Siemens Aktiengesellschaft

Martin Ringsquandl

Steffen Lamparter

Thomas Hubauer

Mikhail Roshchin

Stephan Grimm

Mitchell Joblin

Raffaello Lepratti

Serghei Mogoreanu

Rakebul Muff Hasan

Marcel Hildebrandt

Swathi Shyam Sunder

Mark Buckley

Johannes Maderspacher

Aneta Koleva

Chandra Sekhar Akella

Anna Himmelhuber

Yushan Liu

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, u. 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.

Method and system for semi-automatic completion of an engineering project

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. This unsupervised approach is more suitable for industrial scenarios where labeled data is expensive to create.

Method and system for restoring consistency of a digital twin database

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.

Method and system for automated column type annotation

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.

Monitoring apparatus and method for monitoring a system

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.

Method and apparatus for operating an automation system and accounting for concept drift

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.

Control apparatus of an automation system

Growing community of inventors

Traunstein, Germany

Martin Ringsquandl