Improving Aeromagnetic Calibration Using Artificial Neural Networks

Abstract

Magnetic anomaly navigation has been shown to be highly successful but only under idealized scenarios. In particular, it has proven itself a viable alternative to GPS only on optimized, geosurvey aircraft. No body of research exists which attempts to address the platform effect problem outside the scope of the de facto calibration equations, known in the literature as Tolles-Lawson. We show an alternative calibration technique which achieves a 90 decrease in aircraft disturbance field strength over the Tolles-Lawson equations using deep learning and artificial neural networks.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 26, 2020
Accession Number
AD1103282

Entities

People

  • Mitchel C. Hezel

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Advanced Electronics
  • Autonomy
  • Energy and Power Technologies
  • Sensors
  • Space

DTIC Thesaurus Topics

  • Air Force
  • Aircrafts
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Artificial Neural Networks
  • Computational Science
  • Computers
  • Control Surfaces
  • Deep Learning
  • Detectors
  • Engineering
  • Inertial Navigation Systems
  • Literature Surveys
  • Machine Learning
  • Magnetic Detectors
  • Magnetic Disturbances
  • Magnetic Fields
  • Magnetic Materials
  • Magnetic Navigation
  • Magnetometers
  • Measurement
  • Navigation
  • Neural Networks
  • Recurrent Neural Networks
  • Vector Magnetometers

Readers

  • Neural Network Machine Learning.
  • Positioning, Navigation, and Timing (PNT) Technology.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks
  • Space