Real-Time Synthetic Formation Logging for Drilling Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing drilling and reservoir stimulation processes lack real-time measurement capabilities for various sub-surface parameters, leading to inefficiencies and safety risks due to the high cost and regulatory challenges of using conventional tools, and the inability to optimize drilling and steering based on accurate and timely data.

Innovation Solution

A neural network system that synthesizes formation properties like density, porosity, and sonic velocity in real-time using surface measurements and historical data, eliminating the need for expensive and regulated downhole tools by transforming drilling parameters into synthetic acoustic velocities and mechanical properties.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional downhole tools (e.g., nuclear tools, sonic sondes) are used to measure sub-surface parameters in real-time, then measurement precision is improved, but device complexity and cost increase significantly

Engineering Contradiction:
Improvesub-surface parameter measurementVSAvoiddownhole tool complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates synthetic copies of formation property logs (density, porosity, sonic velocity) by using machine learning models trained on historical data and surface measurements. These synthetic logs replicate the information that would be obtained from expensive downhole tools, eliminating the need for physical deployment of such tools while maintaining measurement precision.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces physical mechanical and nuclear measurement systems (sonic sondes, density tools, neutron tools) with a computational system using machine learning algorithms. The system processes surface measurements and historical data to generate synthetic formation property logs, substituting complex physical measurement equipment with software-based solutions.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If conventional downhole tools are deployed to measure formation properties, then measurement precision is improved, but ease of operation deteriorates due to regulatory requirements and special handling

Engineering Contradiction:
Improveformation property measurementVSAvoidtool deployment and operation
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent generates synthetic formation property logs that replicate the output of conventional downhole tools without requiring their deployment. This copying approach maintains measurement precision while completely avoiding the operational complexities, regulatory requirements, and safety concerns associated with handling nuclear and acoustic logging tools.

Inventive Principle:
Principle #26Copying

3Measurement precision

If additional personnel are present at well site to operate downhole tools, then measurement precision is improved, but health, safety, security and environment risks increase

Engineering Contradiction:
Improvesub-surface parameter measurementVSAvoidwell site safety risks
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent creates synthetic logs that replicate formation property measurements without requiring personnel to handle or deploy hazardous downhole tools. This eliminates exposure risks from nuclear materials and acoustic equipment while maintaining the ability to obtain precise formation property data for drilling optimization.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system uses surface measurements and historical data that are already available at the well site, processing them through machine learning models to generate formation property information. This self-service approach eliminates the need for additional personnel to operate specialized tools, reducing safety risks while maintaining measurement capabilities.

Inventive Principle:
Principle #25Self-service

4Productivity

If real-time measurements of mechanical properties are made using conventional tools, then productivity is improved through optimization, but loss of time increases due to tool deployment and regulation compliance

Engineering Contradiction:
Improvedrilling optimizationVSAvoidtool deployment and compliance time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The machine learning models are trained in advance on historical formation property data and surface measurements. This preliminary training enables the system to rapidly generate synthetic formation property logs during drilling operations without the time-consuming processes of tool deployment, site preparation, and regulatory compliance that would otherwise be required.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent generates synthetic formation property logs that replicate the output of conventional downhole tools instantaneously using pre-trained machine learning models. This copying approach maintains the ability to optimize drilling operations with accurate formation property data while eliminating the significant time losses associated with deploying and complying with regulated measurement tools.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3924599B1Real-time synthetic logging for optimization of drilling, steering, and stimulation
Publication Date: 2025.09.17 QUANTICO ENERGY SOLUTIONS
  • EP3924599B1 patent drawingFigure 1~2B
  • EP3924599B1 patent drawingFigure 2A
  • EP3924599B1 patent drawingFigure 3

AI summary

The present disclosure generally relates to a real-time synthetic logging method for optimizing one or more operations in a well. The method generally includes receiving measurements of one or more parameters in real time while performing operations in the well (310), the measurements being captured without using tools that include active nuclear sources. The method further includes providing the measurements as input to a machine learning algorithm (MLA) that is trained using historical or training well data (320). The method further includes generating, using the MLA and based on the measurements, a synthetic mechanical property log of the well (330). The method further includes generating, based on the synthetic mechanical property log, optimized parameters for at least one operation selected from the following list: drilling the well in real-time; steering the well in real-time; and stimulating a reservoir in real-time (340).