MULTI-PARAMETER SELF-OPTIMIZING SYSTEMS USING CORRELATION TECHNIQUES,
Abstract
A class of self-optimizing systems is dd cribed which continually alters its parameters to reduce a mean-square performance criterion. The change in each hrameter is determined from an error gradient in parameter space computed by cross correlation methods which are independent of signal spectra and require no test signal or parameter perturbation. Application of this technique to ben-loop and closed-loop sys tems are included, and it is shown that a com bination of such self-optimizing systems is a possible solution to the adaptive control problem. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 05, 1963
- Accession Number
- AD0413402
Entities
People
- And Lyle E. Mcbride
- Kumpati Ss Narendra
Organizations
- Harvard University