Abstract: A method for detecting manipulation of a technical device, particularly a technical device in a motor vehicle, especially an exhaust-gas treatment device. The method includes: providing a time series of an input vector having one or more system variables and having at least one manipulated variable for an intervention in the technical device; utilizing a data-based manipulation detection model which includes a recurrent neural network that is designed to determine a state vector as a function of the input vector, and an autoencoder which is designed to determine a reconstructed vector as a function of the state vector, detecting an anomaly as a function of a reconstruction error, which is a function of the reconstructed vector; and detecting a manipulation as a function of the reconstruction error.

Abstract: A method for training a first neural network is disclosed. The neural network is configured to ascertain, based on sensor signals of a technical system, an output signal characterizing a classification and/or a regression result regarding the sensor signal. The method includes (i) during operation of the technical system, receiving a sensor signal of the technical system, (ii) ascertaining a first output signal by way of the first neural network and based on the sensor signal, (iii) ascertaining a second output signal by way of a second neural network and based on the sensor signal, wherein the second neural network has a different architecture than the first neural network, and (iv) training the first neural network by adjusting parameters of the first neural network, wherein the first neural network is trained as a function of the second output signal.

Abstract: A filter element for fluid has a filter medium body with a flow-through medium arranged transversely to a fluid flow direction. A region of the flow-through medium between an inlet surface and an outlet surface of the filter medium body is filled with adsorption medium in intermediate spaces of the flow-through medium. A fluid-permeable cover medium covers the region at a peripheral rim of the inlet surface and/or the outlet surface. A filter system has a filter housing having an inlet and an outlet for fluid. The filter element is exchangeably arranged in the filter housing between a raw-side and a clean-side. A method for producing the filter element includes filling adsorption medium into intermediate spaces of the flow-through medium between an inlet surface and an outlet surface. The region is covered with a fluid-permeable cover medium at a peripheral rim of the inlet surface and/or the outlet surface.

Abstract: A filter element for filtering a fluid has two or more axially extending filter medium bodies arranged to be sequentially flowed through radially and including a first and a second filter medium body. The first filter medium body has an outer diameter smaller than an inner diameter of the second filter medium body, is arranged radially inside the second filter medium body, and has a section projecting axially away from the second filter medium body. A casing is arranged at an outer wall surface of the projecting section and extends at least partially circumferentially around the outer wall surface. The casing fluid-impermeably closes at least temporarily the outer wall surface. The first filter medium body is a particle filter and the second filter medium body is an adsorption filter, or vice versa. A filter system is provided with such a filter element for filtering a fluid.

Abstract: A gas filter system has an outer filter element with a first end plate, a second end plate, and a first filter medium arranged between the first and the second end plates. An inner filter element with a third end plate, a fourth end plate, and a second filter medium arranged between the third and the fourth end plates is provided. The first end plate and the third end plate each have an opening. The first end plate surrounds the third end plate. The first end plate has a first seal protrusion protruding in an axial direction of the gas filter system. The third end plate has a second seal protrusion protruding in the axial direction of the gas filter system. For sealing the third end plate and the first end plate relative to each other, the first seal protrusion and the second seal protrusion engage each other.

Abstract: A gas filter system including a housing, a first filter element having a first filter medium and a second filter element having a second filter medium, the first and second filter elements being arranged inside the housing and the first filter medium and the second filter medium surrounding a common longitudinal axis, wherein a flexible sealing lip protrudes in the axial direction from the first filter medium, wherein the housing has a first sealing surface for sealing abutment against the sealing lip, wherein a rigid sealing rib protrudes from the second filter element, the sealing rib having a second sealing surface for sealing abutment against the sealing lip, wherein the sealing lip is compressed between the first sealing surface and the second sealing surface, and wherein the second sealing surface faces radially outwardly.

Abstract: A gas filter system comprising an outer filter element having a first filter medium arranged between a first end cap and a second end cap, and an inner filter element having a second filter medium arranged between a third end cap and a fourth end cap, the first filter medium being arrangeable to surround the inner filter medium, wherein the first, second, third and fourth end caps are open.

