Automated well productivity estimation and continuous average well pressure monitoring through integration of real-time surface and downhole pressure and temperature measurements

Patent metadata

Field	Value
Publication number	US-12037901-B2
Application number	US-202117215547-A
Country	US
Kind code	B2
Filing date	Mar 29, 2021
Priority date	Mar 31, 2020
Publication date	Jul 16, 2024
Grant date	Jul 16, 2024

Abstract

Systems and methods for intelligent estimation of productivity index and reservoir pressure values using pressure sensors, a neural network model comprising historical flow rate data of at least a well bore, and a data processor. The pressure sensors generate pressure data associated with a well bore's surface point and a downhole point. The data processor, communicatively coupled to the two pressure sensors and the neural network model, is operable to receive the pressure data from the sensors respectively indicative of pressure at each of the two points, estimate a real-time productivity index value in real-time based on the pressure data from the pressure sensors and the historical flowrate data of the neural network model, and estimate a reservoir pressure value of the well bore at a flowing condition, a reservoir pressure value of the well bore at a shut-in condition, or both, based on the real-time productivity index.

First claim

What is claimed is:

1. An intelligent estimation system comprising at least two pressure sensors, a neural network model, and a data processor, wherein:
the at least two pressure sensors are configured to generate well parameters comprising at least pressure data respectively associated with two points of a well bore, the two points comprising a surface point of the well bore and a downhole point of the well bore, wherein the well parameters further comprise at least a measured or estimated bottomhole pressure of the well bore;
the neural network model comprises historical flowrate data associated with at least the well bore; and
the data processor is communicatively coupled to the at least two pressure sensors and the neural network model and is operable to:
receive the well parameters comprising (i) the pressure data from the at least two pressure sensors respectively indicative of pressure at each of the two points of the well bore and (ii) the measured or estimated bottomhole pressure of the well bore,
estimate a real-time productivity index value in real-time based on (i) the well parameters comprising the pressure data from the at least two pressure sensors and the measured or estimated bottomhole pressure of the well bore and (ii) the historical flowrate data of the neural network model, and
estimate a reservoir pressure value of the well bore at a flowing condition, a reservoir pressure value of the well bore at a shut-in condition, or both, based on the real-time productivity index.

2. The intelligent estimation system of claim 1 , wherein the data processor is operable to estimate the real-time productivity index by solving:

J
⁡
(

Productivity
⁢

Index

)

=

Q

P
r

-

P
wf

,

wherein J is representative of the real-time productivity index value, Q is representative of a surface flowrate at standard conditions for the well bore, P r is representative of a reservoir pressure for the well bore, and P wf is representative of a flowing bottomhole pressure for the well bore.

3. The intelligent estimation system of claim 2 , wherein Q is based on the historical flowrate data, P r is an input associated with a pressure point after a pressure buildup is stabilized and based on the pressure data, and P wf is an input associated with a last flowing pressure point before the pressure buildup is initiated and based on the pressure data.

4. The intelligent estimation system of claim 1 , further comprising a flowmeter configured to provide a flowrate associated with the well bore, wherein the data processor is operable to estimate the real-time productivity index by solving:

J
⁡
(

Productivity
⁢

Index

)

=

Q

P
r

-

P
wf

,

wherein J is representative of the real-time productivity index value, Q is representative of a surface flowrate at standard conditions for the well bore based on the flowrate from the flowmeter, P r is representative of a reservoir pressure for the well bore, and P wf is representative of a flowing bottomhole pressure for the well bore.

5. The intelligent estimation system of claim 1 , wherein the data processor is further operable to:
generate a productivity index graphical representation including the real-time productivity index value for the well bore; and
display the productivity index graphical representation in real-time.

6. The intelligent estimation system of claim 5 , wherein the data processor is further operable to:
display the productivity index graphical representation comprising each real-time productivity index value for a plurality of well bores, the plurality of well bores comprising the well bore.

7. The intelligent estimation system of claim 1 , wherein the data processor is further operable to:
generate a reservoir pressure graphical representation including the reservoir pressure value of the well bore at the flowing condition, the reservoir pressure value of the well bore at the shut-in condition, or both; and
display the reservoir pressure graphical representation.

8. The intelligent estimation system of claim 7 , wherein the data processor is further operable to:
display the reservoir pressure graphical representation comprising each reservoir pressure value of each well bore at the flowing condition, the shut-in condition, or both, for a plurality of well bores, the plurality of well bores comprising the well bore.

9. The intelligent estimation system of claim 1 , wherein the data processor is operable to determine when the well bore is in the flowing condition, the shut-in condition, or both, based on the pressure data and received temperature data to identify exact pressure build-up periods indicative of the shut-in condition.

10. An intelligent estimation system comprising at least two pressure sensors, a neural network model, and a data processor, wherein:
the at least two pressure sensors are configured to generate well parameters comprising at least pressure data respectively associated with two points of a well bore, the two points comprising a surface point of the well bore and a downhole point of the well bore of a plurality of well bores, the well parameters further comprising at least a measured or estimated bottomhole pressure of the well bore of the plurality of well bores;
the neural network model comprises historical flowrate data associated with at least the well bore of the plurality of well bores; and
the data processor is communicatively coupled to the at least two pressure sensors and the neural network model and is operable to:
receive the well parameters comprising (i) the pressure data from the at least two pressure sensors respectively indicative of pressure at each of the two points of the well bore and (ii) the measured or estimated bottomhole pressure of the well bore,
estimate a real-time productivity index value of the well bore in real-time based on (i) the well parameters comprising the pressure data from the at least two pressure sensors and the measured or estimated bottomhole pressure of the well bore (

Assignees

• Saudi Arabian Oil Co

Inventors

• Al Shahri Ali M
• Al Shuaibi Anas A
• Kanfar Mohammed Sami
• Dosary Kalid Saad
• Alsaleh Abdulaziz A

Classifications

• G01V9/02

  Determining existence or flow of underground water · CPC title

• E21B47/06 Primary

  Measuring temperature or pressure · CPC title

• E21B2200/22

  Fuzzy logic, artificial intelligence, neural networks or the like · CPC title

• E21B2200/20

  Computer models or simulations, e.g. for reservoirs under production, drill bits · CPC title

• E21B49/087 Primary

  Well testing, e.g. testing for reservoir productivity or formation parameters · CPC title