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

摘要

A method for computer-aided closed and/or open-loop control of a technical system is provided. A first value of an output quantity is predicted on a data-based model at a current point in time. A second value of the output quantity is determined from an analytical model. The state of the technical system at the current point is assigned a confidence score in the correctness of prediction of the data-based model. A third value of the output quantity is determined from the first and second value as a function of the confidence score for controlling the technical system. A suitable value for the output quantity can be derived from the analytical model even for regions of the technical system in which the quality of prediction of the data-based model is low because of a small set of training data. The technical systems can be turbines, such as gas turbines.

主权项

1. 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 learned action selection rule which determines an action to be executed at the current point in time as a function of the state of the technical system at the current point in time.