Fracture Model Optimization Using Genetic Algorithms

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Developing hydrocarbon reservoirs is challenging due to the difficulty in accurately modeling and simulating natural fractures, which affects the optimization of hydrocarbon extraction, as existing methods struggle to accurately characterize and predict the location, size, and behavior of natural fractures in subsurface formations.

Innovation Solution

A method involving the determination of initial ranges for fracture model parameters using geomechanical and borehole image log data, followed by optimization employing a genetic algorithm to identify constrained fracture model parameters, which are then used for simulating reservoir performance and optimizing well operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If natural fracture parameters are estimated using interpretation and additional modeling, then reservoir modeling can proceed with limited direct measurements, but the accuracy of simulations and reservoir characterization deteriorates

Engineering Contradiction:

Improveease of reservoir modelingVSAvoidaccuracy of fracture characterization

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent introduces borehole image logs as an intermediary data source between direct fracture measurements and reservoir-scale simulations. These logs provide detailed fracture information at the wellbore location that serves as a bridge to constrain and calibrate natural fracture models for the broader reservoir, improving accuracy without requiring extensive direct measurements across the entire reservoir.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces traditional mechanical/physical measurement methods (core assessments, direct fracture sampling) with advanced imaging and computational techniques. Borehole image logs and seismic data are processed through inversion algorithms and neural networks to derive fracture parameters, substituting physical measurement systems with information-based systems that provide broader coverage and improved accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If genetic algorithm optimization is applied to determine constrained fracture model parameters, then the accuracy of fracture parameter estimation is improved, but the computational complexity and time required for modeling increases

Engineering Contradiction:

Improveaccuracy of fracture parameter estimationVSAvoidcomputational complexity of modeling system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary processing of borehole image logs and seismic data to extract initial fracture parameters and constraints before applying genetic algorithm optimization. This preliminary action reduces the search space for the optimization algorithm, allowing it to converge to accurate solutions more efficiently and reducing overall computational complexity.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements a feedback mechanism where genetic algorithm optimization results are used to update and refine fracture models, which then generate predictions that are compared against observed well performance data. This feedback loop allows the system to self-correct and improve accuracy iteratively while managing computational resources through adaptive refinement rather than exhaustive optimization.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If comprehensive borehole image log analysis is performed to determine fracture distribution parameters, then the characterization of natural fractures is improved, but the time and resources required for data processing increases

Engineering Contradiction:

Improveaccuracy of fracture distribution characterizationVSAvoidtime for data processing

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts only the most critical fracture parameters from comprehensive borehole image log data, such as fracture orientation, aperture, and spacing, rather than processing all available information. This selective extraction maintains accuracy for the most important parameters while significantly reducing processing time and resource requirements.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms detailed borehole image log data into simplified fracture parameter representations that are suitable for reservoir-scale modeling. By changing the parameter representation from detailed wellbore-scale measurements to aggregated fracture zone characteristics, the system maintains characterization accuracy while enabling efficient processing and integration with larger-scale simulations.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11578596B2Constrained natural fracture parameter hydrocarbon reservoir development

Publication Date: 2023.02.14 SAUDI ARABIAN OIL CO

AI summary

Systems and methods for developing hydrocarbon reservoirs based on constrained natural fracture parameters. A natural fracture modeling is generated for a reservoir, an initial set of fracture model parameters is determined, and a fracture model optimization is conducted to determine an optimized set of fracture model parameters. The optimized set of fracture model parameters are used as a basis for modeling the reservoir, and the modeling is used to generate a simulation of the reservoir.