Neural net for use in drilling simulation

• US 8,285,531 B2
• Filed: 04/17/2008
• Issued: 10/09/2012
• Est. Priority Date: 04/19/2007
• Status: Active Grant

• Current Assignee: Smith International Incorporated (SLB)
• Original Assignee: Smith International Incorporated (SLB)
• Inventors: Moran, David P., Frenzel, Mark P., Duncan, Roy
• Primary Examiner(s): Jacob, Mary C
• Assistant Examiner(s): Chad, Aniss
• Application Number:
  US12/105,108
• Publication Number:
  US 20080262810A1
• Time in Patent Office: 1,636 Days
• Field of Search: 703/6, 703/10, 706/17, 706/50
• US Class Current: 703/10
• CPC Class Codes: E21B 2200/22 Fuzzy logic, artificial intelligence, neural networks or the like
• CPC Class Codes: E21B 44/00 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 Class Codes: E21B 7/00 Special methods or apparatus for drilling
• CPC Class Codes: G05B 13/027 using neural networks only
• CPC Class Codes: G05B 17/02 electric

Abstract

A method of optimizing a drilling tool assembly including inputting well data into an optimization system, the optimization system having an experience data set and an artificial neural network. The method further including comparing the well data to the experience data set and developing an initial drilling tool assembly based on the comparing the well data to the experience data, wherein the drilling tool assembly is developed using the artificial neural network. Additionally, the method including simulating the initial drilling tool assembly in the optimization system and creating result data in the optimization system based on the simulating.

Claims

1. A method of optimizing a drilling tool assembly comprising:

inputting well data into an optimization system, the optimization system including an experience data set and an artificial neural network;

comparing the well data to the experience data set;

developing an initial drilling tool assembly based on the comparing the well data to the experience data, wherein the drilling tool assembly is developed using the artificial neural network;

simulating the initial drilling tool assembly in the optimization system;

creating result data in the optimization system based on the simulating; and

optimizing the drilling tool assembly based on the result data.

2. The method of claim 1,

wherein the optimizing the drilling tool assembly comprises:

adjusting at least one drilling tool assembly design parameter of the initial drilling tool assembly based on the result data to produce an adjusted drilling tool assembly;

re-simulating the adjusted drilling tool assembly in the optimization system to produce a second result data; and

adjusting at least one drilling tool assembly design parameter of the adjusted drilling tool assembly based on the second result data.

3. The method of claim 2, further comprising:

continuing the optimizing until an optimized drilling tool assembly condition is achieved.

4. The method of claim 2, wherein the adjusting at least one drilling tool assembly design parameter comprises:

adjusting the location of a drilling assembly component on a drill string.

5. The method of claim 1, wherein the experience data comprises at least one selected from a group consisting of historical bit run data, offset well data, and prior simulation data.

6. The method of claim 1, wherein the drilling tool assembly design parameter is at least one selected from a group consisting of a bit, a cutting element, a drilling tool assembly component, a mud weight, a weight on bit, a rotary torque, a rotary speed, a lateral force on bit, a ratio of forces on cones, a ratio of forces between the cones, a distribution of forces on cutting elements, a volume of formation cut, and a wear on cutting elements.

7. The method of claim 1, further comprising:

generating a drilling tool assembly order based on the result data; and

outputting the drilling tool assembly order.

8. The method of claim 7, wherein the drilling tool assembly order comprises at least one of a group consisting of a bit, a drilling fluid, a shaker screen, a tubular, and a drill collar, a sub, a stabilizer, a heavy weight drill plate, a downhole measurement device, and a downhole drive device.

9. The method of claim 7, wherein the outputting the drilling assembly order comprises:

generating paperwork for ordering the drilling tool assembly.

10. The method of claim 1, further comprising:

generating a surface equipment order; and

outputting the surface equipment order.

11. The method of claim 10, wherein the surface equipment order comprises at least one of a drilling fluid, a shaker, a shaker screen, a thermal desorption unit, a centrifuge, an environmental unit, a cleaning operation, and a hydrocyclone.

12. The method of claim 1, wherein the experience data set is stored in a remote web store.

13. The method of claim 12, wherein the remote web store is accessible by the artificial neural network.

14. The method of claim 1, wherein the well data comprises at least one of a group consisting of a well type, a formation type, an acceptable vibrational signature, an acceptable rate of penetration, an acceptable wear rate, and an acceptable well path direction.

15. The method of claim 1, further comprising:

training the artificial neural network with the experience data set before developing the initial drilling tool assembly.

16. The method of claim 1, further comprising:

inputting drilling assembly requirements into the optimization system.

17. The method of claim 16, wherein the drilling assembly requirements comprises at least one required drilling assembly component.

18. The method of claim 16, wherein the drilling assembly requirements comprises a list of available components.

19. The method of claim 16, wherein the drilling assembly requirements comprises at least one starting location for a drilling assembly component.

20. A method of manufacturing a drilling tool assembly according to the method of claim 1.

21. A method of designing a drilling tool assembly comprising:

inputting well data into an optimization system, the optimization system including an experience data set and an artificial neural network;

comparing the well data to the experience data set;

developing an initial drilling tool assembly based on the comparing the well data to the experience data, wherein the initial drilling tool assembly is developed using the artificial neural network;

simulating the drilling assembly in the optimization system;

determining a vibrational signature of the initial drilling tool assembly; and

adjusting the initial drilling tool assembly based on the vibrational signature to produce an adjusted drilling tool assembly.

22. The method of claim 21, wherein the adjusting the initial drilling tool assembly based on the vibrational signature comprises:

adjusting the location of a drilling tool assembly component on a drill string.

23. The method of claim 22, further comprising:

simulating the adjusted drilling tool assembly in the optimization system;

adjusting at least one drilling assembly design parameter based on the simulation of the adjusted drilling tool assembly; and

terminating the simulating and the adjusting when the drilling assembly is optimized.