| 1. |
- Henriksson, Björn, et al.
(författare)
-
Control relevant identification of nonlinear systems using linear models
- 2001
-
Ingår i: PROCEEDINGS OF THE 2001 AMERICAN CONTROL CONFERENCE. - 0780364953 ; , s. 1178-1183
-
Konferensbidrag (refereegranskat)abstract
- In this contribution we consider control of nonlinear systems by means of linear time-invariant model based control design. It is shown that a desired closed loop response of the nonlinear system for a given reference signal can be achieved using a controller based on a linear model. This is possible if the linear model used in the control design is able to capture the input/output behaviour of the nonlinear system for the desired response. An identification method, designed for this purpose, is presented and illustrated on an numerical example.
|
|
| 2. |
- Markusson, Ola, et al.
(författare)
-
Higher order cumulant based parameter estimation in nonlinear time series models
- 2001
-
Ingår i: PROCEEDINGS OF THE 2001 AMERICAN CONTROL CONFERENCE. - 0780364953 ; , s. 4888-4889
-
Konferensbidrag (refereegranskat)abstract
- Parameter estimation in nonlinear time-series models based on higher order cumulant matching is proposed in this paper. The cumulant estimates are computed from measured and simulated data and a cost function computed from second and fourth order cumulants is used. To simplify the calculations a reduced cost function is suggested using low-dimensional slices of the cumulant functions. The estimation method is illustrated on a numerical example.
|
|
| 3. |
- Markusson, Ola, et al.
(författare)
-
Inversion of non-linear stochastic models for the purpose of parameter estimation
- 2001
-
Ingår i: International Journal of Control. - 0020-7179 .- 1366-5820. ; 74:18, s. 1783-1795
-
Tidskriftsartikel (refereegranskat)abstract
- Prediction error and maximum likelihood estimation of non-linear stochastic models requires inversion of the model, a step which may require substantial efforts, either in terms of manual calculations or through the use of software capable of symbolic computations. In this paper we show that model inversion can be easily implemented in numerical software such as, e.g. Simulink and Matrix(X), by means of a feedback connection based on the model. It is further shown how the gradients, used for the optimization of the cost function, can be generated by a linear time-varying feedback system associated with the non-linear model. In addition, we derive sufficient conditions for the existence of a stable causal inverse as well as sufficient conditions for the initial transient to decay. These conditions are given in terms of properties for a linear time-varying system associated with the non-linear model. The method is illustrated on numerical examples.
|
|
| 4. |
- Markusson, Ola, et al.
(författare)
-
Inversion of nonlinear stochastic models for parameter estimation
- 2000
-
Ingår i: Proceedings of the IEEE Conference on Decision and Control. ; , s. 1591-1596
-
Konferensbidrag (refereegranskat)abstract
- Prediction error and maximum likelihood estimation of nonlinear stochastic models requires inversion of the model, a step which may require substantial efforts, either in terms of manual calculations or through the use of software capable of symbolic computations. In this paper we show that model inversion can be easily implemented in numerical software such as, e.g., Simulink and Matrixx, by means of a feedback connection based on the model. We derive sufficient conditions for the existence of a stable causal inverse as well as sufficient conditions for the initial transient to decay. These conditions are given in terms of properties for a linear time-varying system associated with the nonlinear model. The method is illustrated on a numerical example.
|
|
| 5. |
- Markusson, Ola, et al.
(författare)
-
Iterative learning control of nonlinear non-minimum phase systems and its application to system and model inversion
- 2001
-
Ingår i: PROCEEDINGS OF THE 40TH IEEE CONFERENCE ON DECISION AND CONTROL. - 0780370619 ; , s. 4481-4482
-
Konferensbidrag (refereegranskat)abstract
- In this contribution we present a model based method for reference tracking in the Iterative Learning Control (ILC) framework. The method can be applied to nonlinear, possibly non-minimum phase, systems. The idea is to use the inverse of a linearized model in the ILC update. In the non-minimum phase case, the batch property of ILC is explored by means of non-causal filtering. Apart from reference tracking, this method is useful for system and model inversion - a problem that arises in many disciplines where nonlinear systems and models are involved, e.g. maximum likelihood identification and input design for identification for control. The method is illustrated on a numerical example.
|
|
| 6. |
- Markusson, Ola, 1971-, et al.
(författare)
-
Iterative Learning Control of Nonlinear Non-Minimum Phase Systems and its Application to System and Model Inversion
- 2002
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- In this contribution we place ILC in the realm of numerical optimization. This clarifies the role played by the design variables and how they affect e.g. convergence properties. We give a model based interpretation of these design variables and also a sufficient condition for convergence of ILC which is similar in spirit to the sufficient and necessary condition previously derived for linear systems. This condition shows that the desired performance has to be traded against modelling accuracy. Finally, one of the main benefits of ILC when non-minimum phase systems are concerned, the possibility of non-causal control, is given a comprehensive coverage.
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
|
|
