Synthetic gas-oil-ratio determination for gas dominant fluids

Patent metadata

Field	Value
Publication number	US-9542511-B2
Application number	US-201314650820-A
Country	US
Kind code	B2
Filing date	Dec 27, 2013
Priority date	Dec 27, 2013
Publication date	Jan 10, 2017
Grant date	Jan 10, 2017

Abstract

The disclosed embodiments include a method, apparatus, and computer program product for determining a synthetic gas-oil-ratio for a gas dominant fluid. For example, one disclosed embodiment includes a system that includes at least one processor, and at least one memory coupled to the at least one processor and storing instructions that when executed by the at least one processor performs operations that include optimizing a gas-oil-ratio database using a genetic algorithm and a multivariate regression simulator and generating a synthetic gas-oil-ratio for a gas dominant fluid. In one embodiment, optimizing a gas-oil-ratio database using a genetic algorithm and a multivariate regression simulator comprises defining gas-oil-ratio searching boundaries gas-oil-ratio for each gas dominant fluid; assigning randomly a synthetic gas-oil-ratio for each gas dominant fluid in a set of gas dominant fluids in the initial population of gas-oil-ratio data, wherein the gas-oil-ratio for each gas dominant fluid is within the searching boundaries; generating an initial population of gas-oil-ratio data for a set of gas dominant fluids; and evaluating synthetic gas-oil-ratio assignments for the initial population using the multivariate regression simulator.

First claim

The invention claimed is:

1. A computer-implemented method for determining a synthetic gas-oil-ratio for a gas dominant fluid, the method comprising:
optimizing a gas-oil-ratio database using a genetic algorithm and a multivariate regression simulator; and
generating the synthetic gas-oil-ratio for the gas dominant fluid.

2. The method of claim 1 , wherein optimizing a gas-oil-ratio database using a genetic algorithm and a multivariate regression simulator comprises:
defining gas-oil-ratio searching boundaries gas-oil-ratio for each gas dominant fluid;
generating an initial population of gas-oil-ratio data for a set of gas dominant fluids; and
evaluating synthetic gas-oil-ratio assignments for the initial population using the multivariate regression simulator.

3. The method of claim 2 , wherein generating an initial population of gas-oil-ratio data for the gas dominant fluids comprises:
assigning randomly a synthetic gas-oil-ratio for each gas dominant fluid in a set of gas dominant fluids in the initial population of gas-oil-ratio data, wherein the gas-oil-ratio for each gas dominant fluid is within the searching boundaries.

4. The method of claim 2 , wherein evaluating synthetic gas-oil-ratio assignments for the initial population using the multivariate regression simulator comprises:
combining the initial population of gas-oil-ratio data for a set of gas dominant fluids and a set of data for other fluids from a standard optical fluid library, wherein the step of combining forms a combined fluid set; and
calculating an overall gas-oil-ratio prediction error through a plurality of models having a plurality of inputs.

5. The method of claim 4 , wherein the plurality of models comprises at least one of a model comprising fluid chemical concentrations and physical property inputs, a model comprising optical sensor inputs, and a model comprising a combination of the model comprising fluid chemical concentration and physical property inputs and the model comprising optical sensor inputs.

6. The method of claim 4 , wherein calculating an overall gas-oil-ratio prediction error through a plurality of models having a plurality of inputs comprises:
calculating a cost function representing the overall gas-oil-ratio prediction error, wherein the cost function comprises a standard calibration error of gas-oil-ratio prediction for each model of the plurality of models.

7. The method of claim 6 , wherein the standard calibration error of gas-oil-ratio prediction for each model comprises a relative error over at least one of a low gas-oil-ratio oil and water-brine mixture, a medium gas-oil-ratio and live oil condensates mixture, and a high gas-oil-ratio gas.

8. The method of claim 4 , further comprising:
determining whether a stop criterion for the overall gas-oil-ratio prediction error is met; and
applying the genetic algorithm based on the overall gas-oil-ratio prediction error until the stop criterion is met.

9. The method of claim 8 , wherein applying the genetic algorithm based on the overall gas-oil-ratio prediction error until the stop criterion is met comprises:
ranking the overall gas-oil-ratio prediction error over the combined fluid samples; and
updating the gas-oil-ratio assigned for each gas dominant fluid using at least one of selection, crossover, and mutation method genetic operators through multiple generations of calculations to determine whether the stop criterion is met.

