Abstract: Various teachings of the present disclosure include disassembly assistance methods. An example includes: visually capturing a product to be disassembled; generating image data for the part; requesting a prompt for a multimodal LLM; transmitting the image data to the LLM module and generating the prompt; generating an output with a disassembly step using the multimodal LLM; transmitting the disassembly data to a visualization module; generating visualization data correlating with the disassembly data using the visualization module; transmitting the visualization data to an image-generating device; generating an image based on the visualization data; displaying the generated image using the image-generating device; detecting a trigger signal corresponding with completion of the disassembly step; and repeating a-k until an abort criterion is reached.

Abstract: To train a machine learning routine (BNN), a sequence of first training data (PIC) is read in through the machine learning routine. The machine learning routine is trained using the first training data, wherein a plurality of learning parameters (LP) of the machine learning routine is set by the training. Furthermore, a value distribution (VLP) of the learning parameters, which occurs during the training, is determined and a continuation signal (CN) is generated on the basis of the determined value distribution of the learning parameters. Depending on the continuation signal, the training is then continued with a further sequence of the first training data or other training data (PIC2) are requested for the training.

Abstract: An image analysis device (BA) is configured to recognize imaged objects. A plurality of training images (TPIC) assigned to an object type (OT) and an object sub-type (OST) are fed into a first neural network module (CNN) to detect image features. Training output data sets (FEA) of the first neural network module are fed into a second neural network module (MLP) to detect object types using the detected image features. For each object type: training images assigned to the object type (OT1, OT2) are fed into the trained first neural network module, the first neural network module training output data set (FEA1, FEA2) generated for the respective training image is assigned to the object sub-type (OST) of the respective training image, and by means of the aforementioned sub-type assignments, a sub-type detection module (BMLP1, BMLP2) is configured to detect object sub-types.

Abstract: A method for detecting an abnormal behavior of a device, includes capturing data of at least two different sensors associated to the device within a temporal sequence of time intervals, estimating a relationship between two different sensors for each combination of two different sensors and for each of the time intervals by determining a precision matrix of a multivariate probabilistic model, each matrix element representing the relationship between two sensors, determining a temporal course of the precision matrix by applying the precision matrix of neighboring time intervals with at least one penalty, and identifying an abnormal behavior of the device, if the precision matrix of adjacent time intervals differs by a value larger than an expected threshold value.

Abstract: To configure a machine controller by an action execution tree, predefined action patterns are read in. A multiplicity of action execution trees for a machine to be controlled is also generated. For a respectively generated action execution tree, a performance for controlling the machine based on the respective action execution tree is determined. The predefined action patterns are also sought in the respective action execution tree. An action pattern found in the respective action execution tree is then replaced at least in part by a reference to the predefined action pattern. A tree size of the thus modified action execution tree is furthermore determined. Based on the generated action execution trees, a numerical optimization method is then used to determine an action execution tree that is optimized with regard to better performance and smaller tree size, and this is output in order to configure the machine controller.

Abstract: Computer-implemented method and control apparatus for controlling a machine by executing program steps which verifiably execute predefined control tasks is provided, including manipulating data based on input data received from the machine and resulting in reference data by data programming steps structured according to a declarative programming paradigm in a data processing unit, and performing control program steps verifying the reference data with respect to explicit conditions, without any further manipulation of the reference data in the control program steps in a control processing unit, and providing instructions resulting from the performed control program steps to the machine for execution of the instructions by the machine.

Abstract: A computer implemented method for automatically generating a behavior tree program for controlling a machine includes the steps of: transmitting a sequence of machine commands input by a user from a user interface to a controller, receiving supervision data in the user interface from the controller while the machine commands are executed in the controller controlling the machine, observing and copying the machine commands and supervision data transmitted between the controller and the user interface, storing the machine commands and the supervision data in a logging unit, generating a behavior tree program derived from the stored machine commands and the supervision data by statistical inference, and sending the generated behavior tree program to the controller unit to control the machine.

Abstract: System and method for engineering at least one technical system including one or more cyber-physical devices is disclosed. The method includes generating an engineering code for the technical system based on at least one of configuration and function associated with the devices, wherein the engineering code enables coordination between the devices whereby at least one operation in the technical system is performable; determining executability of the engineering code based on a compatibility indicator associated with at least one of the devices, the system and the operation; and engineering at least one device of the one or more devices based on the determined executability of the engineering code.

Abstract: An apparatus for monitoring an actuator system, a method for providing an apparatus for monitoring an actuator system, and a method for monitoring an actuator system where the has at least one actuator and at least one data output signal. An anomaly detector detects anomalies. A suppressing engine determines time periods in which a control intervention has been performed. In a resulting monitoring signal, only anomalies are indicated which do not overlap with time periods in which the control intervention has been performed resulting in less irrelevant alerts and false positives output to a human supervisor monitoring the actuator system. The apparatus for monitoring a system may be provided with a plurality of actuators that may affect one another over time. The apparatus may be applied to a system of submersible pumps, or a system of conveyor belts.

Abstract: In order to test an autonomous behavior controller for a technical system, the following are input: a machine model for physically simulating the technical system; an environment model modelling an environment of the technical system; as well as a disruption model modelling potential disruptions in the environment. Disruption data is generated by means of the disruption model, and the environment model is modified according to the disruption data. Environment-specifically simulated sensor data the technical system is then generated by means of the modified environment model and the machine model. According to the simulated sensor data, control data is generated for the technical system by the autonomous behavior controller. An operating behavior of the technical system induced by the control data is then simulated by means of the machine model. Furthermore, a performance value quantifying the operating behavior is determined and output as a test result.

