Recursive estimation of the continuous-time process parameters

Carlos Canudas de Wit

doi:10.1109/CDC.1986.267390

Recursive estimation of the continuous-time process parameters

Carlos Canudas de Wit

Department of Automatic Control

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

The problem of continuous-time process parameter identification is considered. Filtered input-output process signals are used to create a linear differential equation governed by the same continuous-time process parameters. The estimation scheme is implemented by sampling the filtered signals and using a recursive least squares algorithm (RLS). The choice of filter leads to different parameter convergence properties. Conditions for parameter convergence are established in terms of frequency content of the input signal. The convergence rate is also analysed and an upper bound on the parameter error norm is given. The relation between choice of filter, sampling time selection and quality of the estimates is discussed and exemplified with simulation examples.

Original language	English
Title of host publication	25th IEEE Conference on Decision and Control, 1986
DOIs	https://doi.org/10.1109/CDC.1986.267390
Publication status	Published - 1986
Event	25th IEEE Conference on Decision and Control, 1986 - Athens, Greece Duration: 1986 Dec 10 → 1986 Dec 12 Conference number: 25

Conference

Conference	25th IEEE Conference on Decision and Control, 1986
Country/Territory	Greece
City	Athens
Period	1986/12/10 → 1986/12/12

Subject classification (UKÄ)

Control Engineering

Free keywords

Convergence
Differential equations
Frequency
Least squares approximation
Nonlinear filters
Parameter estimation
Recursive Estimation
Resonance light scattering
Signal processing
Signal sampling

Access to Document

10.1109/CDC.1986.267390

Cite this

@inproceedings{04a3d1b59d9143baa34200e500890947,

title = "Recursive estimation of the continuous-time process parameters",

abstract = "The problem of continuous-time process parameter identification is considered. Filtered input-output process signals are used to create a linear differential equation governed by the same continuous-time process parameters. The estimation scheme is implemented by sampling the filtered signals and using a recursive least squares algorithm (RLS). The choice of filter leads to different parameter convergence properties. Conditions for parameter convergence are established in terms of frequency content of the input signal. The convergence rate is also analysed and an upper bound on the parameter error norm is given. The relation between choice of filter, sampling time selection and quality of the estimates is discussed and exemplified with simulation examples.",

keywords = "Convergence, Differential equations, Frequency, Least squares approximation, Nonlinear filters, Parameter estimation, Recursive Estimation, Resonance light scattering, Signal processing, Signal sampling",

author = "{de Wit}, {Carlos Canudas}",

year = "1986",

doi = "10.1109/CDC.1986.267390",

language = "English",

booktitle = "25th IEEE Conference on Decision and Control, 1986",

note = "25th IEEE Conference on Decision and Control, 1986 ; Conference date: 10-12-1986 Through 12-12-1986",

}

TY - GEN

T1 - Recursive estimation of the continuous-time process parameters

AU - de Wit, Carlos Canudas

N1 - Conference code: 25

PY - 1986

Y1 - 1986

N2 - The problem of continuous-time process parameter identification is considered. Filtered input-output process signals are used to create a linear differential equation governed by the same continuous-time process parameters. The estimation scheme is implemented by sampling the filtered signals and using a recursive least squares algorithm (RLS). The choice of filter leads to different parameter convergence properties. Conditions for parameter convergence are established in terms of frequency content of the input signal. The convergence rate is also analysed and an upper bound on the parameter error norm is given. The relation between choice of filter, sampling time selection and quality of the estimates is discussed and exemplified with simulation examples.

AB - The problem of continuous-time process parameter identification is considered. Filtered input-output process signals are used to create a linear differential equation governed by the same continuous-time process parameters. The estimation scheme is implemented by sampling the filtered signals and using a recursive least squares algorithm (RLS). The choice of filter leads to different parameter convergence properties. Conditions for parameter convergence are established in terms of frequency content of the input signal. The convergence rate is also analysed and an upper bound on the parameter error norm is given. The relation between choice of filter, sampling time selection and quality of the estimates is discussed and exemplified with simulation examples.

KW - Convergence

KW - Differential equations

KW - Frequency

KW - Least squares approximation

KW - Nonlinear filters

KW - Parameter estimation

KW - Recursive Estimation

KW - Resonance light scattering

KW - Signal processing

KW - Signal sampling

U2 - 10.1109/CDC.1986.267390

DO - 10.1109/CDC.1986.267390

M3 - Paper in conference proceeding

BT - 25th IEEE Conference on Decision and Control, 1986

T2 - 25th IEEE Conference on Decision and Control, 1986

Y2 - 10 December 1986 through 12 December 1986

ER -

Recursive estimation of the continuous-time process parameters

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Cite this