Abstract: To restore consistency of a digital twin database, identifiers with metadata imported from various data sources are processed by an encoder, which computes latent representations of the identifiers that are compared by an efficient similarity metric. If the respective similarity score exceeds a threshold, a match is detected between the identifiers. In that case, the digital twin database is updated by aligning the first identifier and the second identifier. This matching algorithm for equipment identifiers updates the digital twin data automatically and continuously by aligning identifiers which refer to the same piece of equipment. The updates flow directly into the digital twin database, thereby removing the manual effort. Using approximate nearest neighbor methods is highly efficient, especially for large plants. The encoder is implemented as an autoencoder which relies only on unlabeled training data.

Abstract: A solution for automated column type annotation maps each column contained in a table to a column annotation class. A pre-processor transforms the table into a numerical tensor representation by outputting a sequence of cell tokens for each cell in the table. A table encoder encodes the sequences of cell tokens and a column annotation label for each column into body cell embeddings. A body pooling component processes the body cell embeddings to provide column representations. A classifier classifies the column representations to provide for each column, confidence scores for each column annotation class. The method concludes with comparing the highest confidence score for each column with a threshold, and, if the highest confidence score for each column is above the threshold, annotating each column with the respective column annotation class.

Abstract: A database stores a set of items, with each item having technical attributes, and with each item representing a module that can be used in an engineering project of a first user, u1. A feature encoder embeds each item based on its technical attributes into a low-dimensional vector space. Then, in a second step, a graph neural network pools over these item embeddings to compute an updated user embedding for the first user A decoder mapping then addresses the recommendation task by outputting recommendation scores for each item. That means, heuristically speaking, that the method and system lift the recommendation task to the level of technical attributes to overcome the sparsity problem caused by item sets that are not overlapping between user groups. Thus, when matching similar users, the method does not rely on users configuring exactly the same modules but rather on configured modules that are similar from a technical point of view.

Abstract: An initially trained machine learning model is used by an active learning module to generate candidate triples, which are fed into an expert system for verification. As a result, the expert system outputs novel facts that are used for retraining the machine learning model. This approach consolidates expert systems with machine learning through iterations of an active learning loop, by bringing the two paradigms together, which is in general difficult because training of a neural network (machine learning) requires differentiable functions and rules (used by expert systems) tend not to be differentiable. The method and system provide a data augmentation strategy where the expert system acts as an oracle and outputs the novel facts, which provide labels for the candidate triples. The novel facts provide critical information from the oracle that is injected into the machine learning model at the retraining stage, thus allowing to increase its generalization performance.

Abstract: A computer-implemented method and system for assigning at least one query triplet to at least one respective class. The at least one respective class is true or false. The method includes the steps of providing the at least one query triplet and a knowledge graph with a plurality of triples and extracting at least one affirmative argument using reinforcement learning on the basis of the at least one query triplet and the knowledge graph. The at least one affirmative argument indicates that the at least one query triplet is true. The method further includes extracting at least one opposing argument using reinforcement learning on the basis of the at least one query triplet and the knowledge graph. The at least one opposing argument indicates that the at least one query triplet is false. The method further includes assigning the at least one query triplet to the at least one respective class using supervised machine learning depending on the at least two arguments.

Abstract: A computer-implemented method for generating an adapted task graph, including the steps of providing a first input data set with at least one task graph and at least one task context and/or a second input data set with at least one constraint and at least one task context, generating an adapted task graph using a trained neural network based on the first input data set and/or the second input data set, and providing the adapted task graph.

Abstract: Provided is a computer implemented method for providing an agent for creating a graph neural network architecture, which is suitable for providing a prediction of at least one indicator of a complex system and to a computer implemented method for providing such a graph neural network architecture by an agent. Also provide is an agent and a unit for providing an agent a computer program product and computer readable storage media.

Abstract: Provided is an assistance apparatus for localizing errors in a monitored technical system consisting of devices and/or transmission lines, including at least one processor configured to obtain values of actual attributes of the devices and/or of the transmission lines, determine an error probability for each device and/or transmission line by processing a graph neural network with the obtained actual values of attributes as input, wherein the graph neural network is trained by training attributes assigned to an attributed graph representation of the technical system, and output an indication for such devices and/or transmission lines, whose error probability is higher than a predefined threshold.

