Granted Patent B2

US 12,724,164 · App. 17/000,096 · Granted Sep 1, 2026

Inventors: Keshava Prasad Rangarajan (Sugarland, TX); Raja Vikram R. Pandya (Katy, TX); Srinath Madasu (Houston, TX); Shashi Dande (Spring, TX)

Assignee: Landmark Graphics Corporation

G01V1/40G01V20/00G06F18/214G06F30/27G06N5/04G06N7/01G06N20/00H04L9/006H04L9/0637H04L9/0643H04L9/3247E21B2200/20E21B2200/22H04L9/50

Abstract

Claims (41)

1 . A system for managing well site operations, the system comprising:

at least one predictive engine, executed by a processor, having at least one selected from a group comprising an artificial intelligence algorithm and a trained artificial intelligence algorithm, the at least one predictive engine generates earth model variables using a physics model and at least one selected from a group comprising well log data variables and seismic data variables;

at least one node system stack communicably coupled to the at least one predictive engine, a distributed network, a plurality of sensors, and at least one machine controller, the at least one node system stack comprising one or more nodes configured to perform system control operations to control drilling operations of well site equipment;

at least one chained block of a distributed network, the distributed network comprising a genesis block and a plurality of subsequent blocks, each subsequent block comprising a well site entry and a cryptographic hash value of a previous well site entry, wherein the well site entry comprises at least one transacted operation control variable;

a visualization engine, executed by the processor, the visualization engine generates a display of a drill path, the at least one transacted operation control variable, and the earth model variables; and

an optimization engine, executed by the processor, the optimization engine optimizes the generated earth model variables by sampling the generated earth model variables based on at least one drilling model and an optimization tool to predict at least one optimized drill path, the at least one optimized drill path being predicted according to one or more objective criteria including a shortest length, minimum drilling time, maximum Rate Of Penetration, minimum bit wear, minimum mud loss, minimum overall drilling cost, minimum curvature, complexity of the drill path, and maximum safety;

wherein the at least one transacted operation control variable is, at least in part, based on at least one of the generated earth model variables, and

wherein the visualization engine updates the display based on the optimized drill path.

2 . The system of claim 1 , further comprising at least one partition, wherein each partition comprises the at least one node system stack and at least one selected from a group comprising the least one predictive engine and at least one process of the at least one predictive engine.

3 . The system of claim 2 , wherein the at least one node system stack comprises a middleware controller, the middleware controller communicable coupled to each partition, each node system stack, each predictive engine, and the at least one process.

4 . The system of claim 3 , wherein the middleware controller is a Robot Operating System (ROS) based controller.

5 . The system of claim 1 , wherein the optimization tool is one of a Bayesian optimization, genetic algorithm optimization, and particle swarm optimization.

6 . The system of claim 1 , further comprising: a deep particle filter, executed by the processor, to clean the well log data variables and seismic data variables;

and a forward modeling component, executed by the processor, to compare predicted variables in the generated earth model to the cleaned well log data variables and seismic data variables.

7 . An apparatus for managing well site operations, the apparatus comprising:

a processor;

at least one predictive engine, executed by the processor, having at least one selected from a group comprising an artificial intelligence algorithm and a trained artificial intelligence algorithm, the at least one predictive engine generates earth model variables using a physics model and at least one selected from a group comprising well log data variables and seismic data variables;

at least one node system stack communicable coupled to the at least one predictive engine, a distributed network, a plurality of sensors, and at least one machine controller, the at least one node system stack comprising one or more nodes configured to perform system control operations to control drilling operations of well site equipment;

at least one chained block of a distributed network, the distributed network comprising a genesis block and a plurality of subsequent blocks, each subsequent block comprising a well site entry and a cryptographic hash value of a previous well site entry, wherein the well site entry comprises at least one transacted operation control variable;

a visualization engine, executed by the processor, the visualization engine generates a display of a drill path, the at least one transacted operation control variable, and the earth model variables; and

an optimization engine, executed by the processor, the optimization engine optimizes the generated earth model variables by sampling the generated earth model variables based on at least one drilling model and an optimization tool to predict at least one optimized drill path, the at least one optimized drill path being predicted according to one or more objective criteria including a shortest length, minimum drilling time, maximum Rate Of Penetration, minimum bit wear, minimum mud loss, minimum overall drilling cost, minimum curvature, complexity of the drill path, and maximum safety;

wherein the at least one transacted operation control variable is, at least in part, based on at least one of the generated earth model variables, and

wherein the visualization engine updates the display based on the optimized drill path.

8 . The apparatus of claim 7 , further comprising at least one partition, wherein each partition comprises the at least one node system stack and at least one selected from a group comprising the least one predictive engine and at least one process of the at least one predictive engine.

9 . The apparatus of claim 8 , wherein the at least one node system stack comprises a middleware controller, the middleware controller communicable coupled to each partition, each node system stack, each predictive engine, and the at least one process.

10 . The apparatus of claim 9 , wherein the middleware controller is a Robot Operating System (ROS) based controller.

11 . The apparatus of claim 7 , wherein the optimization tool is one of a Bayesian optimization, genetic algorithm optimization, and particle swarm optimization.

12 . The apparatus of claim 7 , further comprising: a deep particle filter, executed by the processor, to clean the well log data variables and seismic data variables; and a forward modeling component, executed by the processor, to compare predicted variables in the generated earth model to the cleaned well log data variables and seismic data variables.

13 . A method for managing well site operations, the method comprising:

generating earth model variables using an artificial intelligence algorithm or a trained artificial intelligence algorithm, a physics model, and at least one selected from a group comprising well log data variables and seismic data variables;

communicable coupling at least one node system stack to the at least one predictive engine, a distributed network, a plurality of sensors, and at least one machine controller, the at least one node system stack comprising one or more nodes configured to perform system control operations to control drilling operations of well site equipment;

creating at least one chained block in a distributed network, the distributed network comprising a genesis block and a plurality of subsequent blocks, each subsequent block comprising a well site entry and a cryptographic hash value of a previous well site entry, wherein the well site entry comprises at least one transacted operation control variable;

generating a display of a drill path, the at least one transacted operation control variable, and the earth model variables;

optimizing the generated earth model variables by sampling the generated earth model variables based on at least one drilling model and an optimization tool to predict at least one optimized drill path, the at least one optimized drill path being predicted according to one or more objective criteria including a shortest length, minimum drilling time, maximum Rate Of Penetration, minimum bit wear, minimum mud loss, minimum overall drilling cost, minimum curvature, complexity of the drill path, and maximum safety; and

updating the display based on the optimized drill path;

wherein the at least one transacted operation control variable is, at least in part, based on at least one of the generated earth model variables.

14 . The method of claim 13 , further comprising creating at least one partition, wherein each partition comprises the at least one node system stack and at least one selected from a group comprising the least one predictive engine and at least one process of the at least one predictive engine.

15 . The method of claim 14 , communicable coupling a middleware controller to each partition, each node system stack, each predictive engine, and the at least one process.

16 . The method of claim 15 , wherein the middleware controller is a Robot Operating System (ROS) based controller.

17 . The method of claim 13 , wherein the optimization tool comprises one of a Bayesian optimization, genetic algorithm optimization, and particle swarm optimization.

18 . The method of claim 13 , further comprising cleaning the well log data variables and seismic data variables using a deep particle filter; and comparing predicted variables in the generated earth model to the cleaned well log data variables and seismic data variables using a forward modeling component.

Assignments (2)

Continuity (3)

References Cited (42)