Abstract: A system includes a perception system and a processing function including a camera. A vision system processes data from the camera. The system takes the camera data and reconstructs occluded parts to reestablish a violated prior assumption needed for a downstream system. The system is to be trained to reconstruct incomplete information in a sequence of images. The training may be based on historic knowledge or on simulated data.

Abstract: A method for securely operating an industrial control device together with an AI module for processing at least one AI data set via a two-stage decryption method.

Abstract: A method for checking samples for defects is provided, in which image data of the samples are recorded and classified into predeterminable defect categories by a defect detection algorithm, and the samples classified into a defect category are represented in a multi-dimensional confusion matrix as a classification result of the defect detection algorithm, characterized in that miniature images which reproduce the image data are assigned according to the classified defect categories of the image data to segments of the confusion matrix which represent the defect categories, and these miniature images are displayed visually, the miniature image is assigned by an interaction with a user or a software robot to a different segment from the assigned segment of the confusion matrix, and is either provided as training image data for the defect detection algorithm or is output as training image data for the defect detection algorithm.

Abstract: A method and computer program product for analyzing data originating from at least one device, wherein the computer program product includes an ML-artifact forming the functionality of a ML-model and a monitoring-artifact, where the ML-model is trained and/or set up or can be trained and/or set up with a machine learning method using training-data, where the ML-artifact produces an ML-result as a response of inputting input-data, based on data originating from the device, into the ML-artifact, where the monitoring-artifact produces an ML-result-reliability-information regarding the ML-result as a response to inputting the input-data into the monitoring-artifact, where the training-data or part of the training-data is used to train the monitoring artifact, and where the computer program product outputs a qualified-ML-result based on the ML-result and the ML-result-reliability-information when being executed by a computer.

Abstract: An application module for a control device, wherein the application module is configured to communicate and interact with further components of the control device as part of the control of a machine or system, where the application module is configured to generate an additional functionality for the control device through the use of a user application, where an automation engineering system is provided for establishing the control device and an application engineering system is provided for creating the user application, and where the application module is configured such that testing of the user application occurs or can be performed via an interaction of the application module with the application engineering system.

Abstract: A method of communicating with a microservice in an industrial facility. The method is implemented by a controller and includes obtaining one or more data structure types, wherein the data structure types are generated based on an API definition associated with the microservice, generating one or more variables based on the obtained data structure types, wherein the variables are associated with one or more function blocks of the controller, and transmitting data associated with the variables to the microservice via a proxy component. The controller transmits the data associated with the variables in a serialized binary format associated with the variables to the proxy component. The proxy component is configured to translate to translate the data from the serialized binary data to a first serialization format and transmit the data in the first serialization format to the microservice.

Abstract: Various embodiments of the teachings herein include a method for accelerating deep learning inference of a neural network with layers. An example includes: generating a line-wise image consisting of pixels by a line-camera scanning an object; and for each generated new pixel-line, for calculations in the current layer which do not involve the new pixel-line, using results of previous calculations instead of repeating a calculation of a value of a pixel in the next layer.

Abstract: A method of communicating with a microservice in an industrial facility. The method is implemented by a controller and includes obtaining one or more data structure types, wherein the data structure types are generated based on an API definition associated with the microservice, generating one or more variables based on the obtained data structure types, wherein the variables are associated with one or more function blocks of the controller, and transmitting data associated with the variables to the microservice via a proxy component. The controller transmits the data associated with the variables in a serialized binary format associated with the variables to the proxy component. The proxy component is configured to translate to translate the data from the serialized binary data to a first serialization format and transmit the data in the first serialization format to the microservice.

Abstract: An extension device for one or more automation devices in an industrial system is provided. Industrial data processing units capable of performing data processing based on one or more artificial neural networks are provided. To enable and/or accelerate one or more computations in an industrial system, thereby simplifying integration of artificial intelligence into the industrial system, and to simplify data exchange between an extension device capable of processing data using artificial intelligence and an automation device, one or more results of the one or more computations are obtained. The results indicate one or more states of the industrial system. The one or more results are provided via a process state model shared with the automation device to monitor and/or control the industrial system.

Abstract: A computer-implemented method for efficient processing of pooled data shared by users of a cloud platform, the method includes the steps of uploading at least one dataset by a client device of a user to said cloud platform; calculating similarity scores indicating a degree of similarity between the current uploaded dataset and datasets previously uploaded by client devices of other users; and performing a procedure selected by a user on the cloud platform based on pooled data including the current dataset of the respective user and the datasets previously uploaded from client devices of other users stored in a database of the cloud platform having calculated similarity scores in relation to the current uploaded dataset of the respective user exceeding a configurable similarity score threshold, is provided.

