# US 11,994,644 B2 · Method and apparatus for formation tester data interpretation with diverse flow models

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,994,644 B2
- Document ID: US11994644B2
- Status: Granted
- Kind: B2
- Application number: 17/480,986
- Filed: 2021-09-21
- Published: 2022-01-06
- Granted: 2024-05-28
- Earliest claimed: 2021-09-21
- Assignees: Halliburton Energy Services, Inc.
- Applicants: Halliburton Energy Services, Inc.
- Inventors: Dingding Chen; Mark A. Proett; Li Gao; Christopher Michael Jones
- Web page: https://patentgrep.com/patent/US11994644B2

## CPC

- G01V 20/00: Geomodelling in general
- E21B 49/087: {Well testing, e.g. testing for reservoir productivity or formation parameters}
- G06N 3/126: Evolutionary algorithms, e.g. genetic algorithms or genetic programming
- G06N 20/00: Machine learning
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)
- E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Improved systematic inversion methodology applied to formation testing data interpretation with spherical, radial and/or cylindrical flow models is disclosed. A method of determining a parameter of a formation of interest at a desired location comprises directing a formation tester to the desired location in the formation of interest and obtaining data from the desired location in the formation of interest. The obtained data relates to a first parameter at the desired location of the formation of interest. The obtained data is regressed to determine a second parameter at the desired location of the formation of interest. Regressing the obtained data comprises using a method selected from a group consisting of a deterministic approach, a probabilistic approach, and an evolutionary approach.

## Claims

### Claim 1

A method of determining a parameter of a formation of interest at a desired location comprising:
directing a formation tester to the desired location in the formation of interest;
obtaining data from the desired location in the formation of interest, wherein the obtained data relates to a first parameter at the desired location of the formation of interest;
initializing an estimation of a second parameter at the desired location in the formation of interest to simulate the first parameter by using a selected flow model;
calculating a parameter of a curve misfit based, at least in part, on the obtained data and simulated first parameter;
inverting the obtained data to update the second parameter, wherein inverting the obtained data comprises using a method selected from a group consisting of a deterministic approach, a probabilistic approach, and an evolutionary approach;
optimizing a curve match of the obtained data and the simulated first parameter to determine a matrix in part by at least one of deterministic or probabilistic and evolutionary approaches; and
optimizing one or more aspects of performance of one or more operations of the formation tester within a pre-determined time based, at least in part, on one or more parameters of the optimized curve match.

### Claim 2 (depends on 1)

The method of claim 1, further comprising directing the formation tester to another desired location based, at least in part, on the one or more parameters of the optimized curve match.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first parameter is a transient pressure during a formation test at the desired location in the formation of interest, wherein the second parameter is selected from a group consisting of actual reservoir pressure, fluid mobility, skin factor, formation porosity and fluid compressibility.

### Claim 4 (depends on 1)

The method of claim 1, wherein inverting the obtained data comprises using a deterministic approach and wherein the deterministic approach comprises using a Levenberg Marquardt algorithm, and further comprising applying a Gauss-Newton approximation of a Hessian matrix to the first parameter at the desired location to determine the second parameter at the desired location of the formation of interest.

### Claim 5 (depends on 1)

The method of claim 1, wherein inverting the obtained data comprises using a probabilistic approach and wherein the probabilistic approach comprises using a Bayesian learning algorithm.

### Claim 6 (depends on 1)

The method of claim 1, wherein inverting the obtained data comprises using an evolutionary approach and wherein the evolutionary approach comprises using one or more genetic parameters selected from a group consisting of selection, mutation, and crossover to determine the second parameter at the desired location of the formation of interest.

### Claim 7 (depends on 1)

The method of claim 1, wherein the formation tester comprises a first probe and a second probe, wherein obtaining data from the desired location in the formation of interest comprises obtaining a first set of data using the first probe and obtaining a second set of data using the second probe.

