Abstract: An arrangement for pressure monitoring within a battery housing of a battery system. The arrangement includes a first power supply path and a pressure measuring. The pressure measuring unit is electrically connected to the first power supply path. The arrangement also includes a pressure-sensitive mechanical switching unit arranged within the battery housing and electrically connected, in series with the pressure measuring unit, to the first power supply path. The switching unit switches to an electrically conductive switching state when the pressure within the battery housing exceeds a predefined pressure threshold and establishes a supply of power to the pressure measuring unit via the first power supply path, and switches to an electrically blocking switching state when the pressure within the battery housing falls below the pressure threshold and interrupts the supply of power to the pressure measuring unit via the first power supply path.

Abstract: A controller for a technical system 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 including both state data as well as control action data of the technical system. A change in the control action data over time is detected specifically and correlated with changes in the state data over time within different time windows, wherein a time window-specific correlation value is ascertained in each case. A resulting time window is then ascertained on the basis of the ascertained correlation values, and the training data which is found within the resulting time window is extracted in a time window-specific manner. The controller is trained by means of the machine learning method using the extracted training data and thereby configured to control the technical system.

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: Real state information, which influences the switching times of a light signal system, is supplied as input signals to a first neural network in a fixed time cycle. The first neural network calculates estimated state information as a replacement for real state information or parts of the real state information which are not received in good time or are received incorrectly in the fixed time cycle. This estimated state information is output to artificial intelligence which predicts the switching times. The first neural network allows the artificial intelligence to also make good predictions for the switching times of signal groups when one of the many communication paths involved fails or is overloaded. It is therefore possible to predict signal group states in the fixed time cycle in real time with a high degree of robustness and tolerance with respect to gaps in the time cycle of the real state information provided.

Abstract: Various embodiments include a method for producing a quality test system executing a quality test model with a filter mask and a quality model to determine a quality feature of a battery cell. The system has an electrochemical impedance spectroscopic unit for capturing test data relating to the battery within a frequency range. The method includes: creating the model; and producing the system. Creating the model includes: capturing spectroscopic learning data; creating the filter mask using a first machine learning method with analysis data from part of the frequency range by consulting the filter mask and creating the model using a second machine learning method. The first and the second learning method are coupled based on the learning data. The first machine learning method creates a filter mask determining the analysis data such that the second machine learning method creates a quality model optimized with respect to maximizing the quality.

Abstract: A detection unit for a gas sensor, having at least one gas-sensitive element (1) including at least one gas-sensitive material, the optical properties of which vary as a function of the contact with a target gas. The detection unit is configured for arrangement on a mobile evaluation unit (5) having an image acquisition unit (6), in order to form a gas sensor, and the detection unit has at least one optical lens (2), and the gas-sensitive element (1) and the optical lens (2) are arranged in such a way that the ambient light (U) that passes through the gas-sensitive element (1) can be imaged by the optical lens (2), in particular can be imaged onto the image acquisition unit (6) when the detection unit is arranged on the mobile evaluation unit (5).

Abstract: Various embodiments of the teachings herein include a method for producing an electrode layer of a battery store by a system using an electrode layer paste. An example method includes: acquiring system parameters associated with the production of the electrode layer; acquiring a measured value of a variable of the electrode layer; calculating a correction value from a comparison of the acquired measured value of the electrode layer with a defined target value range; and setting the system parameters as a function of the calculated correction value.

Abstract: A pneumatic vehicle tire in radial design that is a summer tire or all-season tire, with a profiled tread including rows of profile blocks and/or profile ribs running around the tire in circumferential direction, wherein the total number of sipes within each row of profile blocks and/or profile ribs is not more than 150, wherein the tread is in the form of a single layer or multiple layers with a radially outermost tread layer that extends at least over the width of the ground contact area, wherein the profile depth of the tread is up to 6.5 mm, and the tread or its radially outermost tread layer consists of a rubber material with a Shore A hardness at room temperature in accordance with DIN ISO 7619-1 of 40 ShA to 55 ShA.

Abstract: A sulfur-crosslinkable rubber mixture, especially for the tread of pneumatic vehicle tires, including at least the following constituents: 10 to 90 phr (parts by weight, based on 100 parts by weight of all rubbers in the mixture) of at least one solid, solution-polymerized, functionalized butadiene rubber, where the functionalization enables interaction with a polar filler, —at least one further diene rubber, —at least one liquid, modified diene polymer A having a weight-average molecular weight Mw by GPC of 500 to 50 000 g/mol, preferably 2000 to 10 000 g/mol, wherein the modification enables interaction with a polar filler and is present along the polymer backbone, and —10 to 300 phr of at least one silica.

Abstract: The present invention relates to the control of an electrical power converter. The power converter is controlled with a predefined modulation frequency. This modulation frequency can be variably adjusted. In particular, the modulation frequency can be varied around a basic frequency in a predefined frequency range. The frequency range, in which the modulation frequency is varied, and also the pattern, with which this variation occurs, can be adjusted.

Abstract: Method and device for controlling a machine in accordance with to multiple control objectives in which machine control is based on automated learning of subordinate control skills, wherein the device provides multiple subordinate control skills which are each assigned to a different one of the multiple control objectives, the device provides multiple learning processes that are reinforcement learning processes that are each assigned to a different one of the multiple control objectives and are configured to optimize the corresponding subordinate control skill based on input data received from the machine, and where the device is configured to determine a superordinate control skill based on the subordinate control skills and to control the machine based on the superordinate control skill.

