Abstract: A monitoring apparatus and method for quality monitoring of a supplemented manufacturing process to a set of predefined manufacturing processes of industrial manufacturing includes: obtaining teacher models, providing an initial version of a student learning model and an initial version of a generator learning model, for each teacher model, training the generator learning model and a teacher specific student model to create data samples where the teacher model and teacher specific student learning models do not agree in their predictions, and adapting the current version of the student learning model based all trained teacher specific student models, customizing the adapted student model to the supplemented manufacturing process by training the adapted student model with annotated data of the supplemented manufacturing process, and monitoring the supplemented manufacturing process by processing the customized student model using data samples collected during the supplemented manufacturing process as input dat

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: In order to be able to take into account machining configurations more flexibly, a method for optimizing numerically controlled machining of a workpiece includes ascertaining geometric interaction data. A relationship between a force to be expected and a configuration parameter of the machining is determined on the basis of the interaction data. The force is calculated during the machining on the basis of the relationship and a current value of the at least one configuration parameter. The machining is adapted depending on the calculated force.

Abstract: A method determines a correction value for a control device for an electric machine, which describes an angular difference between a position of a d-axis of the electric machine and an actual position of the d-axis. The correction value is determined in a rotating state of a rotor of the electric machine as a function of a d voltage value describing a d component of a stator voltage specified by the control device in the initial configuration, of a q voltage value describing a q component of the stator voltage specified by the control device in the initial configuration, of a flux value describing a magnetic flux of the rotor, a speed value describing the speed of the rotor in the rotating state, and of a calibration value describing a speed-dependent voltage error of the d component of the stator voltage.

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: Provided is a method and system for detection of anomalous work pieces that includes computing at least one deviation data signal for a target data signal of a target work piece with respect to reference data signals recorded for a corresponding production process step of a set of reference work pieces, performing a stepwise anomaly detection by data processing of the at least one computed deviation data signal and a process type indicator indicating a type of the production process step using a trained anomaly detection data model to calculate for each time step or path length step of the production process step an anomaly probability that the respective time step or path length step is anomalous, and classifying the target work piece and/or the production process step as being anomalous or not anomalous on the basis of the calculated anomaly probabilities.

Abstract: A method for quality control in industrial manufacturing for one or more production processes for producing at least one workpiece and/or product includes creating a learning model for at least one production process for the at least one workpiece and/or product. The learning model is trained and initialized using a meta-learning algorithm, and the learning model is calibrated using normalized data of the at least one production process for the at least one workpiece and/or product. Currently generated data of the at least one production process for at least one currently produced workpiece/product is forwarded to the learning model. The data is generated by sensors. The learning model compares the currently generated data with the normalized data and finds deviations. The learning model scales the deviations between the currently generated data and the normalized data, and the learning model communicates presence of an anomaly for the currently produced workpiece/product.

Abstract: The present disclosure relates to a method of and a system for building a latent feature extractor as well as a neural network including a latent feature extractor built by the method and/or with the system. The method includes providing non-uniform training data for a multitude of tasks and optimizing parameters of a neural network of the latent feature extractor based on the multitude of tasks.

Abstract: In order to be able to take into account machining configurations more flexibly, a method for optimizing numerically controlled machining of a workpiece includes ascertaining geometric interaction data. A relationship between a force to be expected and a configuration parameter of the machining is determined on the basis of the interaction data. The force is calculated during the machining on the basis of the relationship and a current value of the at least one configuration parameter. The machining is adapted depending on the calculated force.

Abstract: A method determines a correction value for a control device for an electric machine, which describes an angular difference between a position of a d-axis of the electric machine and an actual position of the d-axis. The correction value is determined in a rotating state of a rotor of the electric machine as a function of a d voltage value describing a d component of a stator voltage specified by the control device in the initial configuration, of a q voltage value describing a q component of the stator voltage specified by the control device in the initial configuration, of a flux value describing a magnetic flux of the rotor, a speed value describing the speed of the rotor in the rotating state, and of a calibration value describing a speed-dependent voltage error of the d component of the stator voltage.

Abstract: Provided is a method and system for detection of anomalous work pieces that includes computing at least one deviation data signal for a target data signal of a target work piece with respect to reference data signals recorded for a corresponding production process step of a set of reference work pieces, performing a stepwise anomaly detection by data processing of the at least one computed deviation data signal and a process type indicator indicating a type of the production process step using a trained anomaly detection data model to calculate for each time step or path length step of the production process step an anomaly probability that the respective time step or path length step is anomalous, and classifying the target work piece and/or the production process step as being anomalous or not anomalous on the basis of the calculated anomaly probabilities.

