Abstract: A method of hierarchical machine learning includes receiving a topology model having information on hierarchical relations between components of the industrial plant, determining a representation hierarchy comprising a plurality of levels, wherein each representation on a higher level represents a group of representations on a lower level, wherein the representations comprise a machine learning model, and training an output machine learning model using the determined hierarchical representations.

Abstract: A computer-implemented method for automating the development of industrial machine learning applications includes one or more sub-methods that, depending on the industrial machine learning problem, may be executed iteratively. These sub-methods include at least one of a method to automate the data cleaning in training and later application of machine learning models, a method to label time series (in particular signal data) with help of other timestamp records, feature engineering with the help of process mining, and automated hyper-parameter tuning for data segmentation and classification.

Abstract: An industrial plant machine learning system includes a machine learning model, providing machine learning data, an industrial plant providing plant data and an abstraction layer, connecting the machine learning model and the industrial plant, wherein the abstraction layer is configured to provide standardized communication between the machine learning model and the industrial plant, using a machine learning markup language.

Abstract: A method includes training a first control model by utilizing a first set of input data as first input, resulting in a trained first control model; copying the trained first control model to a second control model, wherein, after copying, the second input layer and the plurality of second hidden layers is identical to the plurality of first hidden layers, and the first output layer is replaced by the second output layer; freezing the plurality of second hidden layers; training the second control model by utilizing the first set of input data as second input, resulting in a trained second control model; and running the trained second control model by utilizing a second set of input data as second input, wherein the second output outputs the quality measure of the first control model.

Abstract: A method and an apparatus for generating sensor data for controlling an autonomous vehicle in an environment is provided, such as driverless transport vehicles in a factory for example. Sensor positions of static sensors and the sensors of autonomous vehicles are defined in a global coordinate system on the basis of an environment model, such as a BIM model for example. Sensor data is centrally generated in this global coordinate system for all sensors as a function of these sensor positions. The sensor data is then transformed into a local coordinate system of an autonomous vehicle and transferred for controlling the autonomous vehicle.

Abstract: For the exact lateral continuous positioning of material plies on a forming tool, a positioning device is provided to position a material ply on a forming tool during a production of a fiber composite component, comprising a positioning unit for positioning the positioning device in relation to a surface of the forming tool, a movement unit for moving the positioning device along a predetermined movement route along the forming tool, a route position detection unit for detecting the current route position of the positioning device on the movement route, and a material ply positioning unit for positioning the material ply in a direction transverse to the movement direction in dependence on the current route position detected by the route position detection unit.

Abstract: The present invention provides a process for the recovery and/or purification of a recombinantly expressed intracellular protein comprising the sequence of Annexin A5 (AnxA5) from an endotoxin-producing host cell with a cell wall, wherein the process comprises releasing the intracellular protein from the host cell, characterised in that the step of releasing the intracellular AnxA5 protein is conducted in the presence of a homogenisation buffer comprising non-ionic detergent, and preferably wherein the process does not include any centrifugation steps for the recovery and/or purification of the AnxA5 protein after its release from the host cell and/or in which the AnxA5 protein remains in solution throughout the process except when temporarily bound to any chromatographic resins.

Abstract: The invention relates to a method for setting a driving speed of a motor vehicle on a route. A control device of the motor vehicle sets the driving speed depending on an operating position limited by two extreme positions of a pedal device of the motor vehicle, which may be operated by a driver, wherein the control device detects the operating position of the pedal device, and depending on the detected operating position, determines in at least one specified driving mode a target driving speed corresponding to the respective operating position, and the control device sets the driving speed corresponding to the respective target driving speed by means of a closed loop control as long as the respective operating position is detected. The setting in this case takes place independently of a current condition of the route. The invention also includes a motor vehicle.

Abstract: A method for oxidizing an alkyl, including a) contacting the alkyl with an aqueous solution comprising a microorganism where the microorganism has a reduced fatty acid degradation capacity compared to its wild type, wherein the fatty acid degradation capacity is reduced by deletion, inhibition or inactivation of a gene encoding an enzyme involved in the ?-oxidation pathway; and the microorganism expresses a recombinant alkane oxidase, and b) contacting the aqueous solution from a) with a water-immiscible organic solvent.

Abstract: In order to provide a method for initiating a defrosting process of a heat exchanger of a heat pump of a motor vehicle, which method is insensitive to external influences and can also be used in combination with other methods, wherein the heat exchanger and a coolant heat exchanger of a cooling circuit of the motor vehicle are arranged in a common air path, a coolant outlet temperature of a coolant from the coolant heat exchanger is determined, and a state of icing of the heat exchanger is determined using the coolant outlet temperature, and initiating a defrosting process of the heat exchanger if icing of the heat exchanger is determined.

