Data Analytics into Hydraulic Modelling for Better Understanding of Well/Surface Network Limits, Proactively Identify Challenges and, Provide Solutions for Improved System Performance in the Greater Burgan Field

Abstract

A network modeling campaign for 15 surface gathering centers involving more than 1800 completion strings has helped to lay out different risks on the existing surface pipeline network facility and improved the screening of different business and action plans for the South East Kuwait (SEK) asset of Kuwait Oil Company. Well and network hydraulic models were created and calibrated to support engineers from field development, planning, and operations teams in evaluating the hydraulics of the production system for the identification of flow assurance problems and system optimization opportunities. Steady-state hydraulic models allowed the analysis of the integrated wells and surface network under multiple operational scenarios, providing an important input to improve the planning and decision-making process. The focus of this study was not only in obtaining an accurate representation of the physical dimension of well and surface network elements, but also in creating a tool that includes standard analytical workflows able to evaluate wells and surface network behavior, thus useful to provide insightful predictive capability and answering the business needs on maintaining oil production and controlling unwanted fluids such as water and gas. For this reason, the model needs to be flexible enough in covering different network operating conditions. With the hydraulic models, the evaluation and diagnosis of the asset for operational problems at well and network level will be faster and more effective, providing reliable solutions in the short- and long-terms. The hydraulic models enable engineers to investigate multiple scenarios to identify constraints and improve the operations performance and the planning process in SEK, with a focus on optimal operational parameters to establish effective wells drawdown, evaluation of artificial lifting requirements, optimal well segregation on gathering centers headers, identification of flow assurance problems and supporting production forecasts to ensure effective production management.

Predictive Analytics Performance on Oil and Gas: A Significant Review

“…Some examples include ML techniques [19]- [21], ensemble techniques [22], [23], [22], [23], soft computing techniques [24], [25], statistical techniques [26], and fuzzy-based systems [27]. The effective application of AI in several O&G domains, such as gas [28], pipeline [29], crude oil [30], oxyhydrogen gas retrofit [31], and transformer oil [32], have increased interest in the last few years.…”

A Review of Predictive Analytics Models in the Oil and Gas Industries

“…Some examples include ML techniques [ 22 , 23 , 24 ], ensemble techniques [ 25 , 26 ], soft computing techniques [ 27 , 28 ], statistical techniques [ 29 ], and fuzzy-based systems [ 30 ]. The effective application of AI in several O&G domains, such as gas [ 31 ], pipeline [ 32 ], crude oil [ 33 ], oxyhydrogen gas retrofit [ 34 ], and transformer oil [ 35 ], has received increased interest in the last few years.…”