Drilling advisory systems and methods with combined global search and local search methods

Patent metadata

Field	Value
Publication number	US-9436173-B2
Application number	US-201213605453-A
Country	US
Kind code	B2
Filing date	Sep 6, 2012
Priority date	Sep 7, 2011
Publication date	Sep 6, 2016
Grant date	Sep 6, 2016

Abstract

Combined methods and systems for optimizing drilling related operations include global search engines and local search engines to find the optimal value for at least one controllable drilling parameter, and a data fusion module to combine or select the operational recommendations from global and local search engines. The operational recommendations are used to optimize the objective function, mitigate dysfunctions, and improve drilling efficiency.

First claim

What is claimed is:

1. A method of drilling a wellbore through subterranean formation, the method comprising:
(a) receiving data regarding at least two drilling operational parameters related to wellbore drilling operations into an operating parameter database;
(b) computing a mathematical objective function based upon the received data for input into each of a global search engine and a local search engine;
(c) inputting the computed objective function and received data into the global search engine to create a global response surface, and to identify at least two global-engine recommended drilling parameters;
(d) inputting the computed objective function and received data into the local search engine to determine a significantly correlated drilling parameter, and to identify at least two local-engine recommended drilling parameters based upon the significantly correlated controllable drilling parameter;
(e) creating a combined dataset using a data fusion process by combining (i) the created global response surface, and (ii) the determined significantly correlated controllable drilling parameter and the local-engine recommended drilling parameters;
(f) using a decision tree process on the data fusion combined dataset to determine whether to define a status mode of the combined dataset as at least one of a learning mode and an application mode;
determining operational updates to at least one of the at least two controllable drilling parameters based at least in part on the further optimized recommendation; and
implementing at least one of the determined operational updates in the wellbore drilling operations.

2. The method of claim 1 , wherein the drilling operational parameters include at least one of weight on bit (WOB), drillstring rotary speed, drillstring torque, rate of penetration (ROP), drilling fluid flow rate, stand pipe pressure, differential pressure across a mud motor, depth-of-cut (DOC), bit friction coefficient mu, and mechanical specific energy (MSE).

3. The method of claim 1 , wherein using the decision tree process on the data fusion combined dataset to determine whether to define the status mode of the combined dataset as at least one of the learning mode and the application mode further comprises the steps of:
determining whether an acceptable variation in drilling operational parameters exists within the global search engine response surface;
determining whether the drilling operations are occurring in the same formation as other data within the operating parameter database; and
determining whether the drilling operations are experiencing a drilling dysfunction.

4. The method of claim 1 , wherein the received data is temporarily accumulated in a moving memory window as the operating parameter database, and wherein the global and local search engines use data from at least a portion of the moving memory window.

5. The method of claim 4 , wherein the moving memory window accumulates data in an interval based on at least one of time and depth; and wherein the length of the window is determined by a frequency of changing the controllable drilling parameters and by a lithology change.

6. The method of claim 1 , wherein the global search engine is based on a grid search method comprising at least one of: 9-point, simplex, golden search, and design of experiments (DOE) methods.

7. The method of claim 1 , wherein the global search engine is based on a grid search method comprising: (1) calculating an objective function from recorded data related to the at least two drilling operational parameters; (2) constructing a response surface by regression or interpolation methods from the objective function values, using at least one of least squares regression, quadratic interpolation or Delaunay triangulation; (3) finding an optimum value for the objective function from the response surface; and (4) determining the optimized controllable drilling parameter values associated with the optimum value of the response surface.

8. The method of claim 7 , wherein the objective function is based on at least one of: rate of penetration (ROP), depth of cut (DOC), mechanical specific energy (MSE), weight on bit (WOB), drillstring rotation rate, bit coefficient of friction (mu), bit rotation rate, torque applied to the drillstring, torque applied to the bit, vibration measurements, hydraulic horsepower, and mathematical combinations thereof.

9. The method of claim 1 , wherein the local search engine is based on at least one of principal component analysis (PCA), Powell's method, and gradient search.

10. The method of claim 1 , wherein a decision tree based on statistical quality metrics is used to select from the application status mode and the learning status mode.

11. The method of claim 1 , wherein a decision tree based on at least one drilling dysfunction map is used to select from the application status mode and the learning status.

12. The method of claim 1 , wherein a decision tree based on a combination of statistical quality metrics and at least one drilling dysfunction map is used to select from the application status mode and the learning status mode to generate operational recommendations.

13. The method of claim 1 , wherein the decision tree determines to define the status mode of the combined dataset as learning mode status and empties the data window, continues to receive drilling parameter data, recommends controllable drilling parameter values to a driller, and calculates a statistical quality metric of the received data.

14. The method of claim 1 , wherein at least one of the determined operational recommendations is implemented in the drilling operation substantially automatically.

15. The method of claim 1 , further comprising:
selecting one of;

(a) wherein if the decision tree status mode determination of step (f) is learning mode, then:
a. providing an additional data input for each of the at least two drilling operational parameters in the operating parameter database and repeating steps (b)-(f) for the additional data input for expanding the created global response surface and for revising the global-engine recommended drilling parameters; and
b. recommending use of the global-engine recommended drilling parameters for making an implementable drilling operational decision; and

(b) wherein if the decision tree status mode selection of step (f) is application mode, then comparing the global-engine recommended drilling parameters with the local-engine recommended drilling parameters;
a. wherein if the compared global-engine recommended drilling parameters and the local-engine recommended drilling parameters are determined to be correlated within a predefined range of agreement with each other, instructing to use either of the global-engine recommended or local-engine recommended set of correlated drilling parameters for use regarding drilling operations; and
b. wherein if the two sets are determined not within a predefined range of agreement with each other, re-perform the local search engine on the global-engine recommended drilling parameters to identify updated local-engine recommended drilling parameters, and instructing to use the local-engine recommended set of correlated drilling parameters for use regarding drilling operations.

16. A computer-based system for use in association with drilling operations, the computer-based system comprising:
a processor adapted to execute a programmed set of instructions;
a storage medium in communication with the processor; and
at least one instruction set accessible by the processor and saved in the storage medium

Assignees

• Wang Lei
• Remmert Stephen M
• Pastusek Paul E
• Bailey Jeffrey R
• Prim Matthew T
• Pais Darren
• Chang Dar-Lon
• Payette Gregory S
• Exxonmobil Upstream Res Co

Inventors

• Wang Lei
• Remmert Stephen M
• Pastusek Paul E
• Bailey Jeffrey R
• Prim Matthew T
• Pais Darren
• Chang Dar-Lon
• Payette Gregory S

Classifications

• G05B19/0405 Primary

  Program-control specially adapted for machine tool control and not otherwise provided for · CPC title

• G05B13/00

  Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion (G05B19/00 takes precedence) · CPC title

• G05B13/024

  in which a parameter or coefficient is automatically adjusted to optimise the performance · CPC title

• E21B44/00 Primary

  Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions · CPC title