Measurement-While-Drilling AI Decoding for Mud Pulse Signals

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Signal integrity issues in measurement-while-drilling (MWD) data due to dynamic forces in well boreholes affect the accuracy of decoding mud pulse and electromagnetic telemetry signals.

Innovation Solution

Utilizing a trained machine learning model to classify and decode mud pulse signals, enhanced by user interface feedback for correcting signal values and synchronization, and continuous model training with cloud-based computing for improved accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional decoding methods are used for MWD signals, then the decoding process is simple and fast, but the accuracy and reliability of signal interpretation deteriorates due to dynamic forces in well boreholes

Engineering Contradiction:

Improvesignal decoding accuracyVSAvoiddecoding system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

A machine learning model is introduced as an intermediary between the raw MWD signal and the decoding process. The model processes the signal to extract features and improve decoding accuracy, acting as a mediator that enhances signal interpretation while managing the complexity of dynamic borehole conditions

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

Traditional mechanical decoding algorithms are replaced with an artificial intelligence-based machine learning system. This substitution enables the system to adapt to varying signal conditions caused by dynamic forces, improving measurement precision through pattern recognition and adaptive processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If machine learning models are used to decode MWD signals, then the accuracy of signal interpretation improves, but the processing time and computational resources increase

Engineering Contradiction:

Improvedata decoding accuracyVSAvoidsignal processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The machine learning model is trained in advance on extensive datasets of MWD signals under various borehole conditions. This preliminary training allows the model to quickly process real-time signals without requiring complex computations during actual drilling operations, reducing processing time while maintaining high accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system adjusts processing parameters dynamically based on signal quality and borehole conditions. By changing parameters such as processing depth, model complexity, and sampling rate, the system optimizes the balance between decoding accuracy and processing speed for different operational scenarios

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12416233B2Enhanced measurement-while-drilling decoding using artificial intelligence

Publication Date: 2025.09.16 ERDOS MILLER INC

AI summary

In one embodiment, a method is disclosed for using a trained machine learning model to classify mud pulse signals. The method may include receiving a mud pulse signal from a measurement while drilling (MVWD) tool, wherein the mud pulse signal includes data. The method may also include decoding, using the trained machine learning model, the data to determine a value of the data, and providing a user interface comprising the value of the data for presentation on a computing device of a user.