Well planning based on hazard predictive models
A method to design well trajectories includes determining dogleg severity as a function of inclination, and a corresponding rate of penetration performance of the tool by a hybrid model including physical modelling and machine learning correction. The method includes solving for optimal steering parameters to predict a dogleg severity as close as possible to a desired dogleg severity at a given inclination of the trajectory, which is repeated for dogleg severity and inclination combinations of interest. The rate of penetration for feasible points is also determined and a rate of penetration (or time-to-target) map can be produced. Potential trajectories are then evaluated relative to the map to estimate drilling time-to-target, and an optimal trajectory can be selected that has a lowest time-to-target while also being feasible for the tool and optionally avoiding risks or downhole obstacles.
1. A method for planning a wellbore, the method comprising:
obtaining geological data corresponding to a geographic area including plurality of offset wellbores;
obtaining drilling operational data from drilling of the plurality of offset wellbores;
identifying hazard events that occurred during drilling of the plurality of offset wellbores, wherein the hazard events include drilling fluid loss events in the plurality of offset wellbores;
correlating the hazard events with geological features in the geological data and with the drilling operational data;
building a hazard predictive model based on the correlating of the hazard events with the geological features and the drilling operational data, wherein the hazard predictive model predicts drilling fluid loss events in the wellbore; and
developing a well plan based on the hazard predictive model.
2. The method of claim 1 , wherein developing the well plan includes determining characteristics of drilling mud for use in drilling the wellbore based on the hazard predictive model.
3. The method of claim 1 , wherein developing the well plan includes selecting a drilling tool or system based on the hazard predictive model.
4. The method of claim 1 , wherein developing the well plan includes changing a trajectory of the wellbore based on the hazard predictive model to avoid a geological feature associated with a predicted fluid loss event.
5. The method of claim 4 , wherein changing the trajectory includes evaluating a time to target for multiple trajectories.
6. The method of claim 5 , wherein changing the trajectory includes selecting a target trajectory having a lowest time to target.
7. The method of claim 4 , wherein changing the trajectory includes separating the trajectory into at least an upper section and a lower section.
8. The method of claim 1 , wherein the geological features include one or more of: a formation; a discrete fracture network; or faults.
9. The method of claim 1 , wherein the drilling operational data includes one or more of: drilling mud properties; drilling mud pressure; drilling system design; weight-on-bit; motor speed; bit diameter; steering system type; or bit type.
10. A wellbore planning system, the wellbore planning system comprising:
a downhole drilling tool;
a processor and memory, the memory including instructions which, when accessed by the processor, cause the processor to:
obtain geological data and drilling operational data for a plurality of offset wellbores;
identify hazard events that occurred during drilling of the plurality of offset wellbores based on the geological data and the drilling operational data for the plurality of offset wellbores, wherein the hazard events include drilling fluid loss events in the plurality of offset wellbores;
correlate the hazard events with geological features in the geological data and with the drilling operational data;
build a hazard predictive model based on the correlating of the hazard events with the geological features and the drilling operational data, wherein the hazard predictive model predicts drilling fluid loss events in the wellbore; and
develop a well plan for the downhole drilling tool based on the hazard predictive model.
11. The wellbore planning system of claim 10 , wherein developing the well plan includes changing a trajectory of the wellbore based on the hazard predictive model to avoid a geological feature associated with a predicted fluid loss event.
12. The wellbore planning system of claim 11 , wherein changing the trajectory includes evaluating a time to target for multiple trajectories.
13. The wellbore planning system of claim 12 , wherein changing the trajectory includes selecting a target trajectory having a lowest time to target.
14. The wellbore planning system of claim 11 , wherein changing the trajectory includes separating the trajectory into at least an upper section and a lower section.
15. The wellbore planning system of claim 10 , wherein the memory further includes instructions which, when accessed by the processor, cause the processor to drill the wellbore with the downhole drilling tool.