Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Results
Abstract Many well control incidents have been analyzed, resulting in the optimumpractices, as outlined in this paper. To the best of the authors' knowledge, there are no systematic guidelines for well control practices. The objective ofthis paper is to propose a set of guidelines for the optimal well controloperations, by integrating current best practices through a decision-makingsystem based on Artificial Bayesian Intelligence. Best well control practicescollected from data, models, and experts' opinions, are integrated into aBayesian Network BN to simulate likely scenarios of its use that will honorefficient practices when dictated by varying operation, kick details, and kick severity. The proposed decision-making model follows a causal and an uncertainty-basedapproach capable of simulating realistic conditions on the use of well controloperations. For instance, as the user vary the operation, rig and crewcapabilities, kick details (such as slim hole, deviated or horizontal well), the system will show the optimum practices for circulation method. Well control experts' opinions were considered in building up the model in thispaper. The advantage of the artificial Bayesian intelligence method is that itcan be updated easily when dealing with different opinions. The outcome of thispaper is user-friendly software, where you can easily find the specific subjectof interest, and by the click of a button, get the related information you areseeking. Introduction The purpose of development of well control procedure is to prevent catastrophesthat could result from blowouts. The objective of this paper is to propose amodel to serve as a training tool. The development of up to date source ofproper well control practices is a challenging task. Using current methods offlow charts in decision making does not allow enough room for different orchanging well control practices to be included. The design of optimum well control practises depends mainly on previousexperience and knowledge to successfully complete with a degree of confidence. Effective communication is also an important factor for successful well controloperations. Good coordination is required between the engineer, the servicecompany and the rig foreman. Knowledge transfer in well control operations istherefore fundamental for the optimal design of the job. Field experiences are required for well control specialists to select optimumpractices. In some instances, well control operation failures can occur becauseof the lack of knowledge or lack of knowledge transfer. There are different methods that companies have approached to make guidelinesfor their engineers to save on operations cost and time. However, these methodscan not be used by other companies or experts with different opinions or withdifferent field conditions. Al-Yami et al. (2010) were the first to propose a systematic approach to buildexpert systems that can be used in optimum selection and execution ofsuccessful cementing operations using Artificial Bayesian Intelligence.
Abstract Many underbalanced drilling operations have been analyzed, resulting in theoptimum practices, as outlined in this paper. To the best of the authors'knowledge, there are no systematic guidelines for underbalanced drilling. The objective of this paper is to propose a set of guidelines for the optimalunderbalanced drilling operations, by integrating current best practicesthrough a decision-making system based on Artificial Bayesian Intelligence. Optimum underbalanced drilling practices collected from data, models, andexperts' opinions, are integrated into a Bayesian Network BN to simulate likelyscenarios of its use that will honor efficient practices when dictated byvarying certain parameters suchas formation pressure and operation. Theproposed decision-making model follows a causal and an uncertainty-basedapproach capable of simulating realistic conditions on the use of underbalanceddrilling operations. For instance, by varying the type of UBD (flow, aerated, etc), operation and formation properties the system will show optimum trippingand connection procedure. The developed model also acknowledged UBD drilling techniques in differentscenarios such as fractured formations, low permeability and high permeabilityformations. The model also shows optimum solutions to problems related tounderbalance drilling such as well control, completion, equipment associatedwith drilling. Experts' opinions were considered in building up the model in this paper. Theadvantage of the artificial Bayesian intelligence method is that it can beupdated easily when dealing with different opinions. The outcome of this paperis user-friendly software, where you can easily find the specific subject ofinterest, and by the click of a button, get the related information you areseeking. Introduction The design of optimum underbalanced drilling operations depends mainly onprevious experience and knowledge to successfully complete with a degree ofconfidence. Effective communication is also an important factor for successfuloperations. Good coordination is required between the engineer, the servicecompany and the rig foreman. Knowledge transfer in underbalanced drillingoperations is therefore fundamental for the optimal design of the job. Long field experience is required for underbalanced drilling specialists toselect optimum practices. In some instances, operation failures can occurbecause of the lack of knowledge or lack of knowledge transfer. There are different methods that companies have approached to make guidelinesfor their engineers to save on operations cost and time. However, these methodscan not be used by other companies or experts with different opinions or withdifferent field conditions. Al-Yami et al. (2010) were the first to propose a systematic approach to buildexpert systems that can be used in optimum selection and execution ofsuccessful cementing operations using Artificial Bayesian Intelligence.