摘要:
For controlling a target system, such as a gas or wind turbine or another technical system, a pool of control policies is used. The pool of control policies including a plurality of control policies and weights for weighting each control policy of the plurality of control policies are received. The plurality of control policies is weighted by the weights to provide a weighted aggregated control policy. The target system is controlled using the weighted aggregated control policy, and performance data relating to a performance of the controlled target system is received. The weights are adjusted based on the received performance data to improve the performance of the controlled target system. The plurality of control policies is reweighted by the adjusted weights to adjust the weighted aggregated control policy.
摘要:
A method for the computer-aided control of a technical system is provided. A recurrent neuronal network is used for modeling the dynamic behaviour of the technical system, the input layer of which contains states of the technical system and actions carried out on the technical system, which are supplied to a recurrent hidden layer. The output layer of the recurrent neuronal network is represented by an evaluation signal which reproduces the dynamics of technical system. The hidden states generated using the recurrent neural network are used to control the technical system on the basis of a learning and/or optimization method.
摘要:
A method for computer-assisted modeling of a technical system is disclosed. At multiple different operating points, the technical system is described by a first state vector with first state variable(s) and by a second state vector with second state variable(s). A neural network comprising a special form of a feed-forward network is used for the computer-assisted modeling of said system. The feed-forward network includes at least one bridging connector that connects a neural layer with an output layer, thereby bridging at least one hidden layer, which allows the training of networks with multiple hidden layers in a simple manner with known learning methods, e.g., the gradient descent method. The method may be used for modeling a gas turbine system, in which a neural network trained using the method may be used to estimate or predict nitrogen oxide or carbon monoxide emissions or parameters relating to combustion chamber vibrations.
摘要:
A method for computer-assisted modeling of a technical system is disclosed. At multiple different operating points, the technical system is described by a first state vector with first state variable(s) and by a second state vector with second state variable(s). A neural network comprising a special form of a feed-forward network is used for the computer-assisted modeling of said system. The feed-forward network includes at least one bridging connector that connects a neural layer with an output layer, thereby bridging at least one hidden layer, which allows the training of networks with multiple hidden layers in a simple manner with known learning methods, e.g., the gradient descent method. The method may be used for modeling a gas turbine system, in which a neural network trained using the method may be used to estimate or predict nitrogen oxide or carbon monoxide emissions or parameters relating to combustion chamber vibrations.
摘要:
A method for the computer-supported generation of a data-driven model of a technical system, in particular of a gas turbine or wind turbine, based on training data is disclosed. The data-driven model is preferably learned in regions of training data having a low data density. According to the invention, it is thus ensured that the data-driven model is generated for information-relevant regions of the training data. The data-driven model generated is used in a particularly preferred embodiment for calculating a suitable control and/or regulation model or monitoring model for the technical system. By determining optimization criteria, such as low pollutant emissions or low combustion dynamics of a gas turbine, the service life of the technical system in operation can be extended. The data model generated by the method according to the invention can furthermore be determined quickly and using low computing resources, since not all training data is used for learning the data-driven model.
摘要:
For controlling a target system, operational data of a plurality of source systems are used. The data of the source systems are received and are distinguished by source system specific identifiers. By a neural network, a neural model is trained on the basis of the received operational data of the source systems taking into account the source system specific identifiers, where a first neural model component is trained on properties shared by the source systems and a second neural model component is trained on properties varying between the source systems. After receiving operational data of the target system, the trained neural model is further trained on the basis of the operational data of the target system, where a further training of the second neural model component is given preference over a further training of the first neural model component. The target system is controlled by the further trained neural network.
摘要:
A method for the computer-supported generation of a data-driven model of a technical system, in particular of a gas turbine or wind turbine, based on training data is disclosed. The data-driven model is preferably learned in regions of training data having a low data density. According to the invention, it is thus ensured that the data-driven model is generated for information-relevant regions of the training data. The data-driven model generated is used in a particularly preferred embodiment for calculating a suitable control and/or regulation model or monitoring model for the technical system. By determining optimization criteria, such as low pollutant emissions or low combustion dynamics of a gas turbine, the service life of the technical system in operation can be extended. The data model generated by the method according to the invention can furthermore be determined quickly and using low computing resources, since not all training data is used for learning the data-driven model.
摘要:
A method of computer-assisted learning of control and/or feedback control of a technical system is provided. A statistical uncertainty of training data used during learning is suitably taken into account when learning control of the technical system. The statistical uncertainty of a quality function, which models an optimal operation of the technical system, is determined by uncertainty propagation and is incorporated during learning of an action-selecting rule. The uncertainty propagation uses a covariance matrix in which non-diagonal elements are ignored. The method can be used for learning control or feedback control of any desired technical systems. In a variant, the method is used for control or feedback control of an operation of a gas turbine. In another variant, the method is used for control or feedback control of a wind power plant.
摘要:
A method for the computer-assisted control and/or regulation of a technical system is provided. The method includes two steps, namely learning the dynamics of a technical system using historical data based on a recurrent neuronal network, and the subsequent learning of an optimum regulation by coupling the recurrent neuronal network to another neuronal network. The method can be used with any technical system in order to control the system in an optimum computer-assisted manner. For example, the method can be used in the control of a gas turbine.
摘要:
A method for the computer-aided learning of a control of a technical system is provided. An operation of the technical system is characterized by states which the technical system can assume during operation. Actions are executed during the operation and convert a relevant state into a subsequent state. The method is characterized in that, when learning the control, suitable consideration is given to the statistical uncertainty of the training data. This is achieved in that the statistical uncertainty of a quality function which models an optimal operation of the technical system is specified by an uncertainty propagation and is incorporated into an action selection rule when learning. By a correspondingly selectable certainty parameter, the learning method can be adapted to different application scenarios which vary in statistical requirements. The method can be used for learning the control of an operation of a turbine, in particular a gas turbine.