Key points are not available for this paper at this time.
Abstract This paper presents the successful development and implementation of a wellbore quality scorecard which is used to evaluate wellbore quality using deterministic and probabilistic methods. This evaluation is based on analysing the real time data during the final trip out of hole with the drilling BHA. The Wellbore Quality Scorecard is being used systematically across a large multi-asset drilling project where there was a history of problematic hole sections. Casing and liner running operations frequently encountered difficulties, and it was recognised that a system for evaluating the hole condition would help to improve operational decision making. The result of the evaluation is used to provide a better understanding of the condition of the wellbore that was drilled before committing to run casing or liner. Understanding the wellbore condition helps the team to decide, for example, whether to run a wiper trip to condition the wellbore or to save time and go ahead with casing or liner run. The evaluation process is a collaboration between the remote collaboration centre, the rigsite team and the office-based operations team. A database is generated which records historical wellbore condition vs liner and casing running information which holds very useful technical insights about how each wellbore parameter quantitatively affects the wellbore quality. The paper will describe how this process has now been applied to over 50 hole sections, and how it has improved decision making and the liner and casing running success rate. A machine learning model has been developed which predicts the likelihood of successfully running the casing or liner to the target depth. This information is used to compliment the Wellbore Quality Score for informing operational decisions.
Cockburn et al. (Tue,) studied this question.