Non-parametric methods of system identification

doi:10.1016/0005-1098(81)90084-4

Automatica

Volume 17, Issue 1, January 1981, Pages 55-69

https://doi.org/10.1016/0005-1098(81)90084-4 Get rights and content

Abstract

The non-parametric identification of systems in terms of unparametrized representations such as the impulse response and frequency response is considered. Basic approaches are outlined in a retrospective setting as are the relationships between non-parametric and parametric identification models. The article concludes with an assessment of non-parametric methods which is conducted in terms of typical industrial applications.

References (41)

G. Jenkins et al.
E.C. Levy
Complex curve fitting
IEEE Trans
(1959)
W.W. Peterson
M.S. Bartlett
J.S. Bendat et al.
R.B. Blackman et al.
J.P. Burg
Maximum entropy spectral analysis
D.W. Clarke
Generalized least squares estimation of the parameters of a dynamic model
J.W. Cooley et al.
An algorithm for the machine calculation of Fourier series
Math. Comput.
(1965)
P.J. Daniell

P.W. Davall

Applications of Statistics in the Spectral Analysis of Time-Varying Systems

W.D.T. Davies

W.D.T. Davis

Generation and properties of maximum length sequences

Control

(1966)

W.D.T. Davis

Generation and properties of maximum length sequences

Control

(1966)

W.D.T. Davis

Generation and properties of maximum length sequences

Control

(1966)

C.S. Elsden et al.

A digital transfer function analyser based on pulserate techniques

Automatica

(1969)

P. Eykhoff

K. Glover

An approximate realisation algorithm which directly identifies the system poles

K.R. Godfrey

Theory of the correlation method of dynamic analysis and its applications

Measurement Control

(1969)

N.R. Goodman

Spectra, cospectrum and quadrative spectrum of a two-dimensional stationary Gaussian process

I. Gustavsson et al.

Identification of processes in closed loop-identifiability and accuracy aspects

Automatica

(1977)

R. Iserman et al.

Comparison of six on-line identification and parallel estimation methods

Automatica

(1974)

Cited by (115)