Abstract: In order to provide a method for initiating a defrosting process of a heat exchanger of a heat pump of a motor vehicle, which method is insensitive to external parameters influencing the air flow through the evaporator, and with which method unnecessary defrosting processes can be avoided, wherein a fan is assigned to the heat exchanger, wherein a power consumption and/or a speed of the fan is monitored, a defrosting process is initiated when the power consumption and/or the speed exceeds and/or falls below a threshold value, and the threshold value is determined as a function of a parameter, wherein the parameter is an indicator of a current relative air speed of the ambient air in relation to the motor vehicle.

Abstract: A method for detecting a leakage of fluid in a supply grid is disclosed. The method includes measuring a flow of the fluid at first locations by first sensors; predicting a flow at a second location by a self-learning system based on the measured flows, wherein the self-learning system has been trained to predict the flow at a specified location in a supply grid; measuring an actual flow of the fluid at the second location by a second sensor located at the second location; ascertaining a difference between the actual flow measured at the second location and the flow at the second location predicted by the trained system; and outputting a notification of an assumed leakage when the ascertained difference is greater than a specified threshold. Devices and assemblies for detecting a leakage of fluid in a supply grid are also disclosed.

Abstract: The invention relates to a method for defrosting an external-air heat exchanger of an electric vehicle. Contrary to the conventional principle of operating systems in an electric vehicle at the lowest possible output power, according to the invention, high output power is used for the defrosting process, to reduce the defrosting time and thus reduce heat loss.

Abstract: A computer-implemented method for generating a computer-readable model for a technical system on the basis of text-based specification data for the technical system, the text-based specification data specifying at least one system condition is provided. A plurality of model components for the computer-aided modelling of the technical system are provided, each model component being assigned a model component identifier. By means of generative adversarial networks, model components are selected, using their model component identifiers, from the plurality of model components on the basis of the text-based specification data, and a computer-readable model for the technical system is generated from the selected model components in such a way that model data of the computer-readable model satisfy at least one system condition specified in the text-based specification data.

Abstract: The present invention discloses an ionization apparatus 10 for ionizing an analyte S, comprising an inlet E, an outlet A, a first electrode 1, a second electrode 2 and a dielectric element 3. The first electrode 1, the second electrode 2 and the dielectric element 3 are arranged relative to one another such that, by applying an electric voltage between the first electrode 1 and the second electrode 2, a dielectric barrier discharge is establishable in a discharge area 5 in the ionization apparatus 10. The first and second electrodes 1, 2 are arranged such that they are displaceable or movable relative to each other.

Abstract: A base body of a computed tomography drum is disclosed. In an embodiment, the base body includes at least the following components: a base plate, an outer ring and an inner ring. The inner ring is arranged concentrically with the outer ring. The outer ring and the inner ring are arranged on the base plate. At least two of the components are configured as separately producible components. Two of the separately producible components are connected to one another by way of at least one of: bonding, welding, riveting, clinching, clinch-bonding and/or rivet-bonding.

Abstract: Methods, devices, and assemblies for controlling pressure in a supply grid are provided. The supply grid is suitable for supplying fluid to loads. The supply grid has first sensors for measuring the flow and/or the pressure of the fluid at first locations in the supply grid and a pump for pumping the fluid or a valve for controlling the flow of the fluid. The method includes: measuring the flow and/or pressure of the fluid at the first locations in the supply grid by the first sensors; predicting the pressure at the second location in the supply grid using a self-learning system based on the measured flows or pressures, wherein the self-learning system is trained to predict the pressure at a specified location in the supply grid; and actuating the pump or the valve at least also based on the pressure predicted by the trained system at the second location.

Abstract: The invention relates to a method for operating a climate-control system (12) for a vehicle (10). According to the invention, total energy efficiencies are determined for a group of operating strategies for the air-conditioning system (12) and an operating strategy with the greatest total efficiency that fulfills the heating output requirement (44) that has been determined, is selected.

Abstract: A method for the production of stiffened components made of fiber-reinforced composite material using two rigid form tools which are suitable for covering the longer end sides of T-shaped preformed reinforcing fibers, using a folded hose core and inflation of the hose core so as to exert pressure on the end side of the preformed reinforcing fibers.

Abstract: An asset condition monitoring method with automatic anomaly detection may include receiving local condition data from an asset fleet, identifying at least one anomaly in the received condition data, identifying a new potential failure case dependent on the identified anomaly, determining a specific condition model dependent on the identified new potential failure case, where the specific condition model is configured for predicting the new potential failure case, and providing the specific condition model to the plurality of assets and/or to digital models of the plurality of assets.