Siemens Aktiengesellschaft

Agfa Healthcare Nv

Yunex Gmbh

Bayerische Motoren Werke Aktiengesellschaft

Siemens Gamesa Renewable Energy A/s

B Ayerische M Otoren W Erke a Ktiengesellschaft

Korber Supply Chain Logistics Gmbh

Siemens Mobility Gmbh

Marc Christian Weber

Steffen Udluft

Clemens Otte

Siegmund Düll

Robert Fasbender

Georg Reiser

Kai Heesche

Ralph Thoma

Andreas Bode

Daniel Hein

Stefan Stallmeister

Stephan Baunach

Heike Minwegen

Rupert Dedler

Manfred Baldauf

Volkmar Sterzing

Thomas A Runkler

Arno Arzberger

Michel Tokic

Harald Frank

Frank Steinbacher

Per Egedal

Peder Bay Enevoldsen

Gurdev Dave Singh

Raymond Scott Nordlund

Alexander Hentschel

Gerhard Hofer

Michael Zettler

Stefan Depeweg

Ruediger Kutzner

Thomas Runkler

Holger Schöner

Rüdiger Kutzner

Markus Kaiser

Jonas Witt

Judith Mosandl

Martin Schall

Frank Pfeiffer

Armin Hirn

Angelika Winkler

Gunnar Stoelben

Philipp Hutterer

Andrew Palmer

Siegmund DÜLL

Raymond S Nordlund

A computer-implemented method, a device for data processing and a computer system for controlling a control device of a conveyor system to achieve an alignment and/or a defined spacing of piece goods, wherein the control of the control device is determined by an agent acting according to Reinforcement Learning methods. An individual, local state vector of predefined dimension that is the same for all the piece goods is created for each of the piece goods and an action vector is selected from an action space according to a strategy that is the same for all piece goods for the current state vector of this piece good. These action vectors are projected onto the conveying elements, wherein conflicts are resolved. After a cycle time has elapsed, state vectors are created again for each piece good and evaluated with rewards and the strategy is adjusted.

Computer-implemented method, apparatus for data processing, and computer system for controlling a control device of a conveyor system

Method and apparatus for industrial scale production of a suspension for a battery, wherein an input material is processed via ball milling in a rotating chamber of a device that is effected as a continuous process with a continuously controlled addition of the input material and with a continuously controlled delivery of the processed output material, where state parameters of the input material and process parameters of the manufacturing installation are acquired as first parameters during production of the suspension, results of laboratory analyses about the state or quality of the manufactured suspension are acquired as second parameters in a learning phase during production, the first and the second parameters are used in the learning phase for training a model for predicting the state or quality via machine learning, and where the device is open-loop or closed-loop controlled outside the learning phase via the first parameters and the trained model.

Method and arrangement for industrial scale production of a suspension for a battery

A controller for a technical system is trained using a machine learning method. For this purpose, a chronological sequence of training data is detected for the machine learning method, the training data including both state data as well as control action data of the technical system. A change in the control action data over time is detected specifically and correlated with changes in the state data over time within different time windows, wherein a time window-specific correlation value is ascertained in each case. A resulting time window is then ascertained on the basis of the ascertained correlation values, and the training data which is found within the resulting time window is extracted in a time window-specific manner. The controller is trained by means of the machine learning method using the extracted training data and thereby configured to control the technical system.

Controller for controlling a technical system, and method for configuring the controller

A technical system controller is trained using a machine learning method. For this purpose, a chronological sequence of training data is detected for the machine learning method. The training data includes state data, which specifies states of the technical system, and control action data, which specifies control actions of the technical system. A chronological sequence of control action data is extracted specifically from the training data and is checked for a change over time. If a change over time is ascertained, a time window including the change is ascertained, and training data which can be found within the time window is extracted in a manner which is specific to the time window. The controller is then trained by the machine learning method using the extracted training data and is thus configured for controlling the technical system.

Real state information, which influences the switching times of a light signal system, is supplied as input signals to a first neural network in a fixed time cycle. The first neural network calculates estimated state information as a replacement for real state information or parts of the real state information which are not received in good time or are received incorrectly in the fixed time cycle. This estimated state information is output to artificial intelligence which predicts the switching times. The first neural network allows the artificial intelligence to also make good predictions for the switching times of signal groups when one of the many communication paths involved fails or is overloaded. It is therefore possible to predict signal group states in the fixed time cycle in real time with a high degree of robustness and tolerance with respect to gaps in the time cycle of the real state information provided.

Method and arrangement for predicting switching times of a signal group of a signal installation for controlling a flow of traffic

Various embodiments include a method for producing a quality test system executing a quality test model with a filter mask and a quality model to determine a quality feature of a battery cell. The system has an electrochemical impedance spectroscopic unit for capturing test data relating to the battery within a frequency range. The method includes: creating the model; and producing the system. Creating the model includes: capturing spectroscopic learning data; creating the filter mask using a first machine learning method with analysis data from part of the frequency range by consulting the filter mask and creating the model using a second machine learning method. The first and the second learning method are coupled based on the learning data. The first machine learning method creates a filter mask determining the analysis data such that the second machine learning method creates a quality model optimized with respect to maximizing the quality.

