Abstract: A method for the computer-assisted exploration of states of a technical system is provided. The states of the technical system are run by carrying out an action in a respective state of the technical system, the action leading to a new state. A safety function and a feedback rule are used to ensure that a large volume of data of states and actions is run during exploration and that at the same time no inadmissible actions occur which could lead directly or indirectly to the technical system being damaged or to a defective operating state. The method allows a large number of states and actions relating to the technical system to be collected and may be used for any technical system, especially the exploration of states in a gas turbine. The method may be used both in the real operation and during simulation of the operation of a technical system.

Abstract: A method for the computer-aided regulation and/or control of a technical system is provided. In the method, first a simulation model of the technical system is created, to which subsequently a plurality of learning and/or optimization methods are applied. Based on the results of these methods, the method best suited for the technical system is selected. The selected learning and/or optimization method is then used to regulate the technical system. Based on the simulation model, the method can thus be used to train an initial controller, which can be used as an intelligent controller, and is not modified during further regulation of the technical system.

Abstract: A method for computer-aided control of any technical system is provided. The method includes two steps, the learning of the dynamic with historical data based on a recurrent neural network and a subsequent learning of an optimal regulation by coupling the recurrent neural network to a further neural network. The recurrent neural network has a hidden layer comprising a first and a second hidden state at a respective time point. The first hidden state is coupled to the second hidden state using a matrix to be learned. This allows a bottleneck structure to be created, in that the dimension of the first hidden state is smaller than the dimension of the second hidden state or vice versa. The autonomous dynamic is taken into account during the learning of the network, thereby improving the approximation capacity of the network. The technical system includes a gas turbine.

Abstract: The invention relates to sensitivity analysis of variables influencing a combustion process. A trainable, statistical model is trained in such a way that it describes the combustion process in the combustion chamber. The trained statistical model is used to determine the influence of the variables on said combustion process in the combustion chamber.

Abstract: A method and an apparatus for ventilating at least one window in a vehicle by blowing and extracting air in a region of the window is described. The airflow blown against the window is substantially laminar and the air is extracted in an upper region of the window. A dew point is lower than the window temperature in a region of extraction being the upper region of the window, and an absolute humidity of the blown air is lower than that of the extracted air.

Abstract: Activity parameters which describe the activity of the respective device are determined of at least some of the devices and/or services. The communication parameters determined are compared with a normal range of dependence determined from dependences determined between the devices by a trained statistical estimator, and it is determined whether the communication performance of the devices meets a predetermined criterion.

Abstract: A process and an arrangement for conditioning input variables of a neural network are described by the invention. From the input variables of the network, time series are formed and these are subdivided into intervals whose length depends on how far the interval and the measured variables contained therein lie back in the past. In this case, the interval length is selected to be larger the further the interval lies back in the past. By means of convolution using a bell-shaped function, a representative input value for the neural network is obtained from all these measured variables contained in the interval. All the input variables which are obtained in this way are fed to the network simultaneously during training and during operation. A memory is thus realized in a simple way for a forwardly directed neural network. Potential applications include, in particular, chemical processes having very different time constants.