Abstract: The invention relates to a drive (1) of a tail rotor (12) of a helicopter (10) by a permanently excited transversal flux machine in duplex arrangement in such a way that between two stators (4), which each have a toroidal winding system (8), there is arranged a disc-shaped impeller (5), which has permanent magnets (15) and on the outer circumference of which propeller blades (14) of the tail rotor (12) are arranged.

Abstract: In a method for operating a three-phase inverter of a converter-fed magnetic bearing, two coils are connected to respective outputs of the three-phase inverter at one end and are connected to each other and to a third output of the three-phase inverter at the other end. A variable control current is injected into the third output. A constant bias current flows between the respective outputs and thus serially through the two coils. The control current is divided among the two respective outputs so as to flow parallel through the two coils. This arrangement significantly reduces the effective current load of the three-phase inverter and significantly increases the slew rate of the control current.

Abstract: In a method for manufacturing a gearwheel, a gearwheel blank is clamped in a workholder of a multi-axis machine tool. A milling head is clamped in a tool holder which is rotated by a spindle drive to enable the milling head to mill out tooth spaces of the gearwheel blank to thereby create a gearwheel having teeth. After replacing the milling head in the tool holder with an inductor, the inductor is inserted successively between two adjacent teeth of the gearwheel and supplied with alternating current from a current supply device of the spindle drive to inductively heat at least one of the two adjacent teeth. The inductor in the tool holder is then replaced with a machining tool to remachine the teeth of the gearwheel.

Abstract: A method for determining an electrical torque of an electrical machine includes determining an electrical torque in a first speed range with a first algorithm, and determining the electrical torque in a second speed range with a second algorithm which differs from the first algorithm. An upper limit of the second speed range is slightly higher than a lower limit of the first speed range. An apparatus is provided to determine the electrical torque of the electrical machine with the aforedescribed method.

Abstract: A drive system for an electric motor includes a connection for a battery, and an inverter having an input side connected to an intermediate circuit and an output side having a connection for an electric motor. The intermediate circuit includes a first thyristor connected in parallel with an intermediate circuit capacitance. The drive system may also include a rectifier having an input side connected at the output side of the inverter in parallel with the electric motor, and a second thyristor connected an output side of the rectifier. The first/second thyristor are configured to be activated by a monitor incorporated in or assigned to the drive system. In the event of a malfunction, the input and/or output side of the inverter can be electrically isolated to allow a multiply redundant armature short circuit.

Abstract: A method for estimating a torque of a three-phase motor for a vehicle includes measuring a respective current strength in at least two of three phase lines, wherein the three-phase motor is supplied with power by a converter, and wherein the three phase lines lead from the converter to the three-phase motor of the vehicle, measuring a respective voltage at each of the three phase lines, determining a rotating field frequency as a function of the measured current strengths or the measured voltages; and determining an estimated value for the torque as a function of the measured current strengths, the measured voltages and the determined rotating field frequency.

Abstract: In a method for operating a three-phase inverter of a converter-fed magnetic bearing, two coils are connected to respective outputs of the three-phase inverter at one end and are connected to each other and to a third output of the three-phase inverter at the other end. A variable control current is injected into the third output. A constant bias current flows between the respective outputs and thus serially through the two coils. The control current is divided among the two respective outputs so as to flow parallel through the two coils. This arrangement significantly reduces the effective current load of the three-phase inverter and significantly increases the slew rate of the control current.

Abstract: A power converter circuit has at least two submodules connected in a series circuit and receiving electrical power from a power source outputting a DC voltage, via an inductance. Each submodule has, on the input side, a single-phase half bridge and, on the load side, a single-phase full bridge, wherein the half bridge and the full bridge are connected on the DC voltage side in parallel with an intermediate circuit capacitor. At least one electrical line composed of several current paths connected in parallel with one another is formed in each submodule.

Abstract: A method for determining an electrical torque of an electrical machine includes determining an electrical torque in a first speed range with a first algorithm, and determining the electrical torque in a second speed range with a second algorithm which differs from the first algorithm. An upper limit of the second speed range is slightly higher than a lower limit of the first speed range. An apparatus is provided to determine the electrical torque of the electrical machine with the aforedescribed method.