Abstract: A control system for handling a processing product includes a control device with at least one application module for interconnecting first and second sensor components, and a control module, wherein the first and second sensor components capture first and second sensor data, the handling component handles, processes and/or manipulates the processing product, and the control module executes the control program, and further includes an edge computing device which determines an item of time information, where times for transporting a product transported on the transport device from the first to the second sensor component and on to the handling component are determined from the item of time information, and wherein the control module executes the control program to provide real-time control of the handling component for handling the processing product taking into account the first and second sensor data and the time information and/or the determined transport times.

Abstract: A method includes determining an artificial intelligence function in an engineering framework system. An inference path is defined for generation of an AI model by a computation graph. An AI function and the inference path are converted into a processing format. The converted AI function is sent and exported to an extraction and extension module of an AI workbench module. The extended computation graph of the inference path is transmitted from the extraction and extension module to an AI framework module. The method includes communicating of a communication adapter with the processing module continuously by using a supporting communication protocol for receiving training data as input for the AI function and forwarding the training data to the AI framework module. Learned parameters of the AI model are transferred from an API interface of the AI framework module to the communication adapter for updating the AI model.

Abstract: A method for securely operating an industrial control device together with an AI module for processing at least one AI data set via a two-stage decryption method.

Abstract: A method for ascertaining control data for a gripping device for gripping an object includes capturing an image of the object, determining at least one object parameter of the captured object, and ascertaining control data for a gripping device to grip the object at at least one gripping point, where ascertaining the at least one gripping point of the object is performed using information relating to at least one possible stable position of the object, and the possible stable position of the object is established such that all of the position data of the object that can be converted into one another via a movement and/or rotation about a surface normal of a support surface on which the object lies are assigned to the possible stable position.

Abstract: The invention relates to a method for generating training data for an ML model. The training data is designed to configure the ML model using a machine learning method. In particular, the ML model is designed to be used as part of a method for ascertaining control data for a gripping device for gripping an object.

Abstract: Provided is a system and method for minimizing non-productive idle times within an automation process executed by an automation facility, the system including a model memory which stores a probabilistic model of a distribution of object exchange times of objects used or consumed in the automation process; and an optimizer adapted to calculate optimal assignments of objects to magazine positions of an object storage magazine depending on the probabilistic model and depending on a sequence of productive non-idle times of objects used or consumed in process steps of the automation process.

Abstract: A computer-implemented method for generating a configuration for external datapoint access is provided, whereby the configuration includes at least one datapoint within an automation system, including: a) searching for and capturing at least one input and/or output field; b) extracting annotation data near to a visualized automation process value in a found I/O-field and surrounding the I/O-field; c) attributing extracted annotation data to at least one datapoint within the automation system; d) providing a data scheme built with via edges linked components representing elements of the user interface surface; e) querying a search through the data scheme for one or more visualized pre-selected automation process values and f) generating a configuration with at least one datapoint along with linked supplemental information as a result from the search; and g) outputting the configuration in an automation system readable and/or computer-readable format.

Abstract: A computer-implemented method for controlling a technical system is provided, including: —reading in hardware configuration parameters and a value of a real-time requirement of a control unit, —reading in hardware configuration parameters of a computing unit for artificial intelligence, —reading in a control application for controlling the technical system, the control application being configured to generate an input value for the control unit in accordance with an artificial intelligence, —determining a processing time of the control application for execution of the control application on the computing unit for artificial intelligence, considering the hardware configuration parameters of the control unit and the hardware configuration parameters of the computing unit for artificial intelligence, —checking the determined processing time based on the value of the real-time requirement of the control unit and outputting a check result, and —the control application, depending on the check result, for the contro

Abstract: A method and system for automatic maintenance of a machine (2) comprising the steps of receiving (S1) at least one maintenance relevant event (E) from a controller (3) of the machine (2); augmenting (S2) the received event (E) with the event's machine context read from a machine maintenance ontology; matching (S3) the event's machine context with maintenance rules to generate at least one maintenance task (T) comprising an associated task description; and providing (S4) a maintenance schedule for the machine (2) assigning the generated maintenance task (T) to suitable maintenance executing entities (5) on the basis of the task description of the respective maintenance task (T).

Abstract: A method for checking samples for defects is provided, in which image data of the samples are recorded and classified into predeterminable defect categories by a defect detection algorithm, and the samples classified into a defect category are represented in a multi-dimensional confusion matrix as a classification result of the defect detection algorithm, characterized in that—miniature images which reproduce the image data are assigned according to the classified defect categories of the image data to segments of the confusion matrix which represent the defect categories, and these miniature images are displayed visually, —the miniature image is assigned by an interaction with a user or a software robot to a different segment from the assigned segment of the confusion matrix, and is either provided as training image data for the defect detection algorithm or is output as training image data for the defect detection algorithm.