Robust optimal experiment design for system identification

Rojas, Cristian R.; Welsh, James S.; Goodwin, Graham C.; Feuer, Arie

doi:10.1016/j.automatica.2006.12.013

Cited by 180 publications

(128 citation statements)

References 28 publications

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…In fact, experimental design is something that is rather overlooked in control engineering world; however, the benefits would be significant. Some previous work can be found in Ng et al (1977) and Rojas et al (2007).…”

Section: Model Parameter Estimationmentioning

confidence: 99%

Improvement of a Robotic Manipulator Model Based on Multivariate Residual Modeling

Gale¹,

Rahmati²,

Gravdahl³

et al. 2017

Front. Robot. AI

View full text Add to dashboard Cite

A new method is presented for extending a dynamic model of a six degrees of freedom robotic manipulator. A non-linear multivariate calibration of input-output training data from several typical motion trajectories is carried out with the aim of predicting the model systematic output error at time (t + 1) from known input reference up till and including time (t). A new partial least squares regression (PLSR) based method, nominal PLSR with interactions was developed and used to handle, unmodelled non-linearities. The performance of the new method is compared with least squares (LS). Different crossvalidation schemes were compared in order to assess the sampling of the state space based on conventional trajectories. The method developed in the paper can be used as fault monitoring mechanism and early warning system for sensor failure. The results show that the suggested methods improves trajectory tracking performance of the robotic manipulator by extending the initial dynamic model of the manipulator.

show abstract

Section: Model Parameter Estimationmentioning

confidence: 99%

Improvement of a Robotic Manipulator Model Based on Multivariate Residual Modeling

Gale¹,

Rahmati²,

Gravdahl³

et al. 2017

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…A remarkable property (established in (Rojas et al, 2007c)) is that bandlimited '1/f ' noise, defined by the spectrum…”

Section: Design Of the Reference Signalmentioning

confidence: 99%

Robust identification of process models from plant data

Goodwin

Agüero

Welsh

et al. 2008

Journal of Process Control

Self Cite

View full text Add to dashboard Cite

A precursor to any advanced control solution is the step of obtaining an accurate model of the process. Suitable models can be obtained from phenomenological reasoning, analysis of plant data or a combination of both. Here, we will focus on the problem of estimating (or calibrating) models from plant data. A key goal is to achieve robust identification. By robust we mean that small errors in the hypotheses should lead to small errors in the estimated models. We argue that, in some circumstances, it is essential that special precautions be taken to ensure that robustness is preserved. We present several practical case studies to illustrate the results.

show abstract

“…in Mehra, 1974, except for the inclusion of the term −g and the minimisation with respect to θ, which can be interpreted as a form of 'robustification' with respect to uncertainty regarding the prior knowledge of θ (Rojas et al, 2007).…”

Section: Theorem 12mentioning

confidence: 99%

“…Therefore, in the sequel we assume that θ 0 is an initial estimate of the true parameter vector θ T (see e.g. (Rojas et al, 2007)), that has been obtained from a previous open-loop experiment using an input signal with spectrum Φ u,init (ω).…”

Section: Basic Definitions In Experiments Designmentioning

confidence: 99%

“…how should one perturb the system to obtain maximal information (Fedorov, 1972;Whittle, 1973;Goodwin and Payne, 1977). Considerable work has been published in the engineering literature on this topic, focussed mainly on experiment design for dynamic systems (Levadi, 1966;Mehra, 1974;Goodwin and Payne, 1977;Zarrop, 1979;Gevers, 2005;Rojas et al, 2007). A primary motivating factor for system identification and hence experiment design, is to obtain accurate plant models for use in one of the many model based control system design methodologies.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the equivalence of least costly and traditional experiment design for control

et al. 2008

Self Cite

View full text Add to dashboard Cite

In this paper we establish the equivalence between least costly and traditional experiment design for control. We consider experiment design problems for both open and closed loop systems. In open loop, equivalence is established for three specific cases, relating to different parametrisations of the covariance expression (i.e. finite and high order approximations) and model structure (i.e. dependent and independently parameterised plant and noise models). In the closed loop setting, we consider only finite order covariance expressions. H∞ performance specifications for control are used to determine the bounds on the covariance expression for both the open and closed loop cases.

show abstract

Robust optimal experiment design for system identification

Cited by 180 publications

References 28 publications

Improvement of a Robotic Manipulator Model Based on Multivariate Residual Modeling

Improvement of a Robotic Manipulator Model Based on Multivariate Residual Modeling

Robust identification of process models from plant data

On the equivalence of least costly and traditional experiment design for control

Contact Info

Product

Resources

About