Abstract: A computer-implemented method for providing an automated chat output with respect to an industrial plant environment includes obtaining a prompt input from a user; selecting at least one related industrial plant document from a provided document database of a plurality of industrial plant documents, wherein the at least one related industrial plant document is related to the obtained prompt input; determining an enhanced prompt using the obtained prompt input and the selected at least one related industrial plant document; and determining a chat output by inputting the enhanced prompt into a first large language model.

Abstract: A method for detecting an anomaly includes obtaining a time-series of historical process variables within a predefined time span; determining a cycle time of the historical process variables; clustering the historical process variables into clusters based on cycle time; arranging the clusters into a tree; storing the tree; obtaining a time-series of a plurality of current process variables, which correspond to the historic process variables; and detecting the anomaly of at least one device by identifying a cycle time of a current process variable that is longer than the cycle time of a corresponding historic variable.

Abstract: A method for interactive explanations in industrial artificial intelligence systems includes providing a machine learning model and a set of test data, a set of training data and a set of historical data simulating a piping and process equipment; predicting a result for the piping and process equipment based on the machine learning model using the set of test data and the set of training data, wherein the set of historical data is used by the machine learning model to predict at least one parameter of the piping and process equipment; and presenting the predicted at least one parameter on a piping and instrumentation diagram of the piping and process equipment.

Abstract: A method for recommending an operational command includes receiving an alarm from a sensor and/or an operator; obtaining the current state of the plant that includes a current process value and/or operational command; comparing the current state to a list of historic states, each comprising a plurality of historic process values and/or historic operational commands; when the current state matches a subset of at least one of the historic states, starting a simulation and running a plurality of simulations, each based on a variation of at least one of the historic operational commands; determining, for each simulation of the plurality of simulations, a quality value, based on at least one quality criterion; and recommending the variation of the operational command that resulted in the simulation with the highest quality value.

Abstract: A method for deciding on a machine learning model result quality based on the identification of distractive samples in the training data includes providing a first result of the model based on initial training data; determining a first performance of the first result of the model; logging input data; providing a second result of the model based on initial training data and the input data, determining a second performance of the second result of the model and thereon based identifying erroneous data within the input data and/or the training data.

Abstract: A method for explanation of machine learning results based on using a model collection includes training at least two machine learning models with at least two competing strategies for the at least one dataset; and using the least two machine learning models to yield at least two different predictions and/or at least two explanations for the at least one dataset.

Abstract: A method for enabling user feedback and summarizing return of investment for machine learning systems includes providing a training data set and an initial machine learning model; providing a result of the initial machine learning model; receiving feedback on the result of the initial machine learning model from a user enriching the training dataset based on the feedback to an enriched data set; and retraining the initial machine learning model to a retrained machine learning model based on an enriched data set.

Abstract: An apparatus for monitoring a switchgear includes: an input unit; a processing unit; and an output unit. The input unit provides the processing unit with a monitor infra-red image of a switchgear. The processing unit implements a machine learning classifier algorithm to analyse the monitor infra-red image and determine if there is one or more anomalous hot spots in the switchgear. The machine learning classifier algorithm has been trained based on a plurality of different training infra-red images, the plurality of training infra-red images including a plurality of synthetic infra-red images generated from a corresponding plurality of visible images. The output unit outputs information relating to the one or more anomalous hot spots.

Abstract: A method for automatic identification of important batch events for a batch execution alignment algorithm, including receiving historical batch data of a batch process, wherein the historical batch data comprises a plurality of batch executions, and wherein each of the plurality of batch executions comprises a plurality of batch events, indicating a specific event of the batch process, and at least one time series of a process variable, indicating a development of the process variable during the batch process; determining a distance between the at least one time series of the plurality of the batch executions for each of the plurality of batch events; and identifying at least one important batch event for a batch execution alignment algorithm with a smallest distance using the determined distances.

Abstract: A method for determining an appropriate sequence of actions to take during operation of an industrial plant includes obtaining values of a plurality of state variables that characterize an operational state of the plant (or a part thereof); encoding by at least one trained state encoder network the plurality of state variables into a representation of the operating state of the plant; mapping by a trained state-to-action network the representation of the operating state to a representation of a sequence of actions to take in response to the operating state; and decoding by a trained action decoder network the representation of the sequence of actions to the sought sequence of actions to take.

Abstract: An apparatus for monitoring a switchgear includes: an input unit; a processing unit; and an output unit. The input unit is provides the processing unit with a monitor infra-red image of the switchgear. The processing unit implements a machine learning classifier algorithm to analyse the monitor infra-red image and determine if there is one or more anomalous hot spots in the switchgear. The machine learning classifier algorithm has been trained based on a plurality of different training infra-red images. The plurality of training infra-red images include a plurality of modified infra-red images generated from a corresponding plurality of infra-red images, each of the modified infra-red images having been modified to remove an effect of obscuration in the image. The output unit outputs information relating to the one or more anomalous hot spots.

