A MACHINE LEARNING BASED GEOTHERMAL DRILLING OPTIMIZATION SYSTEM USING EM SHORT-HOP TELEMETRY OF BIT DYNAMICS MEASUREMENTS

There is currently no cost-effective way to accurately measure the forces and accelerations acting on a drill bit in a hard-rock geothermal well and to then transmit that information uphole to the driller in a timeframe that allows its use in optimizing drilling performance. Consequently, drilling tends to be slow and drill bits suffer short lives, so geothermal wells tend to cost much more than oil and gas wells drilled to the same depth. If an accurate assessment of the dynamic state of the drill bit could be provided to a geothermal driller in near-real time, drilling parameters on the rig could be set to maximize the penetration rate and minimize bit damage in hydrothermal and Enhanced Geothermal System (EGS) wells. This would lead to cost reductions that are needed to improve access to the load-based power potential of geothermal resources, which is a major goal of the U.S. Department of Energy’s Geothermal Technology Office in its efforts to advance geothermal utilization for the benefit of the public. Near-bit sensors and a short-hop communication loop will be combined with an existing directional drilling tool and uphole data analytics to create the Geothermal Drilling Optimization System. This system will have the capability to: 1) measure dynamic drill bit forces and accelerations; 2) process the data downhole to determine weight-on-bit, torque, and rotary speed values and variances; 3) use pattern-recognition algorithms to identify any bit vibration modes indicative of bit dysfunction; 4) deliver the summarized bit dynamic-state data to the surface using state-of-the art, through-the-earth electromagnetic transmission technology; and 5) display dynamic-state data and expert-system advice for the driller on how to modify the drilling parameters to optimize drill bit performance and life. In the first phase of the project, a detailed System Design Document will be written that develops conceptual designs and specifications for the various components of the proposed system, assesses the feasibility of the system, and estimates the cost and development challenges required to build a working system. A prototype bench-scale short-hop transmission loop will also be designed, fabricated, and tested in the lab and on the surface in the field to answer several key feasibility issues. Finally, a rudimentary library of bit dysfunction vibration patterns will be developed, algorithms for identifying these patterns will be written, data latency effects on drilling control will be assessed, the methodology for implementing machine-learning will be explored, and the implementation of rig data and downhole data in an expert system for drilling optimization will be defined.Following Phase I, a successful Phase II project would result in a field- tested Geothermal Drilling Optimization System ready for commercialization.