Autonomous Directional Drilling Achieved With Industry 4.0 Platform

Abstract

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 204607, “Autonomous Directional-Drilling Planning and Execution Using an Industry 4.0 Platform,” by Samba Ba, SPE, Maja Ignova, and Kate Mantle, Schlumberger, et al. The paper has not been peer reviewed. _ In the complete paper, the authors present an autonomous-directional-drilling (ADD) framework using an Industry 4.0 platform built on intelligent planning and execution capabilities and supported by surface and downhole automation technologies to achieve consistent directional-drilling operations accessible for remote operations. This ADD framework minimizes operational risk and cost per foot drilled; maximizes performance and procedural adherence; and establishes consistent results across fields, rigs, and trajectories. Anatomy of ADD The authors write that they identified a need for technology to support all aspects of the drilling process, not just what happens at the wellsite or the bottomhole assembly (BHA). That meant focusing on intelligent planning and intelligent execution capabilities, along with surface automation that would complement the suite of downhole automation features of the steering tools. Fig. 1 highlights what the authors term the four pillars of ADD. To connect these pillars, an integrated data architecture is crucial. In the planning phase, all associated digital data are passed to the intelligent execution pillar to drive both surface and downhole automation. Once the execution phase is complete, the same data pipelines are leveraged to close a feedback loop that would drive further refinements of machine-learning (ML) models in the intelligent planning phase to start the cycle over again. Technology blocks within the pillars will evolve naturally as part of an agile development process. The intelligent execution is at the center of the system because it interacts with each component and manages information-sharing between them. Pillars of ADD Intelligent Planning. In the planning stage, an understanding of BHA steering performance is key. It is important to have a model that will predict BHA directional tendency accurately. Traditionally, physics models were used to quantify the response and qualify the trajectory plan. While physics models can provide very accurate tendency predictions with the help of historical operations data, the prediction accuracy can be improved. This is called a hybrid ML strategy, which combines historical data with the physics model, taking advantage of ML capabilities and synergies with domain knowledge. The Industry 4.0 platform enables the implementation of this hybrid model directly inside the new well-construction-planning portion of the platform. The engineering design will be validated automatically by comparing predicted tool-steering performance with the trajectory plan, with no human intervention required. With this model, the BHA, trajectory, and operating parameters can be optimized for application and delivered digitally for wellsite execution.