Control system
AssigneeBodenseewerk Geratetechnik GmbH
InventorUwe Krogmann
Life of this patent
Estimating the term…
Abstract
The invention relates to a control system to which a state vector representing the states of a controlled system is applied. The control system provides a correcting variables vector of optimized correcting variables. The relation between state vector and correcting variables vector is defined by a matrix of weights. These weights depend on the solution of the state dependent Riccati equation. An equation solving system for solving the state dependent Riccati equation in real time is provided. The state vector is applied to this equation solving system. The solution of the state dependent Riccati equation is transferred to the control system to determine the weights.
Claims12
A control system having input means and output means, for contolling a controlled system having states which are represented by a state vector, comprising means for applying said state vector to said input means of said control system, said control system providing, at said output means, correcting variables which are represented by a correcting variables vector, the relation between said state vector and said correcting variables vector being defined by a matrix of weights, and further comprising equation solving means for algorithmically solving an optimization equation in real time and providing a solution of said optimization equation, and means for applying said state vector to said equation solving means, said solution of said optimization equation being transferred to said control system to determine said weights of said matrix, whereby said control system provides an optimal correcting variables vector.
A control system having input means and output means, for contolling a controlled system having at least one state represented by a state vector, comprising means for applying said state vector to said input means of said control system, said control system providing, at said output means, at least one correcting variable represented by a correcting variables vector, the relation between said state vector and said correcting variables vector being defined by a factor or a matrix of weights;
- and further comprising:
- adaptive model means for modeling said controlled system and for providing, from said state vector and said correcting variables vector, an estimated value of said state vector, means for applying said state vector and said correcting variables vector to said adaptive model means, means for forming the difference of said state vector and said estimated value of the state vector to provide a first vectorial training signal for training said adaptive model means, and means for training said adaptive model means to reduce said difference, thereby to provide a trained model, means for deriving a second vectorial training signal from said trained model of said controlled system, a control system-side network, and means for training said control system-side network in accordance with said second vectorial training signal, means for applying said state vector and said correcting variables vector to said control system-side network, said network being trained by said second vectorial training signal to provide therefrom a correction value to be applied to said optimal correcting variables vector to form an actual correcting variables vector applied to said controlled system.
Dependencies are inferred from the claim text.