Well control systems and associated methods

• US 20070168056A1
• Filed: 01/17/2006
• Published: 07/19/2007
• Est. Priority Date: 01/17/2006
• Status: Active Grant

• Current Assignee: Halliburton Energy Services Incorporated (Halliburton Company)
• Original Assignee: Halliburton Energy Services Incorporated (Halliburton Company)
• Inventors: Chen, Dingding, Schultz, Roger, Shayegi, Sara, Godfrey, Craig
• Granted Patent: US 7,610,251 B2
• Time in Patent Office: Days
• US Class Current: 700/48
• CPC Class Codes: E21B 2200/22 Fuzzy logic, artificial intelligence, neural networks or the like
• CPC Class Codes: G05B 13/048 using a predictor

Abstract

Well control systems and associated methods. A well control method includes the steps of drilling a wellbore and predicting a change in flow between the wellbore and a reservoir prior to the change occurring, the predicting step being performed, and the change in flow occurring while drilling. Another well control method includes the steps of: sensing at least one first drilling operation variable while drilling a wellbore, thereby generating first sensed variables; sensing at least one second drilling operation variable while drilling the wellbore, thereby generating second sensed variables; and training a predictive device, using the first and second sensed variables, to predict the second drilling operation variable at a selected time.

Claims

1. A well control method, comprising the steps of:

drilling a wellbore; and

predicting a change in flow between the wellbore and a reservoir prior to the change occurring, the predicting step being performed during the drilling step, and the change in flow occurring during the drilling step.

2. The method of claim 1, wherein the change in flow is an increased rate of fluid flow from the reservoir into the wellbore.

3. The method of claim 1, wherein the predicting step is performed by a predictive device.

4. The method of claim 3, wherein the predictive device includes a neural network.

5. The method of claim 3, wherein the predictive device includes an artificial intelligence device.

6. The method of claim 3, wherein the predictive device includes a genetic algorithm.

7. The method of claim 3, wherein the predictive device performs a regression analysis.

8. The method of claim 3, wherein the predictive device utilizes granular computing.

9. The method of claim 3, wherein the predictive device includes an adaptive model.

10. The method of claim 9, wherein an output of a first principle model is input to the adaptive model.

11. The method of claim 3, wherein the predictive device includes a nonlinear function which generalizes for real systems.

12. The method of claim 3, wherein the predictive device includes a floating point processing device.

13. The method of claim 3, wherein the predicting step includes adjusting terms in the predictive device based on derivatives of output of the predictive device with respect to the terms.

14. The method of claim 3, further comprising the step of training the predictive device.

15. The method of claim 14, wherein the training step further comprises inputting to the predictive device data obtained during the drilling step.

16. The method of claim 14, wherein the training step further comprises inputting to the predictive device data obtained while drilling at least one prior wellbore.

17. The method of claim 14, wherein the training step further comprises inputting to the predictive device data indicative of past errors in predictions produced by the predictive device.

18. The method of claim 1, wherein the drilling step is performed with an underbalanced condition in the wellbore.

19. The method of claim 1, wherein the drilling step is performed with a balanced condition in the wellbore.

20. The method of claim 1, wherein the drilling step is performed with an overbalanced condition in the wellbore.

21. The method of claim 1, wherein the drilling step is performed while fluid flows from the reservoir into the wellbore.

22. The method of claim 1, wherein the drilling step includes circulating fluid from the reservoir to a surface location.

23. The method of claim 1, wherein the change in flow between the wellbore and the reservoir occurs after the predicting step.

24. The method of claim 1, wherein the change in flow is an increased rate of flow from the wellbore to the reservoir.

25. The method of claim 1, wherein the predicting step further comprises predicting a change in bottom hole pressure during the drilling step.

26. The method of claim 1, wherein the predicting step includes performing regression on a nonlinear function.

97. The method of claim 1, further comprising the step of varying a restriction to flow through a choke in response to the predicting step.

98. The method of claim 97, wherein the varying step alters the predicted change in flow.

27. A well control method, comprising the steps of:

sensing a drilling operation variable while drilling a wellbore, thereby generating sensed variables;

intermittently transmitting the sensed variables; and

training a predictive device, using the sensed variables, to predict a value of the drilling operation variable occurring between transmissions of the sensed variables.

