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: The present invention relates to a photodetector (3) comprising: a longitudinal portion (12) of a waveguide (11) which comprises or is formed by two waveguide segments (12a, 12b), which extend at least substantially parallel to one another in the longitudinal direction and are preferably distanced from one another in the transverse direction, forming a gap (14) between them; and an active element (13), which overlies the longitudinal portion (12) of the waveguide and comprises at least one material or consists of at least one material that absorbs electromagnetic radiation of at least one wavelength and generates an electric photosignal as a result of the absorption, the two waveguide segments (12a, 12b) each being in contact, at least in some portions, on at least one side, in particular on the side facing the active element (14), with a gate electrode (15a, 15b) which preferably comprises silicon or consists of silicon.

Abstract: The present invention relates to an electro-optical device (1) having two interaction regions (2), which each comprise a longitudinal waveguide section (3) and one or two active elements (5), which active element or the respective active element comprises or consists of at least one electro-optical active material, more particularly graphene, wherein the longitudinal waveguide sections (3) of the two interaction regions (2) are arranged spaced apart from one another, and the active element or the respective active element (5) extends at least in some sections above and/or below and/or within the waveguide longitudinal section (3) of the respective interaction region (2), and wherein two or more contact elements (6) are provided which are each in contact with at least one of the active elements (5).

Abstract: Apparatus and method for operating a machine with a tool, wherein the method includes capturing at least one operating data point for the machine and/or the tool, calculating at least one estimate value from the at least one operating data point based on an ML model, determining an anomaly in the form of a discrete-time anomaly value based on the at least one estimate value via a comparison with a predetermined comparison value for the at least one estimate and detection of a match for the estimate comparison, storing the discrete-time anomaly value in a memory and aggregating the trend in the anomaly value over time to form a smoothed anomaly value, comparing the smoothed anomaly value with at least one predetermined comparison value for the anomaly and detecting a match for the anomaly comparison, and outputting a control operation to the machine based on the smoothed anomaly value.

Abstract: A semiconductor device comprising a wafer with a preferably single-piece semiconductor substrate, in particular silicon substrate, and at least one integrated electronic component extending in and/or on the semiconductor substrate, the wafer having a front-end-of-line and a back-end-of-line lying there above, the front-end-of-line comprising the integrated electronic component or at least one of the integrated electronic components, and a photonic platform fabricated on the side of the wafer facing away from the front-end-of-line, which photonic platform comprises at least one waveguide and at least one electro-optical device, in particular at least one photodetector and/or at least one electro-optical modulator, wherein the electro-optical device or at least one of the electro-optical devices of the photonic platform is connected to the integrated electronic component or at least one of the integrated electronic components of the wafer.

Abstract: The present application relates to a method for manufacturing an electro-optical device, wherein a waveguide (3) is provided (S1), a planarization coat (7) overlapping at least a section of the waveguide (3) is fabricated (S2), the planarization coat (7) is provided with a spin-on-glass coating (9) (S3), at least in the region of the spin-on-glass coating (9), a preferably dry chemical etching treatment is carried out (S4), optionally, the steps of providing the planarization coat (7) with a spin-on-glass coating (9) and the etching treatment are repeated at least once (S5, S6), and an active element (10) is provided (S7) on or above the planarization coat (7) and above the waveguide (3).

Abstract: A method and device for machine learning wherein, in order to create favorable method conditions, an at least first machine learning model is trained via an at least first data set, a second machine learning model is trained via a second data set, an at least first prediction data set is formed via the trained at least first machine learning model, a second prediction data set is formed via the trained second machine learning model, a linking machine learning model is trained at least via the first prediction data set and the second prediction data set, a third prediction data set is formed via the linking machine learning model, and controlled variables for controlling a control apparatus are formed at least via the third prediction data set, such that the demand for computing power is reduced and the prediction accuracy and control accuracy are increased.

Abstract: Method for monitoring operation of a technical object, wherein a) a first orientation of the first acceleration sensor in the form of a position vector is determined, b) the mathematical model for operation of the object is generated and trained, c) the first acceleration sensor is disassembled and a three-axle replacement acceleration sensor is assembled with a new orientation on the object, d) acceleration values are detected, e) respective indicator values are calculated from the temporal course of the detected acceleration values of the replacement acceleration sensor, f) a replacement vector is determined from the indicator values and a differential vector between the replacement vector and the position vector of the first acceleration sensor determined in step b) is determined, and g) the model during operation of the object for the position vector in the orientation of the replacement vector is applied by taking into account the differential vector.

