RAPID OPTIMIZATION OF NON-EQUILIBRIUM PLASMAS USING NEW BREAKTHROUGHS IN DATA SCIENCE

Abstract

Proposal offers new methods to characterize non-linear reactions in multi-species plasma by combining reduced-fidelity plasma model with sparse optimization and data discovery techniques, as an example, will optimize performance of molecular-propellant electron cyclotron resonance thruster using machine learning and compare results with traditional optimization methods; and will determine the type and location of diagnostic measurements that best reflect thruster performance and stability.

Document Details

Document Type
DoD Grant Award
Publication Date
Aug 12, 2021
Source ID
FA95502010167

Entities

People

  • Justin M. Little

Organizations

  • Air Force Office of Scientific Research
  • United States Air Force
  • University of Washington

Tags

Readers

  • Aerospace Propulsion Engineering.
  • Distributed Systems and Data Platform Development
  • Pulsed Power and Plasma Physics.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Microelectronics
  • Space
  • Space - Hall-Effect Thruster