Abstract: A method for controlling a gas turbine, having a measurement step, a prediction step which is carried out after the measurement step, and a control step which is carried out after the prediction step. In the measurement step, a state variable of a combustion within a gas turbine is measured. In the prediction step, a future combustion dynamic is predicted using the measured state variable. In the control step, a control signal is output using the prediction of the future combustion dynamic.

Abstract: In order to reproduce noise components of lossy recorded operating signals of a technical system, a neural network is trained to reproduce a recorded target operating signal and a statistical distribution of a stochastic component of the recorded target operating signal on the basis of a recorded input operating signal. A current input operating signal of the technical system is then supplied to the trained neural network. An output signal having a noise component modelled on the statistical distribution is generated on the basis of the supplied current input operating signal and a noise signal. The output signal is then output as the current target operating signal for controlling the technical system.

Abstract: A process for controlling a conveyor line for general cargo, the conveyor line including a plurality of consecutive conveyor line portions , each of which is driven by a drive. One or more sensors for detecting general cargo are located on at least some of the conveyor line portions. The drives are controlled by means of a computing unit using a machine learning model. The machine learning model accomplishes this by repeatedly receiving input data including a vector of a fixed length, each vector element being associated with a section of the conveyor line and indicating a current proportional occupancy of the respective section by an item of general cargo. Each conveyor line portion is split into a plurality of the sections of identical size. An apparatus or a system for data processing, a computer program, a computer-readable data carrier and a data carrier signal is also provided.

Abstract: In order to control a technical system using a control model, a transformation function is provided for reducing and/or obfuscating operating data of the technical system so as to obtain transformed operating data. In addition, the control model is generated by a model generator according to a first set of operating data of the technical system. In an access domain separated from the control model, a second set of operating data of the technical system is recorded and transformed by the transformation function into a transformed second set of operating data which is received by a model execution system. The control model is then executed by the model execution system, by supplying the transformed second set of operating data in an access domain separated from the second set of operating data, control data being derived from the transformed second set of operating data.

Abstract: A machine learning module is provided which is trained to generate from a design data record specifying a design variant of a product, a first performance signal quantifying a predictive performance of the design variant and a predictive uncertainty of the predictive performance. A variety of design data records each specifying a design variant of the product is generated. For a respective design data record, the following steps are performed: a first performance signal and a corresponding predictive uncertainty are generated, depending on the predictive uncertainty, a simulation yielding a second performance signal quantifying a simulated performance of the corresponding design variant is either run or skipped, and a performance value is derived from the second performance signal if the simulation is run or, otherwise, from the first performance signal. Depending on the derived performance values, a performance-optimizing design data record is determined and output to control the production plant.

Abstract: A control device for a technical system, state-specific safety information about an admissibility of a control action signal is read in by a safety module is provided. Furthermore, a state signal indicating a state of the technical system is supplied to a machine learning module and to the safety module. In addition, an output signal of the machine learning module is supplied to the safety module. The output signal is converted into an admissible control action signal by the safety module on the basis of the safety information depending on the state signal. Furthermore, a performance for control of the technical system by the admissible control action signal is ascertained, and the machine learning module is trained to optimize the performance. The control device is then configured by the trained machine learning module.

Abstract: A method for controlling a gas turbine, having a measurement step, a prediction step which is carried out after the measurement step, and a control step which is carried out after the prediction step. In the measurement step, a state variable of a combustion within a gas turbine is measured. In the prediction step, a future combustion dynamic is predicted using the measured state variable. In the control step, a control signal is output using the prediction of the future combustion dynamic.

Abstract: A method of controlling a complex system and a gas turbine being controlled by the method are provided. The method comprises providing training data, which training data represents at least a portion of a state space of the system; setting a generic control objective for the system and a corresponding set point; and exploring the state space, using Reinforcement Learning, for a control policy for the system which maximizes an expected total reward. The expected total reward depends on a randomized deviation of the generic control objective from the corresponding set point.

Abstract: In order to control a technical system using a control model, a transformation function is provided for reducing and/or obfuscating operating data of the technical system so as to obtain transformed operating data. In addition, the control model is generated by a model generator according to a first set of operating data of the technical system. In an access domain separated from the control model, a second set of operating data of the technical system is recorded and transformed by the transformation function into a transformed second set of operating data which is received by a model execution system. The control model is then executed by the model execution system, by supplying the transformed second set of operating data in an access domain separated from the second set of operating data, control data being derived from the transformed second set of operating data.

Abstract: A technical system controller is trained using a machine learning method. For this purpose, a chronological sequence of training data is detected for the machine learning method. The training data includes state data, which specifies states of the technical system, and control action data, which specifies control actions of the technical system. A chronological sequence of control action data is extracted specifically from the training data and is checked for a change over time. If a change over time is ascertained, a time window including the change is ascertained, and training data which can be found within the time window is extracted in a manner which is specific to the time window. The controller is then trained by the machine learning method using the extracted training data and is thus configured for controlling the technical system.

