Paper Originally Published: 26-28 September 2016
The presented Expert System is capable of capturing expert knowledge from various domains in one consistent and unbiased logic framework and applying it to newly acquired data in order to identify, predict and categorize business opportunities following unfavorable well performance changes. A case study and following deployment of an automated well workover candidate recognition process incorporating a knowledge capture framework will be provided.
The described Expert System comprises processes ranging from data integration and data cleansing over problem detection to ranking investment candidates according to production gains, costs, risk and NPV. A probabilistic Expert System processes the detected production problems to yield likelihoods of occurrence for various problems in wells, reservoirs or facilities. Hence, the asset team is assisted in differentiating root causes and prioritizing the different countermeasures at hand.
This paper will present the set-up, calibration and deployment of the Expert System. Also, it will be shown, how algorithms and tools are combined to achieve a continuously executed workflow for reservoir management and production optimization. It will be discussed how the results are used in ongoing operations and how the Expert System facilitates operational decisions.
This paper describes the applied procedures and methods, like data analytics, machine learning and reasoning tools like Bayesian Belief Networks. The screening logic works as a repeatable and automated process that can be scheduled or be executed on demand. The screening of several thousands of wells takes less than an hour. Hence the process can be executed more often and much quicker, leading to an intensified monitoring of possible business opportunities.
Over the last 2 years, several studies in more than 30 fields - with a total number of 7,600 wells - representing a wide variety of reservoir and well characteristics have been performed. In the course of these studies and in independent blind tests the correct and precise functionality was successfully tested.
The developed Expert System provides a framework that allows companies or teams to effectively capture the available knowledge, independent of field or level of expertise or geographic location. The paper will discuss basics of knowledge theory and suggest appropriate technologies, approaches and workflows to capture, maintain, adapt and implement an organization's knowledge in such Expert System.
Ultimately, the objective of the Expert System is to reduce the time engineers spend on repetitive and non- value adding tasks and allow them to focus on production optimization, reservoir management and planning. This is achieved by providing engineers with a knowledge capture and transfer framework, which is also capable of supporting day to day decisions under ever changing economic conditions and evaluating their impact immediately.
- Michael Stundner (Datagration, previously: myr:conn solutions GmbH)
- Georg Zangl (Datagration, previously: myr:conn solutions GmbH)
- Lisa Neuhofer (Datagration, previously: myr:conn solutions GmbH)
- David Zabel (Datagration, previously: myr:conn solutions GmbH)
- Philipp Tippel (OMV-Petrom Romania SA)
- Cosmin-Ionut Pantazescu (OMV-Petrom Romania SA)
- Vladimir Krcmarik (OMV-Petrom Romania SA)
- Andrei Iulian Staicu (OMV-Petrom Romania SA)
- Lisa Krenn (Mining University Leoben)
- Barbara Hachmöller (Mining University Leoben)
Document ID: SPE-181683-MS