1. 
 Agüero, Juan C., et al.
(författare)

Accuracy of linear multipleinput multipleoutput (MIMO) models obtained by maximum likelihood estimation
 2012

Ingår i: Automatica.  00051098. ; 48:4, s. 632637

Tidskriftsartikel (refereegranskat)abstract
 In this paper, we study the accuracy of linear multipleinput multipleoutput (MIMO) models obtained by maximum likelihood estimation. We present a frequencydomain representation for the information matrix for general linear MIMO models. We show that the variance of estimated parametric models for linear MIMO systems satisfies a fundamental integral tradeoff. This tradeoff is expressed as a multivariable 'waterbed' effect. An extension to spectral estimation is also discussed.


2. 
 Akçay, Hüseyin, et al.
(författare)

On the Choice of Norms in System Identification
 1994

Ingår i: Proceedings of the 10th IFAC Symposium on System Identification.  9780080422251 ; s. 103108

Konferensbidrag (refereegranskat)abstract
 In this paper we discuss smooth and sensitive norms for prediction error system identification when the disturbances are magnitude bounded. Formal conditions for sensitive norms, which give an order of magnitude faster convergence of the parameter estimate variance, are developed. However, it also is shown that the parameter estimate variance convergence rate of sensitive norms is arbitrarily bad for certain distributions. A necessary condition for a norm to be statistically robust with respect to the family F(C) of distributions with support [C, C] for some arbitrary C>0 is that its second derivative does not vanish on the support. A direct consequence of this observation is that the quadratic norm is statistically robust among all lpnorms, p⩽2<∞ for F(C).


3. 
 Akçay, Hüseyin, et al.
(författare)

On the Choice of Norms in System Identification
 1996

Rapport (övrigt vetenskapligt)abstract
 In this paper we discuss smooth and sensitive norms for prediction error system identification when the disturbances are magnitude bounded. Formal conditions for sensitive norms, which give an order of magnitude faster convergence of the parameter estimate variance, are developed. However, it also is shown that the parameter estimate variance convergence rate of sensitive norms is arbitrarily bad for certain distributions. A necessary condition for a norm to be statistically robust with respect to the family F(C) of distributions with support [C, C] for some arbitrary C>0 is that its second derivative does not vanish on the support. A direct consequence of this observation is that the quadratic norm is statistically robust among all lpnorms, p⩽2<∞ for F(C).


4. 
 Akçay, Hüseyin, et al.
(författare)

On the Choice of Norms in System Identification
 1994

Rapport (övrigt vetenskapligt)abstract
 In this paper we discuss smooth and sensitive norms for prediction error system identification when the disturbances are magnitude bounded. Formal conditions for sensitive norms, which give an order of magnitude faster convergence of the parameter estimate variance, are developed. However, it also is shown that the parameter estimate variance convergence rate of sensitive norms is arbitrarily bad for certain distributions. A necessary condition for a norm to be statistically robust with respect to the family F(C) of distributions with support [C, C] for some arbitrary C>0 is that its second derivative does not vanish on the support. A direct consequence of this observation is that the quadratic norm is statistically robust among all lpnorms, p⩽2<∞ for F(C).


5. 
 Akçay, Hüseyin, et al.
(författare)

On the Choice of Norms in System Identification
 1995

Rapport (övrigt vetenskapligt)abstract
 In this paper we discuss smooth and sensitive norms for prediction error system identification when the disturbances are magnitude bounded. Formal conditions for sensitive norms, which give an order of magnitude faster convergence of the parameter estimate variance, are developed. However, it also is shown that the parameter estimate variance convergence rate of sensitive norms is arbitrarily bad for certain distributions. A necessary condition for a norm to be statistically robust with respect to the family F(C) of distributions with support [C, C] for some arbitrary C>0 is that its second derivative does not vanish on the support. A direct consequence of this observation is that the quadratic norm is statistically robust among all lpnorms, p⩽2<∞ for F(C).


