The use of Artificial Bayesian Intelligence in Practical Well Control: Development and Field Cases
- Abdullah Saleh Al-Yami (Saudi Aramco) | Jerome Jacob Schubert (Texas A&M University)
- Document ID
- Society of Petroleum Engineers
- SPE Russian Oil and Gas Exploration and Production Technical Conference and Exhibition, 16-18 October, Moscow, Russia
- Publication Date
- Document Type
- Conference Paper
- 2012. Society of Petroleum Engineers
- 4.4.4 Pipeline Leak Detection, 1.6 Drilling Operations, 1.7.1 Underbalanced Drilling, 1.3.2 Subsea Wellheads, 1.10 Drilling Equipment, 1.6.7 Geosteering / Reservoir Navigation, 2 Well Completion, 4.2.4 Risers, 1.14 Casing and Cementing, 6.1.5 Human Resources, Competence and Training, 1.11 Drilling Fluids and Materials, 1.7.5 Well Control, 4.2 Pipelines, Flowlines and Risers, 7.2.3 Decision-making Processes, 7.6.6 Artificial Intelligence
- 0 in the last 30 days
- 387 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
Many well control incidents have been analyzed, resulting in the optimum practices, as outlined in this paper. The objective of this paper is to propose a set of guidelines for the optimal well control operations, by integrating current best practices through a decision-making system based on Artificial Bayesian Intelligence.
Best well control practices collected from data, models, and experts' opinions, are integrated into a Bayesian Network to simulate likely scenarios of its use that will honor efficient practices. When dictated by varying operation, kick details, and kick severity. The proposed decision-making model follows a causal and an uncertainty-based approach capable of simulating realistic conditions on the use of well control operations. For instance, by varying the operation, the system will show the kick indicators for that particular operation. Also in the same model as the user vary the operation, rig and crew capabilities, kick details (such as slim hole, deviated or horizontal well), the system will show the optimum practices for circulation method and shut in method. The model also shows optimum practices for blowout control by varying the un-controlled kick type (surface, subsurface or underground blowouts). Recommended practices after controlling the well are shown by the same operation that caused the well control incident and by varying the potential reason for the incident.
Two well control experts' opinions were considered in building up the model in this paper. The advantage of the artificial Bayesian intelligence method is that it can be updated easily when dealing with different opinions. The outcome of this paper is user-friendly software, where you can easily find the specific subject of interest, and by the click of a button, get the related information you are seeking. Field cases will also be discussed to validate this work.
Expert systems are knowledge processing which enable computers to do certain tasks similar to humans or some times better than human experts. The real motive of such type of research is the shortage of expertise, Hayes-Roth (1987).
Expert system can be defined as "An interactive computer-based decision tool that simulates the thought process of a human expert to solve complex problems in a specific domain.?? We need experts system because of limitations in expertise, working memory, insufficient maintenance of significant data and biased opinions, (Pandey and Osisanya 2001).
There are different methods that companies have approached to make guidelines for their engineers to save on operations cost and time. However, these methods cannot be used by other companies or experts with different opinions or with different field conditions Al-Yami et al. (2012a).
Texas A&M University recently has established a new method to develop a drilling expert system that can be used as a training tool for young engineers or as a consultation system in various drilling engineering concepts such as drilling fluids, cementing, completion, well control, and underbalanced drilling practices.
This method is done by proposing a set of guidelines for the optimal drilling operations in different focus areas, by integrating current best practices through a decision-making system based on Artificial Bayesian Intelligence. Optimum practices collected from literature review and experts' opinions, are integrated into a Bayesian Network BN to simulate likely scenarios of its use that will honor efficient practices when dictated by varying certain parameters.
The term Bayesian derives from Thomas Bayes (1702-1761), who was a British mathematician Bayes introduced Bayes' theorem, which was used in this research.
|File Size||1 MB||Number of Pages||24|