Abstract: A method for training a prediction model includes obtaining training samples representing states of the process that do not cause the undesired event; obtaining based on a process model and a set of predetermined rules that stipulate states having an increased likelihood of the undesired event occurring; training samples representing states with an increased likelihood to cause the undesired event; providing samples to the to-be-trained prediction model to obtain a prediction of the likelihood for occurrence of the undesired event in a state of the process represented by the respective sample; rating a difference between the prediction and the label of the respective sample using a predetermined loss function; and optimizing parameters such that, when predictions are made, the rating by the loss function improves.

Abstract: A method for determining the state of health of an industrial process executed by at least one industrial plant comprising an arrangement of entities, and the state of each such entity, includes obtaining values of the entity state variables; providing the values to a model to obtain a prediction of the state of health; determining propagation paths for anomalies between said entities; determining importances of the states of health of the individual entities for the overall state of health of the process; and aggregating the individual states of health of the entities to obtain the overall state of health of the process.

Abstract: A holding device (100) for holding a structural part, in particular a semiconductor wafer (1) or a lithography mask, comprises a base body (10), which is formed from at least one board (11) with an upper side, and a plurality of protruding studs (12), which are arranged on the upper side of the board (11) and form a contact surface (13) with a predetermined flatness for contacting the structural part, wherein on the upper side of the board (11) a notch absorption layer (21) is provided, which has such a low volume density that the notch absorption layer (21) can be compressed by a compaction in the layer volume in the case of mechanical actions by foreign particles (2), without compromising the flatness of the contact surface (13). A method for manufacturing a holding device (100) for holding a structural part is also described.

Abstract: A method for providing an attribute of an element in a processing system having a plurality of elements, the processing system being represented as a directed graph having a plurality of nodes and directed edges, each node representing an element, each node having an attribute, and each directed edge representing a relation between two elements of the plurality of elements, the method including: selecting one node of the plurality of nodes as a starting node; constructing a subgraph, the subgraph including all the nodes that are forward-connected by at least one directed edge from the starting node; and outputting all nodes and the attribute of the nodes of the subgraph.

Abstract: A method for detecting change points, CPs, in a signal of a process automation system, includes, in an offline learning phase, unsupervised, candidate CPs on at least one offline signal using unsupervised detection method are detected, CPs are selected from the candidate CPs; the selected CPs are provided to a supervised process; in the supervised process, an offline machine-learning (ML) system is trained to refine CPs from the selected CPs using a supervised machine learning method; a training data set for an online ML system is created using the offline ML system by projecting the refined CPs on the signal; the online ML system is trained in a supervised manner, using the created training data set; and after the offline learning phase, CPs are detected using the trained online ML system.

Abstract: A method for determining an interdependency between a plurality of elements in an industrial processing system includes: providing a process flow diagram (PFD) of a topology of the processing system; transforming the PFD into a directed graph, each element of the plurality of elements being transformed into a node and each relation between the plurality of elements being transformed into a directed edge; selecting one node of the plurality of nodes as a starting node; and constructing a subgraph, the subgraph including all the nodes that are forward-connected from the starting node so as to show at least one interdependency between the plurality of elements in the subgraph.

Abstract: An assistance system comprises a plant topology repository comprising a representation of the components of the plant and relations between the components; a monitoring subsystem configured for monitoring signals from the components and for monitoring a related event, as a key for the monitored signals; an aggregation subsystem configured for storing a plurality of the monitored signals and the related events, wherein at least one of the events is the abnormal situation; an identification subsystem configured for comparing currently monitored signals to stored monitored signals and the related event; and an evaluation subsystem configured for outputting a predefined action, if the currently monitored signals match to the event that is the abnormal situation.

Abstract: A method for generating and/or augmenting an execution protocol for an SOP in an industrial plant includes providing at least one SOP of the plant, which includes a plurality of steps; providing measurement data; for each step of the SOP, determining from the measurement data a subset of the measurement data that is indicative of actions performed for the purpose of executing this particular step of the SOP; and aggregating the subset of the measurement data determined for each step of the SOP into at least one instruction for executing this particular step of the SOP, wherein this instruction is part of the sought protocol.

Abstract: The invention relates to an input device comprising capacitive detection device having detection surface including first array of array electrodes; electronic evaluation unit electrically connected to array electrodes to form associated electric measuring field array for spatially resolving detection of capacitive influence on detection surface; handling means disposed on detection surface to be movable along an adjustment path parallel to detection surface, in order to perform an operating input; position indicator; and coupling device with a first surface on which a second array of coupling electrodes is formed, and with a second surface on which a third array including spaced-apart contact surfaces is formed. Based on the position of the handling means, contact surfaces are touch-contacted by the position indicator. The coupling device includes several electrically conductive connections to capacitively influence the measuring field array.