Autonomous Directional Drilling Simulator Development for the Drillbotics 2021-2022 Virtual Competition

Abstract

The work focuses on the drilling control algorithms as well as Artificial Intelligence (AI) technique implementation into an in-house real-time drilling simulator developed by the Drillbotics® Virtual Rig Team from the University of Stavanger, the winner of 2021-2022 Drillbotics Competition. The designed simulator consists of a topside model capable of calculating block position, surface hookload, surface torque, and bottom hole pressure. To achieve drilling efficiency, a formation-based rate of penetration (ROP) optimization module is running in real-time, where the safe-operational windows are considered to reduce/avoid drilling accidents, like stick-slip, axial vibrations, poor hole cleaning, and low efficiency etc. The obtained optimal WOB and RPM by solving such ROP optimization are used as setpoints and then fed into the rotary steerable system module (RSS module) to steer the bit following a planned path. Such path is designed with multiple Bezier curves that can pass given target coordinates and maintain low dogleg severity (DLS). Furthermore, the high-tech AI methodologies are integrated to the simulator to smartly manage downhole pressure via perceiving and interpreting the data, learning through the trial, training through given policy, and taking optimal actions offered by the AI-agent. The simulator is demonstrated to be a powerful and user-friendly tool for path design and optimization, real-time path control, and drilling performance optimization. It provides interactive and automatic operations of steering a bit passing multiple given target points and optimizing drilling behaviors to achieve high efficiency and low costs. From the results, the simulated (real-time) trajectory steered by the automatic RSS module integrating with surface drilling/control modules has small deviations from the planned trajectory. In the meanwhile, the simulator can precisely detect formation changes, accurately control the downhole pressure, and automatically optimize the drilling speed. The progress of the whole simulation can be followed through the web-based graphical user interface (GUI) remotely, where the depth-base data view, time-base data view and 3D graphical wellbore trajectories are visualized. After drilling, data analytics is conducted so that useful information from operational drilling data can be extracted and subsequently evaluated for post well-analysis.