Recursive Estimation of the Parameters of Linear Systems with Time Delay

Pupeikis, Rimantas

doi:10.1016/s1474-6670(17)60657-8

Cited by 19 publications

(24 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RDI algorithm as it is presented above does not take into account that the delay time estimates may converge to a wrong value because of the multimodality of the cost function with respect to delay time [19]. Furthermore, if the delay time estimate is incorrect, the linear coefficients will not converge to the correct values (and vise versa).…”

Section: F Constraints On the Recursive Delay Time Identifiermentioning

confidence: 99%

“…Banyasz and Keviczky [18] provide an insightful derivation based on minimizing a quadratic error function based on a pure gain pure delay system. Unfortunately, they fail to recognize many of the problems associated with such an approach such as the fact that: i) the cost function is not unimodal with respect to delay time [19], ii) derivation with respect to delay time involves differentiation of the observations which can not be blindly performed in case of stochastic signals, and iii) problems associated with identification of linear ARMAX models in case of small time steps [17] on which their derivations were based.…”

Section: Introductionmentioning

confidence: 99%

“…The most promising optimization based approach so far is one in which the estimation error is filtered such that the resulting generalized criterion function with respect to the delay time becomes unimodal are given in [19], [20]. However, their multistep iterative methods do not apply to time varying systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Estimation of time-varying delay time in nonstationary linear systems: an approach to monitor human operator adaptation in manual tracking tasks

Boer

Kenyon

1998

IEEE Trans. Syst., Man, Cybern. A

View full text Add to dashboard Cite

Abstract-Adaptability is one of man's advantages over machines. Perhaps one of the reasons for our limited understanding about human adaptation during manual tracking tasks is that we have only limited tools to identify the model coefficients (especially delay time) of an adapting human operator. In this paper, we introduce a discrete time recursive delay identifier (RDI) capable of simultaneously estimating a human operator's nonstationary delay time and linear model coefficients. At its core lies the extended Kalman filter (EKF). Our goal to obtain fractional delay time estimates was realized by using the bicubic interpolation scheme as part of the EKF to provide subsample magnitude and derivative estimates of the observed input/output time series. While this theoretically limits the RDI's applicability to bandlimited or differentiable signals, this is seldom a concern in practice. Based on data from simulated and experimental time varying tracking tasks, we show the RDI's potential to substantially increase our understanding about human adaptations thus perhaps offering new avenues for machine adaptation.

show abstract

Section: F Constraints On the Recursive Delay Time Identifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of time-varying delay time in nonstationary linear systems: an approach to monitor human operator adaptation in manual tracking tasks

Boer

Kenyon

1998

IEEE Trans. Syst., Man, Cybern. A

View full text Add to dashboard Cite

show abstract

“…The time-delay is a continuous parameter, and all parameters are estimated by a prediction error/maximum likelihood method, using iterative search [23]. It is well known that the objective function may have many local minima in this case, [8,26,29], so the initialization of the parameters must be done with great care. Here we use an initialization method implemented in [24], based on ARXS (see below), followed by a global search for best time delay and model zero for fixed poles, followed by local Gauss-Newton search for all free parameters.…”

Section: 23mentioning

confidence: 99%

“…ARX models, with different time-delays and choosing the best is also of this subclass [2,31]. (b) Two-step explicit methods [5,29]. Alternating between estimating the time-delay and the other parameters.…”

mentioning

confidence: 99%

A review of time-delay estimation techniques

Björklund

Ljung

42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475)

View full text Add to dashboard Cite

Tracking coefficients of a nonstationary system, followed by static nonlinearity jointly with the time delay

Pupeikis

2020

Adaptive Control & Signal

View full text Add to dashboard Cite

Summary This paper considers a block‐oriented nonlinear Wiener system that consists of a linear block with real time‐varying unknown coefficients and pure time delay followed by a static invertible nonlinearity. Consideration is concentrated on the joint linear block coefficients and time delay tracking by processing observation samples. Two problems are analyzed. The first one is the avoidance of mean‐squares prediction error function multiextremality for time delay while seeking the global minimum. The other problem consists of the applicability of unified adaptive algorithms, based on the schema with corrective operators for the Wiener system. An approach used to transform the multiextremal criterion into a unimodal function for a nonstationary linear system, in respect of the time delay, is developed and analyzed for a block‐oriented nonlinear Wiener system with time‐varying coefficients and a time delay. The recursive parametric identification approach, based on the method of corrective operators, is developed for the nonstationary dynamic Wiener system. Applicability of algorithms is supported by various simulation tests solved by a computer.

show abstract

Recursive Estimation of the Parameters of Linear Systems with Time Delay

Cited by 19 publications

References 2 publications

Estimation of time-varying delay time in nonstationary linear systems: an approach to monitor human operator adaptation in manual tracking tasks

Estimation of time-varying delay time in nonstationary linear systems: an approach to monitor human operator adaptation in manual tracking tasks

A review of time-delay estimation techniques

Tracking coefficients of a nonstationary system, followed by static nonlinearity jointly with the time delay

Contact Info

Product

Resources

About