# US 2019/0057168 A1 · Obtaining micro- and macro-rock properties with a calibrated rock deformation simulation

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

- Number: US 2019/0057168 A1
- Document ID: US20190057168A1
- Status: Published application
- Kind: A1
- Application number: 16/160,453
- Filed: 2018-10-15
- Published: 2019-02-21
- Earliest claimed: 2016-03-28
- Assignees: Baker Hughes, A Ge Company, LLC
- Inventors: Marc Holland; Tobias Hoeink; Wouter Van Der Zee
- Web page: https://patentgrep.com/patent/US20190057168A1

## CPC

- G06F 30/13: Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
- E21B 49/003: {by analysing drilling variables or conditions (E21B49/005 takes precedence; systems specially adapted for monitoring a plurality of drilling variables or conditions E21B44/00)}
- E21B 49/02: by mechanically taking samples of the soil
- G01N 33/241: {for hydrocarbon content}
- G01V 20/00: Geomodelling in general
- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G01V 99/00: Subject matter not provided for in other groups of this subclass
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)

## Abstract

A method for estimating a property of an earth formation includes: obtaining a sample of rock; scanning the sample to determine internal rock damage; measuring a deformation parameter of the sample; constructing a mathematical model of the sample that replicates the determined and measured internal rock damage distribution; simulating the one or more tests using the mathematical model; obtaining a rock deformation parameter using the one or more simulated tests corresponding to the measured rock deformation parameter; comparing the rock deformation parameter obtained from the one or more simulated tests to the corresponding measured rock deformation parameter; adjusting parameters of the mathematical model based upon the rock parameter obtained from simulation not being within a selected range of the measured rock parameter; and providing the mathematical model as a verified mathematical model based upon the rock parameter obtained from simulation being within a selected range of the measured rock parameter.

## Claims

### Claim 1

A method for estimating a property of an earth formation, the method comprising:
obtaining a sample of rock from the earth formation;
scanning the sample with a volumetric imaging device to obtain a three-dimensional volume representation of the sample;
determining internal rock damage of the sample using the three-dimensional volume representation of the sample;
performing one or more tests on the sample using a rock test device;
measuring a deformation parameter of the sample using a deformation sensor;
constructing a mathematical model of the sample that replicates the determined and measured internal rock damage and damage distribution of the sample using artificial intelligence (AI), the mathematical model being an AI model;
simulating the one or more tests using the mathematical model;
obtaining a rock deformation parameter using the one or more simulated tests corresponding to the measured rock deformation parameter;
comparing the rock deformation parameter obtained from the one or more simulated tests to the corresponding measured rock deformation parameter;
adjusting parameters of the mathematical model based upon the rock parameter obtained from simulation not being within a selected range of the measured rock parameter; and
providing the mathematical model as a verified mathematical model based upon the rock parameter obtained from simulation being within a selected range of the measured rock parameter;
wherein the determining, constructing, obtaining a rock deformation parameter, comparing adjusting, and providing are performed using a processor.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the constructing a mathematical model comprises performing a training phase to train the AI model.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the training phase comprises: obtaining data related to the sample; creating input variables that are input into the AI model; creating one or more output variables that are output from the AI model; and creating the AI model by mapping the input variables to the one or more output variables.

### Claim 4 (depends on 3)

The method according to claim 3, wherein the input variables comprise a damage parameter that quantifies damage to the sample.

### Claim 5 (depends on 4)

The method according to claim 4, wherein the damage parameter comprises a statistical distribution of values of the damage parameter.

### Claim 6 (depends on 4)

The method according to claim 4, wherein the damage parameter is a function of position in the earth formation.

### Claim 7 (depends on 3)

The method according to claim 3, wherein at least one input variable is a function of a damage value.

### Claim 8 (depends on 7)

The method according to claim 7, wherein the function is one of local average, a minimum, a maximum, and a function that combines the damage value with another type of parameter.

### Claim 9 (depends on 8)

The method according to claim 8, wherein the another type of parameter comprises one of fluid saturation and mineralogy.

### Claim 10 (depends on 3)

The method according to claim 3, wherein the one or more output variables comprise a deformation parameter characterizing deformation of the sample.

### Claim 11 (depends on 10)

The method according to claim 10, wherein the deformation parameter comprises axial strain in one or more directions or volumetric strain.

### Claim 12 (depends on 3)

The method according to claim 3, wherein the one or more output variables comprise a stress parameter.

### Claim 13 (depends on 12)

The method according to claim 12, wherein the stress parameter comprises stress at a selected point on a stress-strain curve.

### Claim 14 (depends on 2)

The method according to claim 2, wherein the AI model comprises an artificial neural network and the training phase comprises optimizing hyper-parameters of the artificial neural network so that the rock parameter obtained from simulation is maintained within a selected range of the measured rock parameter.

### Claim 15 (depends on 1)

The method according to claim 1, wherein the simulating comprises performing an application phase to apply the AI model.

### Claim 16 (depends on 15)

The method according to claim 15, wherein the application phase comprises: obtaining new values of input variables; and applying the new values of input variables to the AI model to obtain new values of one or more output variables from the AI model.

### Claim 17

A system for estimating a property of an earth formation, the system comprising:
a volumetric imaging device configured to scan a sample of rock form the earth formation to obtain a three-dimensional volume representation of the sample;
a rock test device configured to perform one or more tests on the sample;
a deformation sensor configured to measure deformation of the sample due to the one or more tests;
a memory having computer-readable instructions;
a processor for executing the computer-readable instructions, the computer-readable instructions comprising:
determining internal rock damage of the sample using the three-dimensional volume representation of the sample;
constructing a mathematical model of the sample that replicates the determined internal rock damage and damage distribution of the sample using artificial intelligence (AI), the mathematical model being an AI model;
simulating the one or more tests using the mathematical model;
obtaining a rock deformation parameter using the one or more simulated tests corresponding to the measured rock deformation parameter;
comparing the rock deformation parameter obtained from the one or more simulated tests to the corresponding measured rock deformation parameter;
adjusting parameters of the mathematical model based upon the rock parameter obtained from simulation not being with a selected range of the measured rock parameter; and
providing the mathematical model as a verified mathematical model based upon the rock parameter obtained from simulation being within a selected range of the measured rock parameter.

### Claim 18 (depends on 17)

The system according to claim 17, wherein the constructing a mathematical model comprises performing a training phase to train the AI model and the simulating comprises performing an application phase to apply the AI model.

### Claim 19 (depends on 17)

The system according to claim 17, wherein the AI model comprises damage values characterizing damage to the sample as a function of coordinates or as a function of defined grid cells imposed on the sample corresponding to where the damage values were obtained.
