A Real-Time Interactive Drill-Off Test Utilizing Artificial Intelligence Algorithm for DSATS Drilling Automation University Competition

Abstract

The current state of the drilling industry tends to focus on technology and techniques that reduce the cost of well construction. One approach is to use drilling automation to help improve ROP, and perhaps more importantly, to mitigate drilling dysfunctions and human errors than can lead to large, unplanned expenses. SPE's Drilling Systems Automation Technical Section (DSATS) created an international university competition to encourage the development of new drilling algorithms and to get more young people involved in drilling. The students must design, build and operate a small (6 ft / 2 m) drilling rig with fully automated sensors and controls. They drill a specially created, multi-layered rock sample as fast and as straight as possible, with only two buttons: start and stop. This paper summarizes the work done by the West Virginia University team that won the 2016 competition. It shows scalable drilling algorithms can be developed on a miniature rig that can later be transferred to ongoing drilling programs. DSATS implemented a competition to encourage students to investigate the use of automation techniques and tools for drilling systems. The competition fosters a greater understanding of complicated drilling systems, challenging students across disciplines to consider the possibilities of a career in upstream drilling operations. This project requires each university team to first submit a proposal, including structural design, control architecture, and sensor selection with no knowledge of the material to be drilled. Teams were advised to consider mitigating the effect of nonplanar junctions as well as the possibility of lost circulation, and to be especially cognizant of vibration and torque issues. The winning team received a travel grant to attend the ATCE to present their test results at the DSATS symposium in Dubai. This paper addresses the details of that presentation. It includes: Drilling limitations and critical parametersConstruction issues and initial operations that required a re-designFinal design criteria, constraints, tradeoffsSummary of recorded data and key eventsDrilling parameters and how they impacted the testEconomic considerationsSignificant lessons learnedConclusions and recommendations As the competition finishes its second year, it remains the only competition of its kind that requires a multidisciplinary approach at a university level, and prepares those involved for the type of interwoven, team approach often at the heart of oilfield operations today. While the rig designs are practical, they are not limited by historical features or commonplace rig designs. Hands-free drilling is possible and proven on a small scale as more and more companies begin to implement full scale operations to mitigate drilling dysfunctions and improve ROP to lower costs.

Developments and experimental tests on a laboratory-scale drilling automation system

“…The rig is also designed to enter into the international Drillbotics competition hosted by the SPE, in which students are challenged to design and construct autonomous drilling machines to increase the awareness and understanding of how autonomous systems in the future can increase the operational efficiency in the industry and reduce the risk associated with drilling operations. One can find examples of several such autonomous small-scale system designs in Løken et al ( , 2019, Bilgesu et al (2017) and Arnø et al (2018). These rigs act as an infrastructure to establish multi-disciplinary studies necessary to overcome the challenges related to drilling automation and other advanced drilling technologies.…”

Design, Construction, and Analysis of a Pilot-Scale Automated Drilling Platform

“…In determining appropriate hydraulics, the cutting transport ratio should be higher than 50%, which it was at all tested flow rates, and the pressure loss across the bit should be at or slightly above 50%. With those criteria, it was determined that a flow rate between 1.5 and 3 GPM would suffice to adequately clean the hole (Bilgesu et al 2017). The resulting calculations at varying flow rates are given in Table 2.…”