Abstract: A computer implemented method for automatically generating a behavior tree program for controlling a machine includes the steps of: transmitting a sequence of machine commands input by a user from a user interface to a controller, receiving supervision data in the user interface from the controller while the machine commands are executed in the controller controlling the machine, observing and copying the machine commands and supervision data transmitted between the controller and the user interface, storing the machine commands and the supervision data in a logging unit, generating a behavior tree program derived from the stored machine commands and the supervision data by statistical inference, and sending the generated behavior tree program to the controller unit to control the machine.

Abstract: A method for detecting an abnormal behavior of a device, includes capturing data of at least two different sensors associated to the device within a temporal sequence of time intervals, estimating a relationship between two different sensors for each combination of two different sensors and for each of the time intervals by determining a precision matrix of a multivariate probabilistic model, each matrix element representing the relationship between two sensors, determining a temporal course of the precision matrix by applying the precision matrix of neighboring time intervals with at least one penalty, and identifying an abnormal behavior of the device, if the precision matrix of adjacent time intervals differs by a value larger than an expected threshold value.

Abstract: A device obtains a set of time series data monitored on a machine and further obtains first label information indicating a first time window in the time series data. The device determines a first probabilistic model, describing dynamics of the time series data inside the first time window, and a second probabilistic model describing dynamics of the time series data adjacent to the first time window. Based on the first and second probabilistic models, the device determines a first part of the time series data that is estimated to match the first probabilistic model and a second part of the time series data that is estimated to match the second probabilistic model, e.g., using a hidden Markov model. The device then determines second label information indicating a second time window which includes the first part of the time series data and excludes the second part of the time series data.

Abstract: A computer-implemented method and a data processing apparatus provide and apply a trained probabilistic graphical model for verifying and/or improving the consistency of labels within the scope of medical image processing. Also provided are a computer-implemented method for verifying and/or improving the consistency of labels within the scope of medical imaging processing, a data processing apparatus embodied to verify and/or improve the consistency of labels within the scope of medical image processing, and a corresponding computer program product and a computer-readable medium.

Abstract: In order to control a technical system by means of control model a data container is received, in which data container a control model having a training structure and model type information are encoded over all the model types. One of multiple model-type specific execution modules is selected for the technical system as a function of the model type information. Furthermore, operating data channels of the technical system are assigned input channels of the control model as a function of the model type information. Operating data of the technical system are acquired via a respective operating data channel and are transferred to the control model via an input channel assigned to this operating data channel. The control model is executed by means of the selected execution module, wherein control data are derived from the transferred operating data according to the training structure and are output to control the technical system.

Abstract: The aim of the invention is to configure an image analysis device (BA). This is achieved in that a plurality of training images (TPIC) assigned to an object type (OT) and an object sub-type (OST) are fed into a first neural network module (CNN) in Order to detect image features. Furthermore, training output data sets (FEA) of the first neural network module (CNN) are fed into a second neural network module (MLP) in Order to detect object types using image features. According to the invention, the first and second neural network module (CNN, MLP) are trained together such that training output data sets (OOT) of the second neural network module (MLP) at least approximately reproduce the object types (OT) assigned to the training images (TPIC).

Abstract: An apparatus for monitoring an actuator system, a method for providing an apparatus for monitoring an actuator system, and a method for monitoring an actuator system where the has at least one actuator and at least one data output signal. An anomaly detector detects anomalies. A suppressing engine determines time periods in which a control intervention has been performed. In a resulting monitoring signal, only anomalies are indicated which do not overlap with time periods in which the control intervention has been performed resulting in less irrelevant alerts and false positives output to a human supervisor monitoring the actuator system. The apparatus for monitoring a system may be provided with a plurality of actuators that may affect one another over time. The apparatus may be applied to a system of submersible pumps, or a system of conveyor belts.

Abstract: To train a machine learning routine (BNN), a sequence of first training data (PIC) is read in through the machine learning routine. The machine learning routine is trained using the first training data, wherein a plurality of learning parameters (LP) of the machine learning routine is set by the training. Furthermore, a value distribution (VLP) of the learning parameters, which occurs during the training, is determined and a continuation signal (CN) is generated on the basis of the determined value distribution of the learning parameters. Depending on the continuation signal, the training is then continued with a further sequence of the first training data or other training data (PIC2) are requested for the training.

Abstract: In order to control a technical system, e.g. of a wind turbine, a temporal sequence of operating parameter values of the technical system that is continuously recorded and continuously converted into a sequence of filtered signal values by a trainable digital filter. The sequence of the filtered signal values is supplied to a mechanical learning routine which derives prediction values therefrom for a target operating parameter. The digital filter and the mechanical learning routine are trained to reduce a distance between derived prediction values and temporally corresponding, actually recorded values of the target operation parameter. The prediction values for controlling the technical system are then emitted.

Abstract: The present invention relates to a computer-implemented method and a data processing apparatus for providing and applying a trained probabilistic graphical model for verifying and/or improving the consistency of labels within the scope of medical image processing, the use of the model for verifying and/or improving the consistency of labels within the scope of medical image processing, a computer-implemented method for verifying and/or improving the consistency of labels within the scope of medical imaging processing, a data processing apparatus embodied to verify and/or improve the consistency of labels within the scope of medical image processing, and a corresponding computer program product and a computer-readable medium.