Abstract: The present application relates to a electro-optical device manufactured by a method, 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 computer program product, a monitoring unit, gas analysis device equipped with the monitoring unit, use of artificial intelligence for monitoring the gas analysis device, and monitoring methods for a system having a plurality of devices which are configured to provide an associated measured value and/or a control command, wherein the monitoring methods are based on the use of a processing device or a neural network, with which measured values and/or control commands are evaluated.

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 computer-implemented method for anomaly detection in sensor data includes a) generating and training a first and second local model via an autoencoder and determining a local threshold value for each local model output variable; b) transmitting local model weightings and local threshold values to a server; c) generating and training a global model via the autoencoder and determining global threshold values for global model output variables; d) transmitting the global model weightings and global threshold value to the first client, and adopting global model weightings for the first local model; e) capturing first sensor data by a first sensor; f) applying the first sensor data to the first local model and determining the first local model output variable of the first client; and g) detecting an anomaly for the sensor data, if the local model output variable is outside a range that is fixed by the global threshold value.

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 method for operating a terminal with high availability in a network, where a memory stores an identifier, for a backup device of a first edge device, which relates to a second edge device, stores a model for operating the terminal and stores information about the connection configuration between the first and second edge devices, the monitoring device and the terminal, where the first edge device periodically sends a signal about its correct operation, the signal is received by the monitoring device, and detection of an absent or erroneous signal results in an associated error device being detected, and the model and the connection configuration of the error device being transferred from the memory to a substitute device, the substitute device being determined via the identifier associated with the absent or erroneous signal, and the substitute device operating the terminal using the received model and the connection configuration.

Abstract: A computer program product, a monitoring unit, gas analysis device equipped with the monitoring unit, use of artificial intelligence for monitoring the gas analysis device, and monitoring methods for a system having a plurality of devices which are configured to provide an associated measured value and/or a control command, wherein the monitoring methods are based on the use of a processing device or a neural network, with which measured values and/or control commands are evaluated.

Abstract: A computer-implemented method for detecting deviations in a production process with process parameters includes providing reference process data of a reference production process which comprises reference parameters of the production process, generating and training a process model with model nodes and corresponding model weights based on an autoencoder using the reference process data, at least partly assigning model nodes of the process model to process parameters of the production process, providing current process data from a current production process that comprises current parameters of the production process, ascertaining process deviations of the current process data using the process model by determining a reconstruction error and outputting the model weights of the model nodes, estimating the future curve of the reconstruction error, and checking whether the estimated future curve of the reconstruction error lies within a specified value range for the specified duration and if so continuing, otherwi

Abstract: A computer-implemented method for operating a technical device which is connected to a client of a client-server system that includes a server and connected clients that at least temporarily interact with the server, which is captured as interactions, with a model based on federated learning, wherein a reliability factor, a reaction time factor and ca quality-of-information factor are captured, a trust factor formed as a Bayesian network is determined for each of the clients, local models in each of the clients are trained, the trained local models are transmitted from each of the clients to the server, the transmitted local models of each of the clients are aggregated into a global model by applying the relevant trust factor to each local model, the global model is transmitted from the server to the client, and the technical device is controlled aided by the global model.

Abstract: A computer-implemented method for operating a technical device via a model, wherein a) clients having a respective technical device are acquired, b) the clients are grouped into first and second groups through comparison with a respectively predetermined range of values for the respective group, c), d) a first and second group models for the first and second groups are trained and provided to a server, respectively, e) the first and the second group models are received and aggregated via the server and a global model having global model parameters is formed from the first and second group models, f) the global model is transmitted to a client and the technical device is operated via the global model, where the latency of the clients is also acquired in a) and the clients are grouped in b) based on their respective latency.

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-axis 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 computer-implemented method for operating a technical device using a model based on artificial intelligence by a client of a client-server system, wherein each client stores a client model for operating a technical device, where a global model is provided to a client based on federated learning, and where the technical device is operated using the client model and sensitive parameter.

Abstract: A method for operating a terminal with high availability in a network, where a memory stores an identifier, for a backup device of a first edge device, which relates to a second edge device, stores a model for operating the terminal and stores information about the connection configuration between the first and second edge devices, the monitoring device and the terminal, where the first edge device periodically sends a signal about its correct operation, the signal is received by the monitoring device, and detection of an absent or erroneous signal results in an associated error device being detected, and the model and the connection configuration of the error device being transferred from the memory to a substitute device, the substitute device being determined via the identifier associated with the absent or erroneous signal, and the substitute device operating the terminal using the received model and the connection configuration.

Abstract: A computer-implemented method for operating a technical device with a model based on artificial intelligence including detecting a first operating parameter of a reference apparatus in a first operating environment and a first permissible operating mode, detecting a second operating parameter of the reference apparatus in a second operating environment and a second permissible operating mode, performing a first Fourier transform for the first sensor signal and a second Fourier transform for the second sensor signal, determining a quotient from the first and second Fourier transforms as a transfer function, generating and training a first model based on artificial intelligence for the reference apparatus in the first operating environment, generating a second model based on artificial intelligence for the technical device in the second operating environment using the first model and applying the transfer function, and operating the technical device with the second model.

Abstract: Method, inspection device, system for transferring a machine learning model and computer-implemented data structure for transferring the machine learning model includes a description for a technical component, a designation for a feature of the component, a classification model for the feature of the component, and at least one sensor parameter that describes the detection of the component by means of at least one sensor element.

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: 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 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.