System Identification Using Recursive Least Squares
by Robert Weber and Sean Gregerson Advisor: Dr. Winfred Anakwa In order to design a controller for a dynamic system such as a position
controller, a mathematical model that describes its behavior must be constructed.
In this investigation, an algorithm known as Recursive Least Squares (RLS)
will be used to determine a discrete transfer function of a plant from
past input and output data. A Texas Instruments TMS320C30 floating-point
digital signal processor (DSP) evaluation module (EVM) and Mathwork's Matlab
are used in conjunction with a personal computer as a test bench platform
for the RLS implementation. Two 12-bit A/D converters connected to the
dynamic system and the EVM are used to collect the input and output data
from the single-input-single-output (SISO) dynamic system before the TMS320C30
is used for execution of RLS algorithm. Thus, the dynamic system coefficients
which best fit its characteristics may be determined in real-time and used
for control.
|
[Prospective Students]
[Current Students]
[Alumni]
[Faculty]
[Home] [Contact us] [Curriculum] [Senior Projects] [Research] [People] [Links] Copyright (c)1995-2013 Bradley University. All rights reserved. . . |