Investigating Possibilities to Automatically Capture Drilling Lessons Learnt

Research output: ThesisMaster's Thesis

Abstract

This study is devoted to improving Lessons Learnt reporting quality and procedures at OMV Well Engineering.
The first stage of the work was the analysis of informational support along the well engineering process. Types, capture, and transfer of drilling data were described for all well construction lifecycle phases. Reports were systematically categorized by introducing a four-digit coding, reflecting periodicity, data type, operation, and operation details. The analysis of current well construction reports identified shortcomings in the existing structure of the Lessons Learnt report.
The second step was to propose changes to the Lessons Learnt report structure to increase the effectiveness of the information collected. The distribution of non-productive time for OMV wells was analyzed, which identified drilling problem types. As an example, recommendations of improved Lessons Learnt reports were made for a particular type of problem.
The methodology of generating such a report was developed, which consisted of gathering meta-information and – depending on the type of drilling problem – various analyses of technical specifications and sensor data. The result of the procedure is a Lessons Learnt report, which is stored in a database that the drilling engineer uses in the well planning process during the offset well analysis phase.
In order to automate part of the process and reduce the human effort, a web-based application was created to extract non-productive time information from daily drilling reports or activities data.
In the final part of the work, the proposed methodology for creating the Lessons Learnt report was applied on a real well, and the results were successfully verified with historical data.

Details

Translated title of the contributionUntersuchung von Möglichkeiten zur automatischen Erfassung von Lessons Learnt-Berichten
Original languageEnglish
QualificationMSc
Awarding Institution
Supervisors/Advisors
Award date22 Oct 2021
Publication statusPublished - 2021