Production of a quality test system

Method and device for controlling a machine in accordance with to multiple control objectives in which machine control is based on automated learning of subordinate control skills, wherein the device provides multiple subordinate control skills which are each assigned to a different one of the multiple control objectives, the device provides multiple learning processes that are reinforcement learning processes that are each assigned to a different one of the multiple control objectives and are configured to optimize the corresponding subordinate control skill based on input data received from the machine, and where the device is configured to determine a superordinate control skill based on the subordinate control skills and to control the machine based on the superordinate control skill.

Machine control based on automated learning of subordinate control skills

A computer-implemented method for determining at least one remaining time value, to be determined, for a system is provided, having the following steps: a. providing at least one known input data record containing a multiplicity of input elements for at least one determined time; b. providing at least one associated known remaining time value for the at least one input data record; c. determining the at least one remaining time value to be determined by applying an error function to the at least one input data record and the at least one associated remaining time value; and d. providing an output data record containing the at least one determined remaining time value and an associated reliability value. The invention furthermore targets a corresponding determination unit and computer program product.

Method for determining at least one remaining time value, to be determined, for a system

For reducing oscillations in a technical system plurality of different controller settings for the technical system is received. For a respective controller setting signal representing a time series of operational data of the technical system controlled by the respective controller setting is received, the signal is processed, whereby the processing includes a transformation into a frequency domain, and an entropy value of the processed signal is determined. Depending on the determined entropy values a controller setting from the plurality of controller settings is selected, and the selected controller setting is output for configuring the technical system.

Method, controller, and computer product for reducing oscillations in a technical system

Provided is an apparatus and method for cooperative controlling wind turbines of a wind farm, wherein the wind farm includes at least one pair of turbines aligned along a common axis approximately parallel to a current wind direction and having an upstream turbine and a downstream turbine. The method includes the steps of: a) providing a data driven model trained with a machine learning method and stored in a database, b) determining a decision parameter for controlling at least one of the upstream turbine and the downstream turbine by feeding the data driven model with the current power production of the upstream turbine which returns a prediction value indicating whether the downstream turbine will be affected by wake, and/or the temporal evolvement of the current power production of the upstream turbine; c) based on the decision parameter, determining control parameters for the upstream turbine and/or the downstream turbine.

Method and apparatus for cooperative controlling wind turbines of a wind farm

A method of controlling a complex system and a gas turbine being controlled by the method are provided. The method comprises providing training data, which training data represents at least a portion of a state space of the system; setting a generic control objective for the system and a corresponding set point; and exploring the state space, using Reinforcement Learning, for a control policy for the system which maximizes an expected total reward. The expected total reward depends on a randomized deviation of the generic control objective from the corresponding set point.

Randomized reinforcement learning for control of complex systems

A panel assembly for a motor vehicle includes a first panel element and a second panel element that is connected to the first panel element. The first panel element has a fastening extension that is connected to a receiving section on the second panel element by way of a connector. The fastening extension further has a latch that is to interlock with a locking opening in the receiving section of the second panel element.

Panel assembly for a motor vehicle

A cladding assembly for a motor vehicle, in particular for a motorcycle or a motorcycle-like motor vehicle, has at least two flat cladding elements. The first cladding element has a first exterior, and the second cladding element has a second exterior which form at least one part of an outer cladding of the motor vehicle in the assembled state and which are arranged adjacently and are separated from each other by a joint. The first cladding element has a transition section which is angled by a first angle relative to the first exterior and at least one first end of the first cladding element extends below the second cladding element. The second cladding element has a bevel which is formed parallel to the transition section at a second end facing the transition section.

Cladding assembly for a motor vehicle

A measuring system for continuously monitoring a high-voltage bushing provides for multi-stage, secure protection. The system includes a measuring circuit, a connection plug, a connection cable, and a three-stage protective circuit. When overvoltages occur at the measurement connection, each protective stage can produce a short circuit at the measurement connection to limit the voltage. A first protective stage responds at a response voltage U. A second protective stage connected between the first stage and the measurement connection responds at a higher response voltage U. A low-pass filter in the first protective stage decouples the first and second protective stages. The first stage responds to overvoltages at operating frequency, the second stage responds to high-frequency overvoltages. A third protective stage is connected between the measurement connection and the first protective stage in parallel with the measurement connection and includes a mechanical switch for short-circuiting when a third response voltage is present.

Measuring system for continuously monitoring a high-voltage bushing

An apparatus () for erasing a storage phosphor layer () includes a drive () for producing a relative movement between the storage phosphor layer () and the radiation source (), the storage phosphor layer () lying or being moved in a holding plane (), and a reflector () for reflecting radiation. The reflector () is arranged and designed to reflect erasing radiation reflected by the storage phosphor layer () in the direction of the storage phosphor layer (). A width () of the reflector () in the direction () of the relative movement is at least ten times as great as a smallest distance () between the reflector () and the holding plane ().

Storage phosphor layer and system and method for erasing same

Growing community of inventors

Munich, Germany

Marc Christian Weber