### Claim 8

An information handling system having a non-transitory computer readable medium, wherein the non-transitory computer readable medium contains instructions to:
obtain data from a formation tester at a desired location in the formation of interest, wherein the obtained data relates to a first parameter at the desired location of the formation of interest;
initialize an estimation of a second parameter at the desired location in the formation of interest to simulate the first parameter by using a selected flow model;
calculate a parameter of a curve misfit based, at least in part, on the obtained data and simulated first parameter;
invert the obtained data to update the second parameter, wherein inverting the obtained data comprises using a method selected from the group consisting of a deterministic approach, a probabilistic approach, and an evolutionary approach;
optimize a curve match of the obtained data and the simulated first parameter to determine a matrix through deterministic or probabilistic approaches, and
optimize one or more aspects of performance of one or more operations of the formation tester within a pre-determined time based, at least in part, on one or more parameters of the optimized curve match.

### Claim 9 (depends on 8)

The information handling system of claim 8, wherein the first parameter is a transient pressure during a formation test at the desired location in the formation of interest.

### Claim 10 (depends on 9)

The information handling system of claim 9, wherein the second parameter is selected from a group consisting of actual reservoir pressure, fluid mobility, skin factor, formation porosity and fluid compressibility.

### Claim 11 (depends on 8)

The information handling system of claim 8, wherein inverting the obtained data comprises using a deterministic approach and wherein the deterministic approach comprises using a Levenberg-Marquardt algorithm, and further comprising applying a Gauss-Newton approximation of a Hessian matrix to the first parameter at the desired location to determine the second parameter at the desired location of the formation of interest.

### Claim 12 (depends on 8)

The information handling system of claim 8, wherein inverting the obtained data comprises using a probabilistic approach and wherein the probabilistic approach comprises using a Bayesian learning algorithm.

### Claim 13 (depends on 8)

The information handling system of claim 8, wherein inverting the obtained data comprises using an evolutionary approach and wherein the evolutionary approach comprises using one or more genetic parameters selected from a group consisting of selection, mutation, and crossover to determine the second parameter at the desired location of the formation of interest.

### Claim 14

A method of estimating a desired parameter of a formation of interest comprising:
measuring a first parameter of the formation of interest, by a formation tester;
using a relationship between the first parameter of the formation of interest and the desired parameter of the formation of interest to obtain an estimate of the desired parameter of the formation of interest to simulate the first parameter by using a selected flow model;
calculating a parameter of a curve misfit based, at least in part on the first parameter and the simulated first parameter, wherein using the relationship between the first parameter of the formation of interest and the desired parameter of the formation of interest comprises inverting the first parameter of the formation of interest using a method selected from a group consisting of a deterministic approach, a probabilistic approach, and an evolutionary approach to update the desired parameter of the formation of interest;
optimizing a curve match of the first parameter of the formation of interest and the simulated first parameter to determine a matrix through deterministic or probabilistic approaches; and
optimizing one or more aspects of performance of one or more operations of the formation tester within pre-determined time based, at least in part, on one or more parameters of the optimized curve match.

### Claim 15 (depends on 14)

The method of claim 14, wherein the first parameter is a transient pressure during a formation test at a desired location in the formation of interest.

### Claim 16 (depends on 14)

The method of claim 14, wherein the desired parameter is selected from a group consisting of actual reservoir pressure, fluid mobility, skin factor, formation porosity and fluid compressibility.

### Claim 17 (depends on 14)

The method of claim 14, wherein inverting the obtained data comprises using a deterministic approach and wherein the deterministic approach comprises using a Levenberg-Marquardt algorithm.

### Claim 18 (depends on 17)

The method of claim 17, wherein the Levenberg-Marquardt algorithm comprises using at least one of a Jacobian matrix and an approximate Jacobian.

### Claim 19 (depends on 17)

The method of claim 17, further comprising applying a Gauss-Newton approximation of a Hessian matrix to the first parameter at the desired location to determine the desired parameter at the desired location of the formation of interest.

### Claim 20 (depends on 14)

The method of claim 14, wherein inverting the obtained data comprises using a probabilistic approach or an evolutionary approach, wherein the probabilistic approach comprises using a Bayesian learning algorithm, and wherein the evolutionary approach comprises using one or more genetic parameters selected from a group consisting of selection, mutation, and crossover to determine the desired parameter at the desired location of the formation of interest.