Abstract: A gas filter system including an outer filter element having a first filter medium arranged between a first end cap and a second end cap, and an inner filter element having a second filter medium arranged between a third end cap and a fourth end cap, wherein the first filter medium is arrangeable to surround the second filter medium, wherein the first, third and fourth end caps are open, wherein the outer filter element is closed at the second end cap, wherein the outer filter element has an axial protrusion at the second end cap that protrudes into the inner filter element and exhibits a radially outward facing sealing surface, and wherein the fourth end cap of the inner filter element has a second sealing section for sealing abutment against the sealing surface of the protrusion.

Abstract: A gas filter system including a housing with a sealing projection and a housing groove; an outer filter element having a first filter medium with a first end cap and a second end cap; and an inner filter element having a second filter medium with a third end cap and a fourth end cap, wherein the first end cap has a first axial end cap projection and the third end cap has a second axial end cap projection, the end cap projections being arranged in the housing groove; the first and second end cap projections forming a common groove into which the sealing projection protrudes for sealing abutment against the first end cap and the third end cap at the common groove. The use of an outer filter element and/or an inner filter element in the gas filter system.

Abstract: A gas filter system including an outer filter element having a first filter medium arranged between a first end cap and a second end cap, and an inner filter element having a second filter medium arranged between a third end cap and a fourth end cap, wherein the first, second and third end caps are open, the inner filter element is closed at the fourth end cap, the first filter medium is arrangeable to surround the second filter medium, such that the first end cap of the outer filter element surrounds the third end cap of the inner filter element, the first and third end caps are sealed against each other, and such that the second end cap of the outer filter element surrounds the fourth end cap of the inner filter element, and the second and fourth end caps are sealed against each other.

Abstract: A gas filter system including an outer filter element having a first filter medium arranged between a first end cap and a second end cap, and an inner filter element having a second filter medium arranged between a third end cap and a fourth end cap, wherein the first, third and fourth end caps are open, wherein the outer filter element is closed at the second end cap, wherein the first filter medium is arrangeable to surround the second filter medium, such that the outer filter element is sealed against the inner filter element between the second end cap and the fourth end cap.

Abstract: A battery degassing unit for a battery housing has a base body that has a gas passage opening and is to be connected fluid-tightly to a pressure compensation opening of the battery housing. A first filter covers the gas passage opening at an inner side of the base body. The first filter is a separation grid with first grid openings. A second filter is a separation grid arranged between first filter and inner side of the base body and has second grid openings. The base body has fastening regions for fastening the battery degassing unit to the battery housing. One of the first and second filters completely engages across the gas passage opening. One of the first and second filters is a corrugated filter so that a length extension in a stretched state in at least one direction is at least 1.3 times as large as in a corrugated state.

Abstract: A method for training a first neural network is disclosed. The neural network is configured to ascertain, based on sensor signals of a technical system, an output signal characterizing a classification and/or a regression result regarding the sensor signal. The method includes (i) during operation of the technical system, receiving a sensor signal of the technical system, (ii) ascertaining a first output signal by way of the first neural network and based on the sensor signal, (iii) ascertaining a second output signal by way of a second neural network and based on the sensor signal, wherein the second neural network has a different architecture than the first neural network, and (iv) training the first neural network by adjusting parameters of the first neural network, wherein the first neural network is trained as a function of the second output signal.

Abstract: A degassing unit to be connected fluid-tightly to a pressure compensation opening of an electronics housing has a base body with gas passage opening. A semipermeable membrane, fastened fluid-tightly to a membrane carrier, allows gaseous media to pass from an environment into the electronics housing and in reverse but prevents passage of liquid media and solids. In normal operation, the membrane covers the gas passage opening. An axial seal circumferentially extends about the gas passage opening. The membrane carrier is moveable relative to the base body and, in normal operation, is pressed by axial force seal-tightly against the axial seal. The membrane carrier, when a predetermined pressure difference between housing interior and environment is surpassed, lifts off the base body to release an emergency degassing opening surrounding the membrane. The axial seal is a lip seal and made of a material softer than a material of the membrane carrier.

