Please use this identifier to cite or link to this item:
http://hdl.handle.net/11375/13604
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Sinha, N. K. | en_US |
dc.contributor.author | Sen, Abhijit | en_US |
dc.date.accessioned | 2014-06-18T17:04:33Z | - |
dc.date.available | 2014-06-18T17:04:33Z | - |
dc.date.created | 2009-08-21 | en_US |
dc.date.issued | 1976-05 | en_US |
dc.identifier.other | opendissertations/844 | en_US |
dc.identifier.other | 1754 | en_US |
dc.identifier.other | 962434 | en_US |
dc.identifier.uri | http://hdl.handle.net/11375/13604 | - |
dc.description.abstract | <p>The problem of finding the characterizing parameters of an unknown linear discrete-time system "on-line" from the measurements of the input and output data is considered in detail. Two new algorithms for system identification have been proposed for the estimation of parameters of time-invariant single-input single-output systems. The first algorithm, called the Generalized Pseudoinverse, is the recursive version of the generalized least squares algorithm. The second algorithm, combining pseudoinverse and stochastic approx. algorithm, is an iterative scheme and found to be computationally more efficient than the first algorithm. The two algorithms have been used in a number of simulation problems to test the reliability and efficiency of the methods. A critical comparison of the new method with the existing algorithms has shown the new algorithm to be reliable in most of the problems considered. Also a new recursive pseudoinverse algorithm has been developed for identification of a multi-variable transfer function model.</p> | en_US |
dc.subject | Electrical and Electronics | en_US |
dc.subject | Electrical and Electronics | en_US |
dc.title | On-line System Identification | en_US |
dc.type | thesis | en_US |
dc.contributor.department | Electrical Engineering | en_US |
dc.description.degree | Doctor of Philosophy (PhD) | en_US |
Appears in Collections: | Open Access Dissertations and Theses |
Files in This Item:
File | Size | Format | |
---|---|---|---|
fulltext.pdf | 4.31 MB | Adobe PDF | View/Open |
Items in MacSphere are protected by copyright, with all rights reserved, unless otherwise indicated.