Electromagnetic Imager Tool Parameter Identification via ML Regression

Solution Overview

Problem

Electromagnetic imager tools face challenges in accurately identifying mud and formation parameters due to complex responses influenced by multiple factors, leading to inefficient and costly inversion techniques that require significant computational resources and time.

Innovation Solution

The use of machine learning to generate regression functions based on a known dataset associated with the electromagnetic imager tool, allowing for the identification of mud and formation parameters from tool measurements, thereby reducing computational costs and improving efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If inversion techniques are used to identify mud and formation parameters, then measurement precision is improved, but computational cost and processing time increase significantly

Engineering Contradiction:

Improveaccuracy of mud and formation parameter identificationVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-computing a library of synthetic impedance responses covering a range of mud and formation parameters before actual logging operations. This pre-computed library serves as a lookup table that enables rapid parameter identification during field operations without requiring real-time inversion calculations, thus resolving the contradiction between measurement precision and processing time

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses copying by creating synthetic models and simulated impedance responses that replicate the complex electromagnetic tool responses under various conditions. These synthetic copies are stored in a library and matched against actual measurements to identify parameters, avoiding the need to perform computationally intensive inversion calculations on every actual measurement while maintaining accuracy

Inventive Principle:

Principle #26Copying

2Measurement precision

If inversion techniques are used to identify mud and formation parameters, then measurement precision is improved, but computational resource usage increases

Engineering Contradiction:

Improveaccuracy of mud and formation parameter identificationVSAvoidcomputational resource usage

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies preliminary action by pre-computing a library of synthetic impedance responses covering a range of mud and formation parameters before actual logging operations. This pre-computed library serves as a lookup table that enables rapid parameter identification during field operations without requiring real-time inversion calculations, thus resolving the contradiction between measurement precision and processing time

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses copying by creating synthetic models and simulated impedance responses that replicate the complex electromagnetic tool responses under various conditions. These synthetic copies are stored in a library and matched against actual measurements to identify parameters, avoiding the need to perform computationally intensive inversion calculations on every actual measurement while maintaining accuracy

Inventive Principle:

Principle #26Copying

3Measurement precision

If electromagnetic imager tools account for multiple complex responses, then measurement precision is improved, but device complexity increases

Engineering Contradiction:

Improveaccuracy of formation resistivity measurementVSAvoidcomplexity of impedance measurement system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies segmentation by separating the complex impedance measurement into distinct components influenced by different parameters (formation resistivity, mud resistivity, standoff, etc.). Each component is modeled independently in the synthetic library, allowing the system to account for multiple complex responses without requiring a monolithic complex measurement system

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent uses an intermediary approach by introducing a synthetic impedance library as a mediator between the complex electromagnetic measurements and the parameter identification process. This library acts as a translation layer that converts complex multi-parameter responses into interpretable parameter values without requiring direct complex inversion calculations

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11762119B2Machine learning approach for identifying mud and formation parameters based on measurements made by an electromagnetic imager tool

Publication Date: 2023.09.19 HALLIBURTON ENERGY SERVICES INC

AI summary

Aspects of the subject technology relate to systems and methods for identifying values of mud and formation parameters based on measurements gathered by an electromagnetic imager tool through machine learning. One or more regression functions that model mud and formation parameters capable of being identified through an electromagnetic imager tool as a function of possible tool measurements of the electromagnetic imager tool can be generated using a known dataset associated with the electromagnetic imager tool. One or more tool measurements obtained by the electromagnetic imager tool operating to log a wellbore can be gathered. As follows, one or more values of the mud and formation parameters can be identified by applying the one or more regression functions to the one or more tool measurements.