10. The method of claim 4 , wherein calculating an overall gas-oil-ratio prediction error through a plurality of models having a plurality of inputs comprises:
calculating a cost function representing the overall gas-oil-ratio prediction error using an equation:
F=L 1 ×SEC 1 +L 2 ×SEC 2 +L 3 ×SEC 3

wherein F is the cost function, L 1 , L 2 and L 3 are weighting coefficients, SEC 1 is a standard error of calibration for a gas-oil-ratio prediction calculated with a model comprising fluid chemical concentrations and physical properties inputs; SEC 2 is a standard error of calibration for a gas-oil-ratio prediction calculated with a model comprising optical sensor responses inputs; and SEC 3 is a standard error of calibration for a gas-oil-ratio prediction calculated with the model comprising a combination of the model comprising fluid chemical concentrations and physical properties inputs and the model comprising optical sensor inputs.

11. The method of claim 1 , further comprising:
recalibrating a universal gas-oil-ratio predictive model using a neural networks algorithm to include tool-specific inputs.

12. A system comprising:
at least one processor;
at least one memory coupled to the at least one processor and storing instructions that when executed by the at least one processor performs operations comprising:
optimizing a gas-oil-ratio database using a genetic algorithm and a multivariate regression simulator; and
generating a synthetic gas-oil-ratio for a gas dominant fluid.

13. The system of claim 12 , wherein the operations for optimizing a gas-oil-ratio database using a genetic algorithm and a multivariate regression simulator comprises:
defining gas-oil-ratio searching boundaries gas-oil-ratio for each gas dominant fluid;
generating an initial population of gas-oil-ratio data for a set of gas dominant fluids;
assigning randomly a synthetic gas-oil-ratio for each gas dominant fluid in a set of gas dominant fluids in the initial population of gas-oil-ratio data, wherein the gas-oil-ratio for each gas dominant fluid is within the searching boundaries; and
evaluating synthetic gas-oil-ratio assignments for the initial population using the multivariate regression simulator.

14. The system of claim 13 , wherein the operations for evaluating synthetic gas-oil-ratio assignments for the initial population using the multivariate regression simulator comprises:
combining the initial population of gas-oil-ratio data for a set of gas dominant fluids and a set of data for other fluids from a standard optical fluid library, wherein the step of combining forms a combined fluid set;
calculating an overall gas-oil-ratio prediction error through a plurality of models having a plurality of inputs;
determining whether a stop criterion for the overall gas-oil-ratio prediction error is met; and
applying the genetic algorithm based on the overall gas-oil-ratio prediction error until the stop criterion is met.

15. The system of claim 14 , wherein the operations applying the genetic algorithm based on the overall gas-oil-ratio prediction error until the stop criterion is met comprises:
ranking the overall gas-oil-ratio prediction error over the combined fluid samples; and
updating the gas-oil-ratio assigned for each gas dominant fluid using at least one of selection, crossover, and mutation method genetic operators through multiple generations of calculations to determine whether the stop criterion is met.

16. The system of claim 12 , wherein the at least one memory coupled to the at least one processor and storing instructions that when executed by the at least one processor performs operations further comprises:
recalibrating a universal gas-oil-ratio predictive model using a neural networks algorithm to include tool-specific inputs.

17. A non-transitory computer readable medium comprising computer executable instructions for determining a synthetic gas-oil-ratio for a gas dominant fluid, the computer executable instructions when executed causes one or more machines to perform operations comprising:
optimizing a gas-oil-ratio database using

Assignees

• Halliburton Energy Services Inc

Inventors

• Chen Dingding
• Perkins David L
• Jones Christopher Michael
• Shen Jing
• Pelletier Michael T
• Atkinson Robert

Classifications

• G06N3/048

  Activation functions · CPC title

• G16C20/70

  Machine learning, data mining or chemometrics · CPC title

• G06F17/11

  for solving equations {, e.g. nonlinear equations, general mathematical optimization problems (optimization specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title

• G01N33/2823

  Raw oil, drilling fluid or polyphasic mixtures · CPC title

• G16C20/30

  Prediction of properties of chemical compounds, compositions or mixtures · CPC title