
Accession Number : AD0717172
Title : Input Signal Synthesis in Identification Problems.
Descriptive Note : Doctoral thesis,
Corporate Author : CALIFORNIA UNIV LOS ANGELES SCHOOL OF ENGINEERING AND APPLIED SCIENCE
Personal Author(s) : Staley,Robert Michael
Report Date : 1968
Pagination or Media Count : 167
Abstract : The system considered is a scalar input scalar output discrete linear system with Gaussian additive noise on the observations. The identification problem is that of estimating the pdimensional parameter vector phi from the noisy observations. The input signal synthesis problem is that of determining the input signal the set (u sub i) which will minimize some functional related to the estimation error, subject to an energy constraint on the signal. It is assumed that the system is being operated offline during the identification procedure, so that the input signal is open to choice. The first part of the dissertation is devoted to the subject of identifiability, i.e. conditions on the system parameters, input, and initial conditions which will insure that information is obtained on all unknown parameters. Conditions are also given for the system to be completely identifiable. (Author)
Descriptors : (*CONTROL SYSTEMS, MATHEMATICAL MODELS), INFORMATION THEORY, MATRICES(MATHEMATICS), SET THEORY, MONTE CARLO METHOD, STEEPEST DESCENT METHOD, DIFFERENCE EQUATIONS, STOCHASTIC PROCESSES, RANDOM VARIABLES, THEOREMS, THESES, LINEAR SYSTEMS
Subject Categories : Statistics and Probability
Distribution Statement : APPROVED FOR PUBLIC RELEASE