| Popis: |
This paper presents a multi-dimensional optimization engine for optimizing real-time drilling operations by increasing Rate of Penetration (ROP) while reducing Non-Productive Time (NPT) events such as vibration, stick slip, and directional divergence. A key breakthrough here is the development of the vibration health monitoring tool that tracks and filters out recent drilling parameters responsible for high vibration and monitors the overall BHA health. Measurement While Drilling (MWD) or Rotary Steerable (RSS) providers often provide vibration data but are rarely used in real-time decision making by operators due to the lack of a standardized workflow and technology. A vibration monitoring tool is developed that consumes real-time data from downhole MWD/RSS providers for each axis - axial, lateral, and torsional. A database is created for common MWD/RSS tools containing information about moderate and severe thresholds for shock (G) and average (GRMS) values. The algorithm categorizes vibration data into "low", "medium" or "high". The overall tool health is computed by tracking the cumulative count of the shock values and time corresponding to the moderate and severe categories and comparing against the downhole provider’s specifications. A multivariate objective function is used to find the optimal Differential Pressure (DPRES) and Top Drive RPM (TDRPM) values from a parameter sweep within user-specified limits or default tool limits. The objective function consists of three components - ROP, downhole MSE, and rotational tendency. A machine-learning model is used to predict ROP as a function of DPRES and TDRPM values, whereas standard drilling equations are used for calculating MSE and rotational tendency. After eliminating the parameters correlated with high vibration or stick-slip instances in the previous 1,000 ft, the optimization engine recommends DPRES and TDRPM values that correspond to the minimum value of the objective function. The recommendations from the multivariate objective function are presented in the form of a drilling advisory system. The advisory system was tested live on a drilling rig in collaboration with an operator. The results from the field test are presented in the paper. |
