Automated Formation Tester Using Convolutional Neural Networks

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current formation testing methods are inefficient due to slow data transmission via mud-pulse telemetry, manual control issues, and contamination changes during sample transport, leading to inaccurate sample representation and prolonged cleanup times, which increase costs and risk of drill string sticking.

Innovation Solution

Implementing automated systems with convolutional neural networks for real-time formation condition estimation using in-situ measurements, allowing for autonomous operation and optimized sampling parameters to accelerate testing and prediction of formation conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated systems with convolutional neural networks are implemented for real-time formation condition estimation, then productivity and measurement precision are improved, but device complexity increases

Engineering Contradiction:

Improvetesting speedVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent replaces manual control systems with automated computer systems that use convolutional neural networks and deep learning algorithms. This substitution of mechanical/manual operations with intelligent automated systems enables real-time analysis of formation conditions, significantly improving productivity and measurement precision while the system learns and adapts to specific formation characteristics

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The computer system performs autonomous operation by automatically analyzing in-situ measurements, predicting formation conditions, and optimizing sampling parameters without continuous human intervention. The system serves itself by using its own measurements to improve its predictions and control decisions in real-time, reducing the need for external manual control

Inventive Principle:

Principle #25Self-service

2Measurement precision

If in-situ measurements are used for real-time analysis, then measurement precision and reliability are improved, but loss of time in sample transport is reduced

Engineering Contradiction:

Improvesample representation accuracyVSAvoidcleanup time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of formation conditions by measuring fluid properties in-situ before contamination can occur during transport. By conducting measurements and predictions at the wellbore location itself, the system eliminates the time delay associated with bringing samples to the surface and prevents contamination-related measurement errors

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses optical density measurements as an intermediary parameter to assess fluid contamination levels in real-time. This intermediary measurement allows the system to predict sample quality and formation conditions without physically transporting the actual fluid samples, thereby maintaining measurement precision while eliminating transport time losses

Inventive Principle:

Principle #24Intermediary (Mediator)

3Ease of operation

If manual control is used for sample collection, then ease of operation is maintained, but productivity and measurement precision deteriorate due to contamination changes during transport

Engineering Contradiction:

Improveoperational simplicityVSAvoidsample characterization accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent replaces manual control operations with automated computer-controlled systems that use convolutional neural networks. This substitution maintains ease of operation through automated decision-making while dramatically improving measurement precision by eliminating human error and contamination risks associated with manual sample handling and transport

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Device complexity

If traditional formation testing methods are used, then device complexity is kept low, but productivity and reliability worsen due to slow data transmission and prolonged testing times

Engineering Contradiction:

Improvesystem simplicityVSAvoidtesting efficiency

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The patent replaces traditional mechanical data transmission methods (mud-pulse telemetry) with electronic data processing systems using convolutional neural networks. This substitution maintains relatively simple device architecture while dramatically improving productivity through real-time analysis and faster decision-making capabilities

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20230273180A1Systems and methods for automated, real-time analysis and optimization of formation-tester measurements

Publication Date: 2023.08.31 BOARD OF RGT THE UNIV OF TEXAS SYST

AI summary

Described herein are methods and systems, and techniques relating to hydrocarbon-bearing formation testing and, particularly, to estimating a formation condition. The disclosed methods, systems, and techniques allow for improved prediction of the formation condition and cleanout of the formation following well drilling. In some cases, the disclosed methods, systems, and techniques include using a formation testing tool to obtain a sampled fluid from a formation according to a set of sampling parameters and using the formation testing tool to analyze the sampled fluid to identify a set of fluid parameters for the sampled fluid. A numerical model may be used to determine a formation condition with inputs including the sampling parameters and the fluid parameters.