Abstract: A method for adapting a first software application that is executed in a gateway G and that controls the data transfer of the gateway, wherein in the gateway connects at least one device of a local network to a cloud network, where machine learning is performed via a second software application based on at least one state of the environment of the gateway and at least one possible action of the gateway, the result of the machine learning contains at least one quality value of a pairing of a state of the environment of the gateway and an action of the gateway, and where the first software application executes those actions of the gateway that have a higher quality value for a given state of the environment of the gateway than other actions.

Abstract: A method for identifying the occurrence of a defect in a pipeline by estimation, wherein at least one first indicator is identified by a first detector assigned to a first detection location, from which a first estimation value regarding the occurrence of the defect in the pipeline is determined, and at least one second indicator is identified by at least one second detector assigned to a second detection location, from which at least one second estimation value regarding the occurrence of the defect in the pipeline is determined. An overall estimation value is determined from the first estimation value and the at least one second estimation value by an overall estimation function by taking into account the respective positions of the first detection location and the second detection location, from which overall estimation value the occurrence of the defect is estimated.

Abstract: A method for operating a technical installation with an optimal model, wherein the installation forms part of a system with a first technical installation and at least one second technical installation, where each installation includes a control apparatus and a connected technical device, and where the system also includes a server with a memory.

Abstract: A method for distributing sub-applications among computers of at least two different levels, wherein a first level has more computing power available than a second level, where constraints for execution of an application and individual sub-applications are registered in a database, where prerequisites of the different levels that correspond to the constraints for execution, namely prerequisites of the at least one platform of a level, are registered in a database, where the sub-applications necessary for the application are selected, where, from the constraints for the application and individual sub-applications and from the corresponding prerequisites of the different levels, namely the at least one platform of each level, a constraint satisfaction problem is automatically created and solved, and where the sub-applications are distributed among computers of the different platforms in accordance with the solution of the constraint satisfaction problem such that the method becomes plannable in an automated and

Abstract: A method and device for machine learning wherein, in order to create favorable method conditions, an at least first machine learning model is trained via an at least first data set, a second machine learning model is trained via a second data set, an at least first prediction data set is formed via the trained at least first machine learning model, a second prediction data set is formed via the trained second machine learning model, a linking machine learning model is trained at least via the first prediction data set and the second prediction data set, a third prediction data set is formed via the linking machine learning model, and controlled variables for controlling a control apparatus are formed at least via the third prediction data set, such that the demand for computing power is reduced and the prediction accuracy and control accuracy are increased.

Abstract: A method for visualizing and validating process events in process monitoring systems, wherein a permanently installed sensor system reports states to a process monitoring system, if predefined limit values are exceeded, then the process monitoring system initiates, plans and performs local data acquisition using a mobile sensor, where the result of this data acquisition is analyzed and visualized in the process monitoring system and is integrated in the state information relating to the process or the installation.

Abstract: A method for assembling a team with the aid of a computer, wherein the team is assembled for the purpose of performing a specific task and wherein the team includes humans and robots as members, where the method includes specifying the technical skills that are required to perform the task, picking a subgroup of potential members having these technical skills from a given group of humans and robots, and assembling the members for the team from this subgroup via a genetic algorithm using a fitness function.

Abstract: An apparatus for installing a pipeline slipliner, by pushing rather than drawing the slipliner into the host pipe. The gripper assembly is mounted on the boom of an earthworking machine or other vehicle, such as a track excavator. The gripper assembly includes gripper tracks that engage the exterior of the slipliner and advance it in a linear fashion. The gripper assembly is lowered on a boom into a excavation so as to level with the opening of the host pipe. The gripper assembly is then operated to advance the slipliner into the host pipe, with the slipliner being feed down to the gripper assembly on the surface of the excavation. The gripper assembly resiliently compresses the slipliner to establish a grip that enables it to push the slipliner great distances into the host pipe.