Drill Bit Attitude Prediction via Sensor Fusion

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Accurately steering a drilling tool in subterranean wellbores is challenging due to remote downhole operations and unpredictable conditions, requiring precise estimation of bit inclination and azimuth for autonomous control.

Innovation Solution

A moving horizon weighted least square regression algorithm is used to estimate current bit inclination and azimuth, incorporating sensor data from a bottom-hole assembly with measurement weights to predict future values, allowing for real-time adjustments and control inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional sensor data processing methods are used for downhole drilling tool steering, then human operators can analyze sensor measurements to control the drilling tool, but the remote distance and unpredictable downhole conditions result in inaccurate steering and inability to reach set targets

Engineering Contradiction:

Improvebit inclination and azimuth estimation accuracyVSAvoidcomputational algorithm complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transforms the raw sensor measurement data into calibrated parameters by estimating model parameters that relate sensor measurements to bit inclination and azimuth. This parameter transformation enables accurate steering predictions by changing the form of data representation from raw sensor readings to meaningful geological orientation parameters

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces traditional mechanical sensor systems with a computational model-based system that uses sensor fusion and regression algorithms. Instead of relying solely on physical sensors to directly measure bit orientation, the system substitutes a mathematical model that processes sensor data to estimate bit inclination and azimuth, achieving higher accuracy in unpredictable downhole conditions

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Extent of automation

If complex sensor fusion algorithms are implemented to improve steering accuracy, then autonomous control becomes possible, but computational load increases

Engineering Contradiction:

Improveautonomous drill bit steering capabilityVSAvoidcomputational energy consumption

Core Design Contradiction:

Extent of automationVSUse of energy by moving object

Solution Approach 1:

The patent implements a self-calibrating system where the model parameters are automatically estimated and updated using sensor data without requiring external intervention. The system performs self-service calibration by continuously processing sensor measurements to refine the relationship between sensor readings and bit orientation, enabling autonomous operation

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent applies a moving horizon regression approach that processes only the necessary subset of sensor data within a defined time window rather than analyzing all historical data. This partial action approach provides sufficient accuracy for autonomous control while reducing computational energy consumption by focusing on relevant recent measurements

Inventive Principle:

Principle #16Partial or excessive action

3Manufacturing precision

If model parameter calibration is performed to improve bit position prediction accuracy, then real-time adjustments can be made, but the processing time and computational resources increase

Engineering Contradiction:

Improvedrill bit position prediction accuracyVSAvoidparameter estimation time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary calibration of model parameters using historical sensor data before real-time drilling operations. By pre-establishing the relationship between sensor measurements and bit orientation parameters, the system reduces the computational burden during real-time operation, allowing quick adjustments without excessive processing time

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements a dynamic parameter estimation approach where model parameters are continuously updated as new sensor data becomes available. The moving horizon regression method allows the system to adapt to changing downhole conditions in real-time, maintaining prediction accuracy while balancing computational efficiency through incremental parameter updates rather than complete re-calibration

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11326441B2Sensor fusion and model calibration for bit attitude prediction

Publication Date: 2022.05.10 HALLIBURTON ENERGY SERVICES INC

AI summary

Techniques for estimating a current inclination and azimuth of a drill bit of a wellbore drilling system are described. The estimates for the current inclination and azimuth are generated using measurements obtained for one or more parameters associated with the drilling process performed by the drill bit and taken over a range of the wellbore falling within a sliding window having a predefined distance D extending along the wellbore.