Bias of anticipated non-parametric closed-loop frequency response for controller gain re-tuning
2023, Automatica
In data-driven controller re-tuning, when requirements exist for the closed-loop frequency response, it is essential that the estimated closed-loop frequency response for a new controller parameter set, correctly reflects the respective true closed-loop. To quantify the difference between the true and estimated frequency response, this paper presents the bias of the non-parametric closed-loop frequency response estimate for the closed-loop system with updated controller parameters. It is calculated for the case where the estimate of the closed-loop frequency response of the system with an initial controller is used, to estimate the new closed-loop frequency response with an updated controller. Such estimates are useful in the process of gain re-tuning based on closed-loop experiments, where new controller parameters are calculated to satisfy requirements for the closed-loop frequency response. It is shown that the estimate appears similar in structure to the indirect non-parametric plant estimate, and hence the bias is reduced with an increasing excitation-to-noise-ratio for the closed-loop experiment. It is also seen that the bias tends to zero when the change in the controller parameters tends to zero or the feed-forward is increased sufficiently. Simulation results demonstrate the concept for a flight-test-based gain re-tuning of a pitch rate controller for an aircraft.
An electrostatically suspended contactless platform
2021, Mechatronics
Electrostatic suspension of a silicon disk with explicit control of the lateral translational degrees-of-freedom is reported. The transduction subsystem configures electrode pairs to exert electrostatic forces on the disk and to also measure differential capacitances related to the disk position. Disk sidewall forcing electrodes are not necessary to control the disk’s lateral position because tilting the disk relative to the plane of the electrodes exerts lateral forces on the disk. Despite the fact that the disk’s lateral and angular degrees-of-freedom are strongly coupled, the system is not strongly stabilizable using only the disk’s vertical position and tilt estimates derived from electrode–disk gap measurements. Nevertheless, a stabilizing controller is proposed and lateral position measurements are added for regulating the disk’s in-plane position. Extensive experimental results corroborate the model and analysis.
Nonparametric frequency response function estimates for switching piecewise linear systems
2016, Signal Processing
This paper proposes two algorithms (ATIRMM and ALPM) for estimating the time-varying behavior of single input single output (SISO) switching piecewise linear systems. Walsh basis functions are used to capture the non-smooth fast varying dynamics. The piecewise time-varying frequency response function (TV-FRF) is approximated by the sum of a series of LTI FRFs multiplied with a set of Walsh functions. The best linear time invariant approximation (BLTIA) of the TV-FRF is estimated with small uncertainty. Besides the BLTIA, the two methods are capable of estimating the noise power spectrum and the TV-FRF. The error analysis shows that ATIRMM delivers more accurate TV-FRF and BLTIA estimations, while ALPM has better performance in noise power spectrum estimation. The conclusions are illustrated by simulations.
Application of the Newton iteration algorithm to the parameter estimation for dynamical systems
2015, Journal of Computational and Applied Mathematics
This paper uses the Newton iteration to study new identification methods for determining the parameters of dynamical systems from step responses. On the basis of the step response analysis, we present the Newton iterative algorithms. Moreover, in order to test the accuracy of the estimated parameters, the frequency and step response experiment are applied to the dynamical systems between the estimated and true models. The simulation results show that the obtained models can capture the dynamics of the systems, i.e., the estimated model’s outputs are close to the outputs of the actual systems. This confirms the effectiveness of the proposed Newton iterative identification methods.
MIMO Lowly Damped System: Free-Free Vibrations of an Aluminium Tooling Plate
2015, IFAC-PapersOnLine
Real life problems are always more complicated than expected. What is thought to be a generalised output error stochastic problem (known input, noisy output observations) of a linear system operating in open loop is often an errors-in-variables stochastic problem (noisy input, noisy output observations) of a nonlinear system operating in feedback. In addition, for lowly damped systems a "large" data set can still be "short" compared with the length of the impulse response of the system. The free-free vibrations of an aluminium tooling plate presented in this benchmark problem combine all these difficulties. The benchmark data are available at the IFAC TC1.1 repository http://tc.ifac-control.org/1/1/Data%20Repository.
Adaptive position-pressure control of a brake by wire actuator for sport motorcycles
2014, European Journal of Control
In this work the control of an electro-hydraulic brake by wire system is presented. The actuator is composed of an electric motor, a mechanical transmission, a hydraulic pump and a pipeline connected to the brake caliper. The highly nonlinear, time-varying relationship between pump piston position and plant pressure ismodelled, showing how the closed loop performances degrade without considering it. A hybrid position–pressure switching controller that aims at coping with the mentioned non-linearity is proposed. A position–pressure map estimation algorithm is introduced; this allows one to make the closed loop system robust with respect to temperature variation and brake pad wear.

View all citing articles on Scopus

^☆: The original version of this paper was presented at the 5th IFAC Symposium on Identification and System Parameter Estimation which was held in Darmstadt, Federal Republic of Germany during September, 1979. The published Proceedings of this IFAC Meeting may be ordered from: Pergamon Press Limited, Headington Hill Hall, Oxford OX3 0BW, England. This paper was recommended for publication in revised form by guest associate editor, T. Söderström.

View full text

Non-parametric methods of system identification☆

Abstract

IEEE Trans

Maximum entropy spectral analysis

Generalized least squares estimation of the parameters of a dynamic model

An algorithm for the machine calculation of Fourier series

Math. Comput.

Applications of Statistics in the Spectral Analysis of Time-Varying Systems

Generation and properties of maximum length sequences

Control

Generation and properties of maximum length sequences

Control

Generation and properties of maximum length sequences

Control

A digital transfer function analyser based on pulserate techniques

Automatica

An approximate realisation algorithm which directly identifies the system poles

Theory of the correlation method of dynamic analysis and its applications

Measurement Control

Spectra, cospectrum and quadrative spectrum of a two-dimensional stationary Gaussian process

Identification of processes in closed loop-identifiability and accuracy aspects

Automatica

Comparison of six on-line identification and parallel estimation methods

Automatica