Future Workforce Education through Big Data Analysis for Drilling Optimization

Abstract

On their continuous quest to improve drilling efficiency, operators are reaching more and more towards the sensor and data-streaming technologies and their powerful data analytics capabilities. For this project, an operator partnered with the drilling automation research group at the University of Texas at Austin to develop a workflow for big data analysis and visualization. The objectives were to maximize the value derived from data, establish an analysis toolkit, and train students on data analytics—a necessary job function of any future drilling engineer. The operator provided data sets, business and technical objectives, and guidance for the project, while a multi-disciplinary group of undergraduate and graduate students piloted an analysis workflow. The students developed methods to: 1) understand and clean the data; 2) structure, combine, and condense information; 3) visualize, benchmark, and interpret the data, as well as derive key performance indicators (KPIs); and 4) automate these processes. The operator provided data collected from drilling 16 wells in an US unconventional play. The large data sets comprised of un-organized time and depth based information from surface and downhole sensors, daily drilling reports, geological information, etc. Students were trained on specialized software and subsequently curated data into smaller sizes and standard formats. Students investigated bottom hole assembly (BHA) and directional drilling performance using a combination of auto-generated conventional visuals (e.g., BHA designs, annotated time vs depth curves) and newly developed tools (e.g., tortuosity, 3D well trajectory plots combined with operational data). Methods for ‘push a button' investigations of mechanic specific energy (MSE), vibration, torque and drag were also developed by calculating specific KPIs from the raw measurement data. The analysis work itself coupled with the attempt to improve the workflow processes served as a meaningful and highly effective way to educate students and prepare them to be the "drilling engineers of the future" with proficiency in data analytics.