28. The method of claim 27, wherein the sensing step is performed in the wellbore.

29. The method of claim 27, wherein the sensing step is performed at a surface location.

30. The method of claim 27, wherein the predictive device includes a neural network.

31. The method of claim 27, wherein the predictive device includes an artificial intelligence device.

32. The method of claim 27, wherein the predictive device includes a genetic algorithm.

33. The method of claim 27, wherein the predictive device performs a regression analysis.

34. The method of claim 27, wherein the predictive device utilizes granular computing.

35. The method of claim 27, wherein the predictive device includes an adaptive model.

36. The method of claim 35, wherein an output of a first principle model is input to the adaptive model.

37. The method of claim 27, wherein the predictive device includes a nonlinear function which generalizes for real systems.

38. The method of claim 27, wherein the predictive device includes a floating point processing device.

39. The method of claim 27, wherein the training step includes adjusting terms in the predictive device based on derivatives of output of the predictive device with respect to the terms.

40. The method of claim 27, wherein the training step further comprises inputting to the predictive device data obtained while drilling at least one prior wellbore.

41. The method of claim 27, wherein the training step further comprises inputting to the predictive device data indicative of past errors in predictions produced by the predictive device.

42. The method of claim 27, wherein the drilling operation variable is a rate of fluid flow between a reservoir and the wellbore.

43. The method of claim 27, wherein the drilling operation variable is a change in flow rate between a reservoir and the wellbore.

44. The method of claim 27, wherein drilling the wellbore is performed in an underbalanced condition.

45. The method of claim 27, wherein drilling the wellbore is performed in a balanced condition.

46. The method of claim 27, wherein drilling the wellbore is performed in an overbalanced condition.

47. The method of claim 27, wherein the drilling operation variable is at least one of pressure, pressure differential, temperature, flow rate, produced gas rate, produced liquid rate, produced solids rate, true vertical depth, rate of penetration, bottom hole pressure, and fluid properties.

99. The method of claim 27, further comprising the step of varying a restriction to flow through a choke based on the value predicted in the training step.

100. The method of claim 99, wherein the varying step alters the predicted value.

48. A well control method, comprising the steps of:

sensing at least one first drilling operation variable while drilling a wellbore, thereby generating first sensed variables;

sensing at least one second drilling operation variable while drilling the wellbore, thereby generating second sensed variables; and

training a predictive device, using the first and second sensed variables, to predict the second drilling operation variable at a selected time.

49. The method of claim 48, further comprising the step of utilizing the trained predictive device to predict the second drilling operation variable at the selected time when the second sensed variable is unavailable.

50. The method of claim 48, wherein the selected time is when the first sensed variable is available, but the second sensed variable is unavailable.

51. The method of claim 48, wherein the second sensed variable is a rate of fluid flow between the wellbore and a reservoir.

52. The method of claim 48, wherein the second sensed variable is at least one of pressure, pressure differential, surface temperature, downhole temperature, multiphase flow rate, and single phase flow rate.

53. The method of claim 48, wherein the second sensed variable is at least one of rate of penetration and bottom hole pressure.

54. The method of claim 48, wherein the predictive device includes a neural network.

55. The method of claim 48, wherein the predictive device includes an artificial intelligence device.

56. The method of claim 48, wherein the predictive device includes a genetic algorithm.

57. The method of claim 48, wherein the predictive device performs a regression analysis.

58. The method of claim 48, wherein the predictive device utilizes granular computing.

59. The method of claim 48, wherein the predictive device includes an adaptive model.

60. The method of claim 59, wherein an output of a first principle model is input to the adaptive model.

61. The method of claim 48, wherein the predictive device includes a nonlinear function which generalizes for real systems.

62. The method of claim 48, wherein the predictive device includes a floating point processing device.

63. The method of claim 48, wherein the training step includes adjusting terms in the predictive device based on derivatives of output of the predictive device with respect to the terms.

64. The method of claim 48, wherein the training step further comprises inputting to the predictive device data obtained while drilling at least one prior wellbore.