Abstract: A computer-implemented method for determining at least one remaining time value, to be determined, for a system is provided, having the following steps: a. providing at least one known input data record containing a multiplicity of input elements for at least one determined time; b. providing at least one associated known remaining time value for the at least one input data record; c. determining the at least one remaining time value to be determined by applying an error function to the at least one input data record and the at least one associated remaining time value; and d. providing an output data record containing the at least one determined remaining time value and an associated reliability value. The invention furthermore targets a corresponding determination unit and computer program product.

Abstract: A pneumatic vehicle tyre of radial type of construction, having a tread (1), having a carcass inlay (3), having electrically nonconductive sidewalls (7) and having at least one electrically conductive component (8) or element in a bead region, which component or element, in the case of a tyre mounted on a wheel rim, comes into contact with said wheel rim, wherein either the tread (1) is electrically conductive or, in the tread region, at least one electrically conductive component (10) is provided which is overlapped on the outside by the sidewalls (7) and which is connected in electrically conductive fashion to the tread outer surface, and wherein filaments provided with an electrically conductive coating are incorporated at least in a sidewall region, the coating of which filaments forms electrically conductive passages between the tread (1) or the component (10) and the at least one electrically conductive component (8) or element in the bead region.

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: A pneumatic vehicle tire in radial design that is a summer tire or all-season tire, with a profiled tread comprising rows of profile blocks and/or profile ribs running around the tire in circumferential direction, wherein the total number of sipes within each row of profile blocks and/or profile ribs is not more than 150, wherein the tread is in the form of a single layer or multiple layers with a radially outermost tread layer that extends at least over the width of the ground contact area, and wherein the profile depth of the tread is up to 6.5 mm. The tread or its radially outermost tread layer consists of a rubber material with a Shore A hardness at room temperature in accordance with DIN ISO 7619-1 of 40 ShA to 55 ShA.

Abstract: An operating signal is fed to a first machine learning module to reproduce a behavior signal of a technical system, the behavior signal occurring specifically without the current use of a control action and output the reproduced behavior signal as a first output signal. The first output signal is fed to a second machine learning module to reproduce a resulting behavior signal using a control action signal and output the reproduced behavior signal as a second output signal. Furthermore, an operating signal is fed to a third machine learning module, and a third output signal is fed to the trained second machine learning module. A control action performance ascertained using the second output signal, and the control action performance is used to train the third machine learning module to optimize the control action performance. By training the third machine learning module, a control device controls the technical system.

Abstract: A computer-implemented method, a device for data processing and a computer system for controlling a control device of a conveyor system to achieve an alignment and/or a defined spacing of piece goods, wherein the control of the control device is determined by an agent acting according to Reinforcement Learning methods. An individual, local state vector of predefined dimension that is the same for all the piece goods is created for each of the piece goods and an action vector is selected from an action space according to a strategy that is the same for all piece goods for the current state vector of this piece good. These action vectors are projected onto the conveying elements, wherein conflicts are resolved. After a cycle time has elapsed, state vectors are created again for each piece good and evaluated with rewards and the strategy is adjusted.

Abstract: A method for determining a concentration of a target gas in blood of a human or animal animate being. The method includes the steps of: generating electromagnetic excitation radiation having a carrier frequency, wherein the carrier frequency is selected such that the target gas and an absorbing gas absorb the excitation radiation, modulating an amplitude or the carrier frequency of the excitation radiation with a modulation frequency, illuminating an absorption path superficial to a skin of the animate being with the excitation radiation, generating a sound wave by an absorption of the excitation radiation in the absorption gas, and detecting at least one of an amplitude and a phase of the sound wave as a measure of a concentration of the target gas on the absorption path. Also provided is a photoacoustic sensor for determining a concentration of a target gas in blood of a human or animal animate being.

Abstract: A method including providing an acoustic resonator having an absorption element with a surface portion, providing a sample fluid or a fluid mixture containing the sample fluid with at least one absorption fluid or particles such that the acoustic resonator is filled with the same, the surface portion of the absorption element being in contact with the sample fluid. Irradiating the surface portion of the absorption element with a first electromagnetic radiation such that the absorption element at least partly absorbs the first electromagnetic radiation in the region of the surface portion, or irradiating the fluid mixture with a first electromagnetic radiation such that the absorption fluid or the absorption particles at least partly absorb(s) the first electromagnetic radiation, and so, by way of the absorption, pressure energy is generated in the sample fluid or the fluid mixture, with the first electromagnetic radiation being amplitude modulated or frequency modulated with a modulation frequency.

Abstract: A method for teaching an electronic computing device includes at least a machine learning algorithm for predicting a position-based propagation of radio waves in an environment, including the steps of: providing a mathematical model for the position-based propagation, wherein the mathematical model includes at least a physical model for the position-based propagation in the environment generating training data for the machine learning algorithm including a propagation field and/or a propagation domain; training the machine learning algorithm by fitting the training data to a partial derivative of the machine learning algorithm; and obtaining a prediction of a propagation loss by a weighted sum of multiple evaluations of the trained machine learning algorithm. Furthermore, provided is a computer program product, a computer-readable storage medium as well as an electronic computing device.