Abstract: Various embodiments of the teachings herein include a computer implemented sample preparation method for generating a new sample of data for augmenting simulation data to generate realistic data to be applied for training of a data evaluation model. The method may include generating the new sample based on an output data set sampled from a model of an input data set based on residual data. The residual data are based on real data of a real process and simulated data of a simulated process corresponding to the real process.

Abstract: Various embodiments of the teachings herein include a method for arranging a shared cryptographic key with a communication partner. The method may include: selecting a first point of a first elliptic curve; sending the first point to the communication partner using a public channel; receiving a second point of the first elliptic curve from the communication partner; and determining the shared key using a non-trivial, inverse shared mapping of the second point with respect to a shared isomorphic mapping of a second elliptic curve onto the first elliptic curve.

Abstract: A method for monitoring a semiconductor element in a semiconductor module, wherein the semiconductor module has feed lines contacting the semiconductor element, includes arranging a magneto-optical sensor in a region of the semiconductor element or of at least one of the feed lines, reflecting a polarized light signal from the magneto-optical sensor or transmitting a polarized light signal through the magneto-optical sensor, and determining a current from a polarization of the reflected or transmitted light signal.

Abstract: Various embodiments of the teachings herein include a method for analyzing an electrode paste and/or an electrode layer for a battery cell. The method may include: measuring a property of the electrode layer paste and/or the electrode layer using a measuring facility; generating measurement data; and determining a quality value of the electrode layer paste and/or the electrode layer using an AI engine based on the measurement data.

Abstract: Various embodiments of the teachings herein include a method for deploying power quality monitoring (PQM) devices. The method may include: determining a maximum number of PQM devices and historical power data of candidate deployment points, wherein the number of the candidate deployment points is greater than the maximum number of the PQM devices; clustering the historical power data of the candidate deployment points, wherein a target number of categories is determined on the basis of a silhouette coefficient of each candidate number of categories and the maximum number of the PQM devices; and determining PQM device deployment points based on the center of each category in the target number of categories.

Abstract: A method for operating a control arrangement for an energy network. The control arrangement has a cloud infrastructure with data processor resources and data storage resources. A first group of software modules is executed on the cloud infrastructure, and a second group of software modules is locally executed on a server computer arrangement. The first group and the second group are connected for data communication via interfaces. The interfaces utilize a public key infrastructure (PKI) for encryption.

Abstract: An integrating model for a technical system composed of at least one of a machine, a component of a machine, and a technical process includes a machine-machine interface, and a plurality of individual models having each assigned a raw model and a data pre-processing, wherein different individual models model different parts of the technical system and have different raw models and a different data pre-processing, and wherein at least one of the individual models is interchangeable for a part of the technical system.

Abstract: A system includes an Industrial facility having a first memory storing first machine-executable components and a first processor coupled to the first memory and designed to execute the first machine-executable components. The first machine-executable components include a cloud connectivity component, a second memory residing at a cloud platform and coupled to a second processor storing second machine-executable components and is designed to execute the second machine-executable components which include a management component. The management component belongs to an entity that produces Industrial devices residing at the industrial facility. During an Interaction with the cloud connectivity component, the management component defines an allowed installation context and authorizes installation of a computer program on the Industrial devices only within the scope of the allowed installation context, wherein the interaction excludes sending the computer program to the management component.

Abstract: A method for resource management includes: providing a representation of a set of resources; obtaining a set of use requests, wherein a use request can be fulfilled by allocating a resource to the use request; wherein the resources are categorized into resource classes, so that resources in a resource class are interchangeable with respect to fulfilling a use request; wherein a use request can be fulfilled for a specific use period requested by the use request, by allocating a resource to a resource class requested by the use request; wherein a target distribution of resources for use requests is determined on the basis of an optimization parameterization; wherein the optimization parameterization is based on weightings of allocations of resources to use requests; wherein, further, to determine the target distribution, a starting solution is created that represents a distribution of resources for use requests, is provided.

Abstract: System for performance-based design space composition in engineering systems includes design configuration module, explainable recommendation module and user interface module. A list of one or more system configurations is generated, each system configuration having a unique set of components that satisfy system goals and system requirements. For each system configuration, system performance values are determined based on performance enabled by each system component. A design dashboard presents the system configurations in rank order and the system performance value for each of the system configuration components.

Abstract: In order to control at least partially automated vehicles in a road danger zone, in particular road junctions in road traffic, in such a way that the vehicles can pass through the road danger zone in flowing traffic without stop/start interruptions, such as those caused e.g. by signalling equipment, traffic lights, the following proposes the following steps: a) each vehicle of the vehicles, on approaching the road danger zone, surrender the power to control the dynamic driving tasks of the vehicle in order to pass through said zone, b) when the vehicles have surrendered vehicle control power, a central control entity generates a digital road danger zone twin, and, as a result of the vehicles having surrendered vehicle control power, vehicle movements of the vehicle are automatically and dynamically controlled in a vehicle-coordinated and collision-free manner in order to pass through the road danger zone.

Abstract: Provided is a method for performing entity linking between a surface entity mention in a surface text and entities of a knowledge graph, including supplying the surface text to a contextual text representation model, pooling contextual representations of the tokens of a surface entity mention in the surface text with contextual representations of the other tokens within the surface text to provide a contextual entity representation vector representing the surface entity mention; supplying an identifier of a candidate knowledge graph entity to a knowledge graph embedding model, to provide an entity node embedding vector and combining the contextual entity representation vector with the entity node embedding vector to generate an input vector applied to a fully connected layer which provides an unnormalized output transformed by a softmax function into a normalized output processed to classify whether the surface entity mention corresponds to the candidate knowledge graph entity.

Abstract: Provided are methods and apparatuses for hardening a communication device, which methods and apparatuses make it possible to identify a use of at least one port, by which port a request is submitted to the communication device by a message, and to output a signal for blocking the at least one port if, after a specifiable time period, either the use of the port in question is detected as low or no use of the port in question is detected. Embodiments can be used to harden communication devices in a production line, in a hospital and/or in a power supply network.

Abstract: Provided is a method for computer-implemented determination of a data-driven prediction model. The method processes digital input data having input and output variables and being semantically annotated based on a digital semantic representation having a hierarchical tree structure where each tree in the structure represents an input variable of the data, the leaf nodes of the respective tree being the discrete values of the input variable. The method of the embodiment provides a recoding of those discrete values by cutting off hierarchical levels of the respective trees. Based on this recoding, a plurality of data modifications is determined for the input data. Those data modifications are trained by a machine learning method where the trained machine learning method with the highest prediction quality is derived from the trained machine learning methods.

Abstract: Disclosed is a method for monitoring the operation of a drive component. In order to minimize additional hardware complexity, the monitoring method is cared out by a coil that is integrated in a mobile terminal by acquiring an electromagnetic variable of the drive component outside a housing of the drive component by the integrated coil, determining at least one first frequency based on the acquired electromagnetic variable, and determining a first status variable of the drive component from the at least one first frequency.

Abstract: Assistance apparatus for automatically identifying failure types of a technical system is provided including at least one processor configured to determine for each sensor data a set of specific temporal courses of first time series of the sensor data of the sensor and assign a symbolic representation to each of the different specific temporal courses, provide at least one failure pattern, obtain more than one monitored time series of sensor data of the technical system, each of them divided into a sequence of time segments, and automatically assign to each time segment a symbolic representations according to the temporal course of the sensor data in the time segment, calculate a similarity measure for the set of symbolic representations of a selected time interval, determine a ranking of the failure pattern depending on decreasing values of the calculated similarity measure, and output the ranking.