65. The method of claim 48, wherein the training step further comprises inputting to the predictive device data indicative of past errors in predictions produced by the predictive device.

66. The method of claim 48, wherein the second drilling operation variable is a rate of fluid flow between a reservoir and the wellbore.

67. The method of claim 48, wherein the second drilling operation variable is a change in flow rate between a reservoir and the wellbore.

68. The method of claim 48, wherein drilling the wellbore is performed in an underbalanced condition.

69. The method of claim 48, wherein drilling the wellbore is performed in a balanced condition.

70. The method of claim 48, wherein drilling the wellbore is performed in an overbalanced condition.

71. The method of claim 48, wherein the second drilling operation variable is at least one of pressure, pressure differential, temperature, flow rate, bottom hole pressure, rate of penetration, rate of fluid flow between the wellbore and a reservoir, change in flow rate between the wellbore and the reservoir, produced gas rate, produced liquids rate, produced solids rate, true vertical depth, fluid properties, separator pressure, differential pressure across a choke, and annulus pressure.

72. The method of claim 48, wherein the selected time is a time after the training step is performed.

73. The method of claim 48, wherein a flow coefficient Cv of a choke is used in the training step as an input to train the predictive device.

101. The method of claim 48, further comprising the step of varying a restriction to flow through a choke based on the second drilling operation variable predicted in the training step.

102. The method of claim 101, wherein the varying step alters the predicted second drilling operation variable.

74. A well control method, comprising the steps of:

sensing at least one first drilling operation variable while drilling a first wellbore, thereby generating first sensed variables;

sensing at least one second drilling operation variable while drilling a second wellbore, thereby generating second sensed variables; and

training a predictive device, using the first and second sensed variables, to predict the second drilling operation variable at a selected time.

75. The method of claim 74, further comprising the step of utilizing the trained predictive device to predict the second drilling operation variable at the selected time when the second sensed variable is unavailable.

76. The method of claim 74, wherein the selected time is when the first sensed variable is available, but the second sensed variable is unavailable.

77. The method of claim 74, wherein the second sensed variable is a rate of fluid flow between the second wellbore and a reservoir.

78. The method of claim 74, wherein the second sensed variable is at least one of pressure, pressure differential, surface temperature, downhole temperature, multiphase flow rate, and single phase flow rate.

79. The method of claim 74, wherein the predictive device includes a neural network.

80. The method of claim 74, wherein the predictive device includes an artificial intelligence device.

81. The method of claim 74, wherein the predictive device includes a genetic algorithm.

82. The method of claim 74, wherein the predictive device performs a regression analysis.

83. The method of claim 74, wherein the predictive device utilizes granular computing.

84. The method of claim 74, wherein the predictive device includes an adaptive model.

85. The method of claim 84, wherein an output of a first principle model is input to the adaptive model.

86. The method of claim 74, wherein the predictive device includes a nonlinear function which generalizes for real systems.

87. The method of claim 74, wherein the predictive device includes a floating point processing device.

88. The method of claim 74, wherein the training step includes adjusting terms in the predictive device based on derivatives of output of the predictive device with respect to the terms.

89. The method of claim 74, wherein the training step further comprises inputting to the predictive device data indicative of past errors in predictions produced by the predictive device.

90. The method of claim 74, wherein the first drilling operation variable is a rate of fluid flow between a reservoir and the first wellbore.

91. The method of claim 74, wherein the first drilling operation variable is a change in flow rate between a reservoir and the first wellbore.

92. The method of claim 74, wherein drilling the second wellbore is performed in an underbalanced condition.

93. The method of claim 74, wherein drilling the second wellbore is performed in a balanced condition.

94. The method of claim 74, wherein drilling the second wellbore is performed in an overbalanced condition.

95. The method of claim 74, wherein the first drilling operation variable is at least one of pressure, pressure differential, temperature, and flow rate.

96. The method of claim 74, wherein the selected time is a time after the training step is performed.

103. The method of claim 74, further comprising the step of varying a restriction to flow through a choke based on the second drilling operation variable predicted in the training step.

104. The method of claim 103, wherein the varying step alters the predicted second drilling operation variable.