Tool string design using machine learning
AssigneeHalliburton Energy Services, Inc.
InventorsJian Li, Bin Dai, Christopher Michael Jones, James M. Price, Cameron M. Rekully
Life of this patent
Estimating the term…
Abstract
A method for designing a tool string for use in a wellbore includes receiving a merit function, and determining, with a computing system and based on the merit function, a tool string design for a tool string. The merit function comprises one or more defined objectives for performing a process in a wellbore. The tool string design comprises an indication of one or more tools used to form a tool string for performing the process in the wellbore, and the tool string design satisfies the merit function.
Claims19
A method for designing a tool string for use in a wellbore, the method comprising:
- receiving a merit function, wherein the merit function comprises one or more defined objectives for performing at least one process in a wellbore;
- and
- using a machine learning model on a computing system to determine, based on the merit function, a tool string design for a tool string, wherein the tool string design comprises a first tool string design for a first tool string, wherein the first tool string is used to perform a first process in the wellbore, wherein the first tool string design comprises a selection of a first tool from a plurality of tools and an arrangement for the first tool string, and wherein the machine learning model uses the merit function to determine the tool string design such that the tool string design satisfies the merit function.
A system for determining a tool string design, the system comprising:
- a processor;
- a memory, wherein the memory comprises a machine learning model, and wherein the machine learning model, when executed on the processor, configures the processor to:
- receive a merit function, wherein the merit function comprises one or more defined objectives for performing at least one process in a wellbore;
- and
- determine, based on the merit function, a tool string design for a tool string, wherein the tool string design comprises a first tool string design for a first tool string, wherein the first tool string is used to perform a first process in the wellbore, wherein the first tool string design comprises a selection of a first tool from a plurality of tools and an arrangement for the first tool string, and wherein the machine learning model uses the merit function to determine the tool string design such that the tool string design satisfies the merit function.
A method for designing a tool string for use in a wellbore, the method comprising:
- receiving a merit function, wherein the merit function comprises one or more defined objectives for performing at least one tool string process in a wellbore;
- using a machine learning model on a computing system to determine, determining, using a dictionary learning algorithm with sparse coding, one or more atoms based on the merit function, wherein the dictionary learning algorithm uses a dictionary of system parameters, wherein a plurality of atoms are defined by combinations of the system parameters from the dictionary, and wherein the plurality of atoms represent a sparse representation of the system parameters;
- and
- using the machine learning model on a computing system to determine a tool string design based on the one or more atoms, wherein the tool string design comprises a first tool string design for a first tool string, wherein the first tool string is used to perform a first process in the wellbore, wherein the first tool string design comprises a selection of a first tool from a plurality of tools and an arrangement for the first tool string, and wherein the machine learning model uses the one or more atoms based on the merit function to determine the tool string design such that the tool string design satisfies the merit function.
Dependencies are inferred from the claim text.