Siemens Aktiengesellschaft

Siemens Energy Global Gmbh & Co. Kg

Siemens Aktiengesell Schaft

Denis Krompaß

Sigurd Spieckermann

Hans-Georg Köpken

Volker Tresp

Silvio Becher

Dagmar Beyer

Andreas Litzinger

Sebnem Rusitschka

Thomas Hubauer

Mikhail Roshchin

Ulrich Münz

Felix Buggenthin

Bernt Andrassy

Giuseppe Fabio Ceschini

Mark Buckley

Davood Naderi

Richard Arnatt

Michael Werner

Zlatan Cota

Almir Avdovic

Tomislav Tomov

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.

Methods for building a deep latent feature extractor for industrial sensor data

A method and an apparatus for optimizing diagnostics of rotating equipment is provided. The apparatus includes a device for providing status information about status of the rotating equipment over a series of time windows whereby status can be derived from sensor features of at least one available sensor taking measurements during a predefinable time period, a device for using deep learning which combines provided historic sensor information with sequence of events data indicating warnings and/or alerts of the rotating equipment, whereby status information is supplemented with via deep learning predicted probabilities whether a warning and/or an alert has occurred within a time window, device for providing an amount of textual diagnostic knowledge cases, device for extracting semantic information on text features from the textual diagnostic knowledge cases, and device for combining status information and semantic information into a unified representation enabling optimization of the diagnostics.

Method and apparatus for optimizing diagnostics of rotating equipment

A monitoring system for recognizing a contingency in a power supply network including in-field measurement devices adapted to generate measurement data of the power supply network and a processing unit adapted to process the measurement data generated by the in-field measurement devices of the power supply network by using a local network state estimation model to calculate local network state profiles used to generate a global network state profile, wherein the processing unit is further adapted to process the measurement data generated by the in-field measurement devices of the power supply network to provide a relevance profile including for the in-field measurement devices a relevance distribution indicating a probability where the origin of a contingency within the power supply network.

Method for recognizing contingencies in a power supply network

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.

Data driven method for automated detection of anomalous work pieces during a production process

A monitoring system includes in-field measurement devices adapted to generate measurement data of a power supply network, and a processing unit adapted to process the measurement data using a local network state estimation model to calculate local network state profiles used to generate a global network state profile. The processing unit is adapted to process the measurement data to provide a relevance profile comprising, for the in-field measurement devices, a relevance distribution indicating a probability where an origin of a contingency within the power supply network resides. The processing unit is adapted to compute a similarity between a candidate contingency profile formed by the generated global network state profile and by the calculated relevance profile and reference contingency profiles stored in a reference contingency database of the monitoring system to identify a reference contingency profile having a highest computed similarity as a recognized contingency within the power supply network.

A method for operating a network, such as an automation network, for example, has multiple node devices provided that are networked to one another. There is a global time available, and the node devices record their operating parameters. The operating parameters are allocated to a respective address element as content elements in order to be stored in a tensorial database structure. Control or adaptation of the operation of the network with its node devices and couplings is facilitated thereby. The method is suitable particularly for use in supply networks, automated production installations, communication networks, transport networks and logistical networks. The proposed storing allows easy visualisation, depiction and evaluation of operating states of the network and of its node devices.

Method for operating a network having multiple node devices, and network

A method for identifying automatically an inner node within a hierarchical network causing an outage of a group of leaf nodes at the lowest hierarchical level, the method including providing an outage state matrix representing an outage state of leaf nodes at the lowest hierarchical level; decomposing the state matrix into a first probability matrix indicating for each inner node the probability that the inner node forms the origin of an outage at the lowest hierarchical level of the hierarchical network and into a second probability matrix indicating for each leaf node at the lowest hierarchical level of the hierarchical network the probability that an inner node forms a hierarchical superordinate node of the respective leaf node at the lowest hierarchical level of the hierarchical network and evaluating the first probability matrix to identify the inner node having caused the outage of the group of leaf nodes.

Method and apparatus for automatic identification of an outage of a network node

A method and apparatus for determining a network topology of a hierarchical network, the apparatus including: a memory unit to store an outage state matrix representing an outage state of leaf nodes at the lowest hierarchical level of the hierarchical network; and a processing unit to decompose the stored state matrix into a first probability matrix indicating for each inner node of the hierarchical network the probability that the respective inner node forms the origin of an outage at the lowest hierarchical level of the hierarchical network and into a second probability matrix indicating for each leaf node at the lowest hierarchical level of the hierarchical network the probability that an inner node forms a hierarchical superordinate node of the respective leaf node at the lowest hierarchical level of the hierarchical network, wherein the decomposed second probability matrix is evaluated by the processing unit to determine the network topology.

Method and apparatus for determining a network topology of a hierarchical network

A method and apparatus for automatic recognition of similarities between perturbations in a network, the apparatus includes a memory unit for storing a first data array of multiple perturbation data snapshots each recorded in response to a perturbation observed in the network; a generation unit adapted to generate by machine learning a data model of perturbations trained on the first data array, wherein the trained data model provides a latent vector representation for each of the perturbations; a recording unit adapted to record a perturbation data snapshot if a perturbation is observed during operation of said network and adapted to provide a corresponding second data array for the recorded perturbation data snapshot; and a processing unit adapted to derive a latent vector representation for the observed perturbation from the second data array using the trained data model of perturbations.

Growing community of inventors

Munich, Germany

Denis Krompaß