Method for computer-aided closed-loop and/or open-loop control of a technical system

A method for computer-aided controlling a technical system, wherein the technical system is described with a plurality of points in time by a state comprising a plurality of state variables and an action comprising a plurality of action variables to be executed in the state, the method comprising:

• predicting a first value for an output quantity having a plurality of output variables of the technical system from a state at a current point in time based on a data-based model, wherein the data-based model is learned with training data from known states and actions of the technical system;
• predicting a second value for the output quantity from the state at the current point in time based on an analytical model, wherein the analytical model analytically describes a behavior of the technical system;
• allocating a confidence score to the state of the technical system at the current point in time, wherein the confidence score describes a confidence in correctness of the prediction of the data-based model for the state of the technical system at the current point in time;
• determining a third value for the output quantity from the first and the second value for the output quantity as a function of the confidence score, wherein the first value is weighted greater in determining the third value if a confidence is higher in the confidence score;
• and
• controlling the technical system using the third value,
• wherein the data-based model comprises a recurrent neural network.

A method for computer-aided controlling a technical system, wherein the technical system is described with a plurality of points in time by a state comprising a plurality of state variables and an action comprising a plurality of action variables to be executed in the state, the method comprising:

• predicting a first value for an output quantity having a plurality of output variables of the technical system from a state at a current point in time based on a data-based model, wherein the data-based model is learned with training data from known states and actions of the technical system;
• predicting a second value for the output quantity from the state at the current point in time based on an analytical model, wherein the analytical model analytically describes a behavior of the technical system;
• allocating a confidence score to the state of the technical system at the current point in time, wherein the confidence score describes a confidence in correctness of the prediction of the data-based model for the state of the technical system at the current point in time;
• determining a third value for the output quantity from the first and the second value for the output quantity as a function of the confidence score, wherein the first value is weighted greater in determining the third value if a confidence is higher in the confidence score;
• and
• controlling the technical system using the third value,
• wherein the confidence score is represented by a value between 0 and 1 with the value 1 representing maximum confidence, and wherein the third value is determined as a sum of the first value multiplied by the confidence score and the second value multiplied by a difference between 1 and the confidence score.

A method for computer-aided controlling a technical system, wherein the technical system is described with a plurality of points in time by a state comprising a plurality of state variables and an action comprising a plurality of action variables to be executed in the state, the method comprising:

• predicting a first value for an output quantity having a plurality of output variables of the technical system from a state at a current point in time based on a data-based model, wherein the data-based model is learned with training data from known states and actions of the technical system;
• predicting a second value for the output quantity from the state at the current point in time based on an analytical model, wherein the analytical model analytically describes a behavior of the technical system;
• allocating a confidence score to the state of the technical system at the current point in time, wherein the confidence score describes a confidence in correctness of the prediction of the data-based model for the state of the technical system at the current point in time;
• determining a third value for the output quantity from the first and the second value for the output quantity as a function of the confidence score, wherein the first value is weighted greater in determining the third value if a confidence is higher in the confidence score;
• and
• controlling the technical system using the third value,
• wherein the analytical model is learned based on a neural network.

A method for computer-aided controlling a technical system, wherein the technical system is described with a plurality of points in time by a state comprising a plurality of state variables and an action comprising a plurality of action variables to be executed in the state, the method comprising:

• predicting a first value for an output quantity having a plurality of output variables of the technical system from a state at a current point in time based on a data-based model, wherein the data-based model is learned with training data from known states and actions of the technical system;
• predicting a second value for the output quantity from the state at the current point in time based on an analytical model, wherein the analytical model analytically describes a behavior of the technical system;
• allocating a confidence score to the state of the technical system at the current point in time, wherein the confidence score describes a confidence in correctness of the prediction of the data-based model for the state of the technical system at the current point in time;
• determining a third value for the output quantity from the first and the second value for the output quantity as a function of the confidence score, wherein the first value is weighted greater in determining the third value if a confidence is higher in the confidence score;
• and
• controlling the technical system using the third value,
• wherein the technical system comprises a turbine.