6. 
 Akçay, Hüseyin, et al.
(författare)

The LeastSquares Identification of FIR Systems Subject to WorstCase Noise
 1993

Rapport (övrigt vetenskapligt)abstract
 The leastsquares identification of FIR systems is analyzed assuming that the noise is a bounded signal and the input signal is a pseudorandom binary sequence. A lower bound on the worstcase transfer function error shows that the lestsquare estimate of the transfer function diverges as the order of the FIR system is increased. This implies that, in the presence of the worstcase noise, the tradeoff between the estimation error due to the disturbance and the bias error (due to unmodeled dynamics) is significantly different from the corresponding tradeoff in the random error case: with a worstcase formulation, the model complexity should not increase indefinitely as the size of the data set increases.


7. 
 Akçay, Hüseyin, et al.
(författare)

The LeastSquares Identification of FIR Systems Subject to WorstCase Noise
 1994

Ingår i: Proceedings of the 10th IFAC Symposium on System Identification.  9780080422251 ; s. 8590

Konferensbidrag (refereegranskat)abstract
 The leastsquares identification of FIR systems is analyzed assuming that the noise is a bounded signal and the input signal is a pseudorandom binary sequence. A lower bound on the worstcase transfer function error shows that the lestsquare estimate of the transfer function diverges as the order of the FIR system is increased. This implies that, in the presence of the worstcase noise, the tradeoff between the estimation error due to the disturbance and the bias error (due to unmodeled dynamics) is significantly different from the corresponding tradeoff in the random error case: with a worstcase formulation, the model complexity should not increase indefinitely as the size of the data set increases.


8. 
 Akçay, Hüseyin, et al.
(författare)

The LeastSquares Identification of FIR Systems Subject to WorstCase Noise
 1994

Ingår i: Systems & control letters (Print).  01676911. ; 23:5, s. 329338

Tidskriftsartikel (refereegranskat)abstract
 The leastsquares identification of FIR systems is analyzed assuming that the noise is a bounded signal and the input signal is a pseudorandom binary sequence. A lower bound on the worstcase transfer function error shows that the leastsquare estimate of the transfer function diverges as the order of the FIR system is increased. This implies that, in the presence of the worstcase noise, the tradeoff between the estimation error due to the disturbance and the bias error (due to unmodeled dynamics) is significantly different from the corresponding tradeoff in the random error case: with a worstcase formulation, the model complexity should not increase indefinitely as the size of the data set increases.


9. 
 Akçay, Hüseyin, et al.
(författare)

The LeastSquares Identification of FIR Systems Subject to WorstCase Noise
 1994

Rapport (övrigt vetenskapligt)abstract
 The leastsquares identification of FIR systems is analyzed assuming that the noise is a bounded signal and the input signal is a pseudorandom binary sequence. A lower bound on the worstcase transfer function error shows that the leastsquare estimate of the transfer function diverges as the order of the FIR system is increased. This implies that, in the presence of the worstcase noise, the tradeoff between the estimation error due to the disturbance and the bias error (due to unmodeled dynamics) is significantly different from the corresponding tradeoff in the random error case: with a worstcase formulation, the model complexity should not increase indefinitely as the size of the data set increases.


10. 
 Alberer, Daniel, et al.
(författare)

System Identification for Automotive Systems : Opportunities and Challenges
 2012

Ingår i: Identification for Automotive Systems.  Springer London.  9781447122203 ; s. 110

Bokkapitel (övrigt vetenskapligt)abstract
 Without control many essential targets of the automotive industry could not be achieved. As control relies directly or indirectly on models and model quality directly influences the control performance, especially in feedforward structures as widely used in the automotive world, good models are needed. Good first principle models would be the first choice, and their determination is frequently difficult or even impossible. Against this background methods and tools developed by the system identification community could be used to obtain fast and reliably models, but a large gap seems to exist: neither these methods are sufficiently well known in the automotive community, nor enough attention is paid by the system identification community to the needs of the automotive industry. This introduction summarizes the state of the art and highlights possible critical issues for a future cooperation as they arose from an ACCM Workshop on Identification for Automotive Systems recently held in Linz, Austria.