Abstract: For reducing oscillations in a technical system plurality of different controller settings for the technical system is received. For a respective controller setting signal representing a time series of operational data of the technical system controlled by the respective controller setting is received, the signal is processed, whereby the processing includes a transformation into a frequency domain, and an entropy value of the processed signal is determined. Depending on the determined entropy values a controller setting from the plurality of controller settings is selected, and the selected controller setting is output for configuring the technical system.

Abstract: Provided is a method for the model-based determination of a system status of a dynamic system by means of a model, wherein: a recurrent neural network is provided as the model of the dynamic system; the model is supplied with a time series of potentially recordable measurement values as an input variable, the values comprising recorded and missing measurement values; at least one system status associated with a time point is generated from the model, from which status at least one target value belonging to the respective time point can be determined; sequential system statuses transition into one other by means of a respective status transition; and a correction of at least one system status is carried out on the basis of the time series with the aid of the status transition.

Abstract: Provided is an optical sensor directed into a combustion chamber is used to selectively sense a predefined spectral range of an optical spectrum for different light paths running through the combustion chamber to measure a gas temperature distribution in the combustion chamber. A spectral intensity is determined for each spectral range and associated with an item of light path information which identifies the light path in question. The spectral intensities determined and and the associated items of light path information are fed as input data to a machine learning routine which is trained to reproduce spatially resolved training temperature distributions. Output data from the machine learning routine are then output as the gas temperature distribution.

Abstract: A method of controlling a complex system and a gas turbine being controlled by the method are provided. The method comprises providing training data, which training data represents at least a portion of a state space of the system; setting a generic control objective for the system and a corresponding set point; and exploring the state space, using Reinforcement Learning, for a control policy for the system which maximizes an expected total reward. The expected total reward depends on a randomized deviation of the generic control objective from the corresponding set point.

Abstract: In order to determine a power output by a first energy producer, wherein the first energy producer is coupled to a second energy producer, a first soft sensor which is trained to determine an individual mode power value of the first energy producer is queried. In a mode combining the first and second energy producers, an individual mode power value determined for the first energy producer by the first soft sensor is read in here. Furthermore, a second soft sensor determines a first power value for the first energy producer and a second power value for the second energy producer. In addition, a total power of the energy producers is determined.

Abstract: Disclosed is a method for the computer-assisted modeling of a technical system. One or more output vectors are modeled dependent on one or more input vectors by the learning process of a neural network on the basis of training data of known input vectors and output vectors. Each output vector comprises one or more operating variables of the technical system, and each input vector comprises one or more input variables that influence the operating variable(s). The neural network is a feedforward network with an input layer, a plurality of hidden layers, and an output layer. The output layer comprises a plurality of output clusters, each of which consists of one or more output neurons, the plurality of output clusters corresponding to the plurality of hidden layers. Each output cluster describes the same output vector and is connected to another hidden layer.

Abstract: A method for improving the usability of photovoltaic installations (PV installations) by taking account of shading information of adjacent PV installations for forecasting the power output by a relevant PV installation is provided. In particular, cloud movements and cloud shapes are taken into account. This improves the accuracy of the forecast. Here, it is advantageous that short-term forecasts in relation to e.g. the next 15 minutes are possible and a substitute energy source can be activated accordingly, in good time, prior to a dip in the power output by the PV installation. The invention can be used e.g. in the field of renewable energies, PV installations or smart grids.

Abstract: A method for computer-assisted monitoring of an electrical energy-generating installation, in which output variables (y(t)) of the installation are prognosticated using a data-driven model (NN) based on corresponding input variables (x(t)). A confidence measurement (C(t)) is determined for respective input variables (x(t)), using one or more density estimators (DE), this measurement being higher, the greater the similarity of the input variables (x(t)) to known input variables from training data with which the data-driven model (NN) and the density estimator (DE) are taught. Based thereon, an average weighted deviation (E(t)) is determined between the prognosticated output variables (y(t)) and the output variables (y0(t)) actually occurring. If the average weighted deviation (y(t)) exceeds a predetermined threshold (ETh) successive times, an error in operation is detected and an alarm is issued.

Abstract: Disclosed is a method for the computer-assisted modeling of a technical system. One or more output vectors are modeled dependent on one or more input vectors by the learning process of a neural network on the basis of training data of known input vectors and output vectors. Each output vector comprises one or more operating variables of the technical system, and each input vector comprises one or more input variables that influence the operating variable(s). The neural network is a feedforward network with an input layer, a plurality of hidden layers, and an output layer. The output layer comprises a plurality of output clusters, each of which consists of one or more output neurons, the plurality of output clusters corresponding to the plurality of hidden layers. Each output cluster describes the same output vector and is connected to another hidden layer.

Abstract: A method for improving the usability of photovoltaic installations (PV installations) by taking account of shading information of adjacent PV installations for forecasting the power output by a relevant PV installation is provided. In particular, cloud movements and cloud shapes are taken into account. This improves the accuracy of the forecast. Here, it is advantageous that short-term forecasts in relation to e.g. the next 15 minutes are possible and a substitute energy source can be activated accordingly, in good time, prior to a dip in the power output by the PV installation. The invention can be used e.g. in the field of renewable energies, PV installations or smart grids.