Using bayesian network to model drilling fluids practices in Saudi Arabia Conference Paper uri icon

abstract

  • 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 and completion fluids, cementing, completion, and underbalanced drilling practices. To the best of the authors knowledge there is no standards developed to aid drilling engineers and scientists to formulate effective drilling fluids systems for the entire well sections. The objective of this paper is to set a module that should aid drilling engineers when designing drilling fluids. A module was created based on several inputs. To create this module, we interviewed experts to gather the information required to determine best practices as a function of different probabilities. Drilling fluids formulations were gathered from Saudi Arabia fields to build up this model. The Bayesian approach was found suitable for designing expert system. The model can work as a guide to aid drilling engineers and scientists to design and execute optimum drilling fluids. Using this approach to build up expert systems is more flexible than using flow charts. Updating flow charts is time consuming and require redesigning them again to be used by different experts or in different fields. Using Bayesian network allows us to update our industry practices by updating the probabilities states mentioned in this paper. Copyright 2012, Society of Petroleum Engineers.

published proceedings

  • SPE Production and Operations Symposium, Proceedings

author list (cited authors)

  • Al-Yami, A. S., & Schubert, J.

complete list of authors

  • Al-Yami, AS||Schubert, J

publication date

  • September 2012