Applications of Neural Networks to Adaptive Control
Abstract
The amount of a priori knowledge required to design some modern control systems is becoming prohibitive. Two current methods addressing this problem are robust control, in which the control design is insensitive to errors in system knowledge, and adaptive control, in which the control law is adjusted in response to a continually updated model of the system. This thesis examines the application of parallel distributed processing (neural networks) to the problem of adaptive control. The structure of neural networks is introduced, focusing on the Backpropagation paradigm. A general form of controller consistent with use in neural networks is developed and combined with a discussion of linear east squares parameter estimation techniques to suggest a structure for neural network adaptive controllers. This neural network adaptive control structure is then applied to a number of estimation and control problems using as a model the longitudinal motion of the A-4 aircraft. The purpose of this thesis is to develop and demonstrate a neural network adaptive control structure consistent with adaptive control theory. Theses.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 1989
- Accession Number
- ADA225408
Entities
People
- Russell W. Scott Ii
Organizations
- Naval Postgraduate School