Neural Network Based Adaptive Control of Uncertain and Unknown Nonlinear Systems

Abstract

Our main accomplishment this past year has been to finalize and apply two approaches to output feedback adaptive control. The first is a direct adaptive approach, while the second uses a new error state observe. Both approaches overcome the limitation of earlier adaptive state observer based methods, which require that the order of the plant be known, and impose severe restrictions on the relative degree of regulated output variables. Within this context, we also have continued to exploit our approach for adaptive hedging' of actuator limits, which was the highlight of last year's report. We have also made some progress in the area of decentralized adaptive control. Our most significant interactions have been with NASA Marshall, NASA Ames, Wright Patterson AFB, Eglin AFB, Boeing and Lockheed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2001
Accession Number
ADA396974

Entities

People

  • Anthony J. Calise

Organizations

  • Georgia Tech

Tags

Communities of Interest

  • Space

DTIC Thesaurus Topics

  • Actuators
  • Adaptive Control Systems
  • Applied Mathematics
  • Automatic Pilots
  • Control Systems
  • Dynamics
  • Engineering
  • Feedback
  • Flight Control Systems
  • Governments
  • Guidance
  • Launch Vehicles
  • Neural Networks
  • Nonlinear Systems
  • Observers
  • Signal Generation
  • Vehicles

Readers

  • Robotics and Automation.
  • Systems Analysis and Design
  • Technical Research and Report Writing.

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Machine Learning Algorithms