Abstract: A device and a computer-implemented method for classifying data, in particular for a Controller Area Network or an automotive Ethernet network. A plurality of messages is received from a communications network. A message that has a predefined message type is selected for an input variable for an input model of a plurality of input models of an artificial neural network associated with the predefined message type. The input variable is determined as a function of the message, and in an output area of the artificial neural network a prediction is output that is usable for classifying the message as a function of the input variable, or a reconstruction of an input variable is output that is usable for classifying the message as a function of this input variable.

Abstract: A method for aggregating a dataset, which respectively assigns an output variable value to a plurality of input variable vectors, into a function term. In the method, one or more elementary function expression(s) from an alphabet is/are sampled using a neural transform network. The elementary function expressions are assembled to form one or more candidate function term(s). When the candidate function term(s) is/are complete, the input variables are mapped to associated candidate output variable values using each candidate function term. A deviation between candidate output variable values and corresponding output variable values of the dataset is evaluated using a predefined metric. It is checked whether a predefined abort condition is satisfied. If the abort condition has not been satisfied, parameters which characterize the behavior of the transformer network are updated and branching back for sampling elementary function expressions using the transformer network takes place.

Abstract: A method for manipulation detection of a technical device, i.e., an exhaust gas after treatment device in a motor vehicle, including: providing an input vector including system variable(s) and including at least one control variable for an intervention in the technical device for successive time steps; using a data-based manipulation detection model to generate a corresponding output vector as a classification vector in each time step for each input vector, each output vector indicates a classification of a monitored variable in value ranges, for the input vector; providing an actual monitored variable based on at least one measured value in the successive time steps; creating a measurement classification vector from the actual monitored variable for each time step; detecting a manipulation as a function of the measurement classification vector and a first and a second comparison vector for time step(s) of the time window.

Abstract: A computer-implemented method for detecting a manipulation of a technical device. The method includes: providing time characteristics of operating variables having system variable(s) and/or a correction variable for an intervention in the technical device which correspond to time series of values of the operating variables for each of consecutive time steps; using a data-based manipulation detection model in each current time step to ascertain one or more output variable(s) that correspond at least to a portion of the operating variables as a function of input variables which include at least a portion of the operating variables. The manipulation detection model includes an autoencoder having a first recurrent neural network, a prediction model having a second recurrent neural network, and an evaluation model, the outputs of the autoencoder and the prediction model being combined with one another and then conveyed to an evaluation model for an ascertainment of the output variables.

Abstract: A battery degassing unit for a battery housing has a base body that has a gas passage opening and is to be connected fluid-tightly to a pressure compensation opening of the battery housing. A first filter covers the gas passage opening at an inner side of the base body. The first filter is a separation grid with first grid openings. A second filter is a separation grid arranged between first filter and inner side of the base body and has second grid openings. The base body has fastening regions for fastening the battery degassing unit to the battery housing. One of the first and second filters completely engages across the gas passage opening. One of the first and second filters is a corrugated filter so that a length extension in a stretched state in at least one direction is at least 1.3 times as large as in a corrugated state.

Abstract: A method for detecting manipulation of a technical device, particularly a technical device in a motor vehicle, especially an exhaust-gas treatment device. The method includes: providing a time series of an input vector having one or more system variables and having at least one manipulated variable for an intervention in the technical device; utilizing a data-based manipulation detection model which includes a recurrent neural network that is designed to determine a state vector as a function of the input vector, and an autoencoder which is designed to determine a reconstructed vector as a function of the state vector, detecting an anomaly as a function of a reconstruction error, which is a function of the reconstructed vector; and detecting a manipulation as a function of the reconstruction error.