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.

One of the responsibilities of a directional driller (DD) is the computation of the current bit position given the last survey station measurement, and with that information calculate the path back to plan if directional correction is needed. Having only a few minutes during a drilling connection to perform these calculations, the DD is limited to compute only a handful of possible paths that will be presented to the Drilling Engineer/Company Man. With this information, the Company Man will decide which path to follow. The present work aims to develop a computer algorithm that replicates the field knowledge of DDs but can compute hundreds of paths in less than one minute. In addition, since the objective of the trajectory correction may differ, the algorithm also can optimize for one of three goals: maximum rate of penetration (ROP), minimum tortuosity in the path, or maximum footage in the drilling target window. The paper presents examples of four different path recommendations in the lateral portion of a horizontal well. The results show the optimum recommended paths for the same position for a specific optimization goal. Finally, a comparison between the running time and number of paths computed is presented. All results were obtained during the validation tests of the algorithm.

During drilling, surveys to determine the wellbore trajectory are performed at every drilling connection. However, due to the offset between the survey instrument and the bit (typically between 30-100 ft), this survey represents the sensor's position which is lagged compared to the bit. This paper describes a method to automatically calculate projections to the bit in real-time utilizing multiple data sources: WITSML stream, BHA components and rotary trend analysis while rotary drilling. The projection to the bit calculation routine is performed in real time every 30 seconds. This paper presents results of projections for four horizontal unconventional wells drilled in West Texas. Nearly 75,000 projections were generated on the four wells, validated with 839 survey stations, with median divergence of the projections from the nearest survey stations being less than one foot.

No abstract