For one ESP, PFA detected scale deposition and predicted a sharp decline in RUL. After confirming the decrease in production fluid, and other surface and downhole sensor trends indicating scale deposition in the ESP, the production engineer applied chemical injection and avoided the failure. For a second ESP in this case study, PFA detected a grounding condition and predicted sudden decline in RUL. The production engineer noticed motor amps increased beyond the recommended threshold and performed electrical optimization to reduce motor amps. The ESP ran for another year and eventually failed due to grounded downhole sensor failure, which PFA had detected two weeks prior to the failure.