DOPPLER VS. SPINNER PLT SENSING FOR HYDROCARBON VELOCITY ESTIMATE BY DEEP-LEARNING APPROACH

Abstract

Logging hydrocarbon production potential of wells has been at the forefront of enhancing oil and gas exploration and maximize productivity from oil and gas reservoirs. A major challenge is accurate downhole fluid phases flow velocity measurements in production logging (PLT) due to the criticality of mechanical spinner-based sensor devices. Ultrasonic Doppler-based sensors are more robust and deployable either in wireline or logging while drilling (LWD) conditions; however, due to the different sensing physics, the measurement results may vary. Ultrasonic Doppler flow meters utilize the Doppler effect that is a change in frequency of the sound waves that are reflected on a moving target. A common example is the change in pitch when a vehicle sounding a horn approaches and recedes from an observer. The frequency shift is in direct proportion of the relative velocity of the fluid with respect to the emitter-receiver and allows to infer the speed of the flowing fluid. Doppler flow meters offer many advantages over mechanical spinners such as the ability to measure without requiring calibration passes, the absence of mechanical moving parts, the sensors robustness to shocks and hits, easy installation and minimal affection by changes in temperature, density and viscosity of the fluid thus capability to work even in highly contaminated conditions such as tar, asphaltene deposits on equipment. Despite being widely used in surface flow metering, ultrasonic Doppler sensor applications to downhole environment have been so far very limited. We present in this work an innovative deep learning framework to estimate spinner phase velocities from Doppler based sensor velocities. Tests of the framework on a benchmark data set displayed strong estimation results, in particular outlining the ability to utilize Doppler-based sensors for downhole phase velocity measurements and allows the comparison of the estimates with previously recorded spinner velocity measurements. This allows for the real-time automated interpretative framework implementation and flow velocity estimations either in conventional wireline production logging technologies and potentially also in LWD conditions, when the well is flowing in underbalanced conditions.