Verifying Feasibility of Artificial Lift Methods in Rapid Selection Tool

This paper summarizes lessons learned from a 2-year program aiming at the implementation of Digital Oil Field (DOF) across unconventional resources (UCR) fields produced with ESP. First, the outcomes of the 6-month pilot program are presented. The goal of this pilot was to define workflows and practices for (a) data collection and processing, (b) automatic ESP model matching and VLP generation, and (c) well optimization. Next, digital oil field (DOF) implementation is discussed including data integration, well test validation and learnings from field optimization with gas lift and ESP wells. Petroleum Expert DOF is software application chosen for this project, therefore, most of the discussion is focused on Petex suite: Prosper, GAP and DOF. The introduction of unforeseen biases through data treatment is one of those learning. For example, a downtime event would introduce zeros in the averaging of operating frequency potentially causing unrealistic low frequency values while pressure build-up during downtime would drive an over-estimation of average intake pressure. Likewise, we learnt the importance of qualitative match between model results and ESP real-time data analysis. Most engineers would gain confidence in simulation results if the model outcome matched real-time ESP trend interpretations. Finally, a brief discussion of ESP model-based optimization is carried out in the context of UCR wells. Despite successful deployment across multiple Permian fields and automatically matching more than 100 ESP wells every month, the team learnt that tool true value is only achievable through broad user adoption. Therefore, training and mentoring are discussed as well as the creation of tools that speed up model building bottlenecks.

show abstract

Artificial Lift Selection Methods in Conventional and Unconventional Wells: A Summary and Review from Old Techniques to Machine Learning Applications

Alhaj A. Mahdi,

Amish,

Oluyemi

2024

International Journal of Innovative Science and Research Techno

View full text Add to dashboard Cite

Artificial lift (AL) selection is an important process in enhancing oil and gas production from reservoirs. This article explores the old and current states of AL selection in conventional and unconventional wells, identifying the challenges faced in the process. The role of various factors such as production and reservoir data and economic and environmental considerations is highlighted. The article also examines the use of machine learning (ML) techniques in the AL selection process, emphasising their potential to increase the accuracy of selection and reduce data analysis time. The findings of this article provide valuable insights for researchers and practitioners in the oil and gas industry, as well as for those interested in the development of AL selection methods.

show abstract

Verifying Feasibility of Artificial Lift Methods in Rapid Selection Tool

Cited by 4 publications

References 3 publications

Application of New Electrical Submersible Progressive Cavity Pump Technology in Drainage Gas Recovery of Coalbed Methane Wells

Application of New Electrical Submersible Progressive Cavity Pump Technology in Drainage Gas Recovery of Coalbed Methane Wells

Lesson Learned from Digital Oil Field Implementation in ESP UCR Wells

Artificial Lift Selection Methods in Conventional and Unconventional Wells: A Summary and Review from Old Techniques to Machine Learning Applications

Contact Info

Product

Resources

About