Satellite Navigation Preprocessor Using Fuzzy Genetic Learning Automata

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current satellite navigation systems face inaccuracies due to the Earth's orientation changes caused by gravitational influences and shifts, leading to errors in satellite position determination, which are difficult to improve due to time constraints and complexity in orbital mechanics.

Innovation Solution

A system that includes a satellite, monitors, and a master controller using a preprocessor with fuzzy genetic learning automata to preprocess measurement data, reducing reliance on inaccurate Earth orientation models and enhancing the accuracy of satellite position determination by providing better data to the Kalman filter for position, velocity, and timing accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If smoothing (averaging) is used to improve position accuracy, then measurement precision is improved, but loss of information occurs due to averaging out important variations

Engineering Contradiction:

Improveposition accuracyVSAvoidmeasurement data information

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The preprocessor performs preliminary actions on measurement data before it reaches the Kalman filter, using machine learning techniques to identify and correct errors, fill gaps, and improve data quality in advance. This allows the main navigation system to receive pre-enhanced data without losing original information characteristics.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The preprocessor acts as an intermediary between the raw measurement data source and the Kalman filter. It processes measurement data through machine learning algorithms to reduce covariance and improve quality, then passes the enhanced data to the Kalman filter, thereby mediating between raw data and final position calculation.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If Earth orientation models are used to correct satellite position, then position accuracy is improved, but reliability deteriorates due to inaccuracies in Earth orientation modeling

Engineering Contradiction:

Improvesatellite position accuracyVSAvoidEarth orientation model accuracy

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system uses machine learning algorithms that learn from historical measurement data and performance feedback to continuously improve their correction capabilities. The preprocessor adapts to actual measurement patterns rather than relying solely on theoretical Earth orientation models, incorporating feedback from real-world data performance.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The machine learning techniques change the parameters of measurement data processing by learning optimal correction factors and covariance reductions from historical data, rather than relying on fixed Earth orientation model parameters. This allows dynamic adaptation to actual measurement conditions.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11546001B2Preprocessor for device navigation

Publication Date: 2023.01.03 RAYTHEON CO

AI summary

A method for preprocessing data for device operations can include preprocessing measurement data using a machine learning technique, determining, by a Kalman filter and based on (1) the preprocessed measurement data or the measurement data and (2) prediction data from a prediction model predicting a measurement associated with the measurement data, corrected measurement data, and providing the corrected measurement data based on the predicted measurement and the preprocessed measurement data.