Abstract: The monitoring of a technical system using sensor data. In the event of the failure of a sensor, in this case, for the failed sensor, virtual sensor data are created on the basis of the remaining functional sensors. In this case, the sensors for the calculation of the virtual sensor data are selected in two stages. In a first step, firstly, possible candidates of sensors are ascertained on the basis of a knowledge-based approach and the topology of the system. A second step involves calculating a mathematical relationship between the sensor data of a faulty sensor and the possible candidates of sensors for the calculation of the virtual sensor data. Those sensors which form a suitable basis for the calculation of the virtual sensor data can be identified in this way.

Abstract: A computer implemented method for providing a service for a complex industrial system, the method including the steps of providing Bill of Materials, BoM, trees of system component instances of said complex industrial system; generating automatically a unified BoM data model by clustering matching nodes within the provided BoM trees; and performing the service for the complex industrial system based on the generated unified BoM data model is provided.

Abstract: A method and an apparatus for operating an automation system is provided. The method for operating an automation system includes the method steps of: providing a learning-based prediction model for the automation system trained by process data including context of an automation process, receiving information about current context of the automation process, verifying context change by comparing the current context to the context of said process data, in the case of any context change verifying a concept drift by comparing pre-drift process data and post-drift process data, in the case of any concept drift re-training said model with post-drift process data, in the case of no context change testing for random concept drift not detected by verifying context change, in the case of any random concept drift extend the current context by using data comprising previous context changes, otherwise no further method steps are required.

Abstract: A method for generating graph-structured representations of a brownfield system including collecting training data of training systems. Training data includes training pairs, with each training pair including training sensor observations and a training digital twin model. The method includes transforming the training digital twin models into training graph-structured representations. The training graph-structured representations include nodes and links. The nodes represent components of the training system and the links represent relations between the components of the training system. A graph generative model is trained to generate graph-structured representations of the brownfield system using the training sensor observations and the training graph-structured representations of the training digital twin models. Graph-structured representations of the brownfield system are generated using the trained graph generative model and sensor observations of the brownfield system.

Abstract: The monitoring of a technical system using sensor data. In the event of the failure of a sensor, in this case, for the failed sensor, virtual sensor data are created on the basis of the remaining functional sensors. In this case, the sensors for the calculation of the virtual sensor data are selected in two stages. In a first step, firstly, possible candidates of sensors are ascertained on the basis of a knowledge-based approach and the topology of the system. A second step involves calculating a mathematical relationship between the sensor data of a faulty sensor and the possible candidates of sensors for the calculation of the virtual sensor data. Those sensors which form a suitable basis for the calculation of the virtual sensor data can be identified in this way.

Abstract: A control apparatus of an automation system, the control apparatus includes a database adapted to store time series data in a historian data source and adapted to store events derived from the time series data based on event detection rules in an event data source, wherein a semantic data or event query received by the control apparatus is mapped to a corresponding data source of the database to retrieve the queried data or event which are contextualized using an ontological context model of the automation system stored in the database and output by control apparatus in a semantic format is provided.

Abstract: In a monitoring phase, live instance vectors including data from all devices of a manufacturing system are acquired. A constraint-based clustering algorithm assigns each live instance vector to a cluster, thereby forming a live sequence of clusters. The live sequence is classified based on at least one behavior model. An anomaly is detected depending on the classification result. Each cluster represents a state of the manufacturing system. The sequences of clusters can be generated by consecutive operations that are performed in the manufacturing system. The constraint-based clustering algorithm facilitates an unsupervised (automated) or semi-supervised learning of system behavior that may be supplemented with supervised or unsupervised learning of the behavior models. The method provides a way of automated learning of discrete event dynamic systems from data generated by sensors and actuators without requiring manual input.

Abstract: A method and an apparatus for operating an automation system is provided. The method for operating an automation system includes the method steps of: providing a learning-based prediction model for the automation system trained by process data including context of an automation process, receiving information about current context of the automation process, verifying context change by comparing the current context to the context of said process data, in the case of any context change verifying a concept drift by comparing pre-drift process data and post-drift process data, in the case of any concept drift re-training said model with post-drift process data, in the case of no context change testing for random concept drift not detected by verifying context change, in the case of any random concept drift extend the current context by using data comprising previous context changes, otherwise no further method steps are required.

Abstract: A control apparatus of an automation system, the control apparatus includers a database adapted to store time series data in a historian data source and adapted to store events derived from the time series data based on event detection rules in an event data source, wherein a semantic data or event query received by the control apparatus is mapped to a corresponding data source of the database to retrieve the queried data or event which are contextualized using an ontological context model of the automation system stored in the database and output by said-control apparatus in a semantic format is provided.

Abstract: In the method for modeling a technical system, a semantic system model of the technical system is generated and the dependencies inside the system model are analyzed by a dependency analysis based on properties of the semantic system model.