-
公开(公告)号：US20240345549A1
公开(公告)日：2024-10-17
申请号：US18294408
申请日：2021-08-18
Applicant: Siemens Aktiengesellschaft
Inventor： Dirk Hartmann , Amit Pandey , Suat Gumussoy , Ulrich Muenz
IPC: G05B13/02
CPC classification number: G05B13/027
Abstract: A method for configuring a controller of a dynamical system includes obtaining a control data manifold formed by a plurality of stored control points, each representative of a state signal specifying a state of the dynamical system and an assigned control signal. Each state signal is mapped to a multi-dimensional state space. The assigned control signal is generated by a first control algorithm as a function of the state signal. The method includes detecting patches on the control data manifold by identifying control points on the control data manifold that belong to a common local approximation function, and training a classifier to classify control points into different patches. The method further includes training a respective regression model for each detected patch for approximating a relationship between state signals and the control signals in that patch, to create an explicit rule-based control algorithm.
-
公开(公告)号：US20240176310A1
公开(公告)日：2024-05-30
申请号：US18552514
申请日：2022-03-17
Applicant: Siemens Aktiengesellschaft
Inventor： Theodoros Papadopoulos , Felix Köhler , Dirk Hartmann
IPC: G05B13/02
CPC classification number: G05B13/0265
Abstract: To configure a machine controller for a machine, a plurality of state signals of a first state space is read in, each state signal being assigned an optimized control signal. Using the state signals, a first signal converter is trained to convert state signals from the first state space into a second state space which is dimension-reduced in comparison with the first state space. A second signal converter is trained to reproduce corresponding optimized control signals by converting reduced state signals by means of the conversion rule. Thus, the machine controller is designed to convert a state signal of the machine into a reduced state signal by means of the trained first signal converter and to convert the reduced state signal into an optimized control signal by means of the trained second signal converter, the optimized control signal being used to control the machine.
-
公开(公告)号：US11551037B2
公开(公告)日：2023-01-10
申请号：US16388958
申请日：2019-04-19
Applicant: Siemens Aktiengesellschaft
Inventor： Stefan Gavranovic , Dirk Hartmann
Abstract: Provided is a method for determining a physical shape having a predefined physical target property that includes calculating a sensitivity landscape on the basis of a shape data record for the physical shape with the aid of a calculation device. The calculation device is a machine-taught artificial intelligence device. The shape data record identifies locations at or on the physical shape. For a plurality of these locations, the sensitivity landscape respectively indicates how the target property of the physical shape changes if the physical shape changes in the region of the location. Furthermore, the shape data record for the physical shape to be determined is changed on the basis of the sensitivity landscape in such a manner that the predefined physical target property is improved.
-
公开(公告)号：US20190031204A1
公开(公告)日：2019-01-31
申请号：US15963240
申请日：2018-04-26
Applicant: Siemens Aktiengesellschaft
Inventor： Dirk Hartmann , Birgit Obst , Erik Olof Johannes Wannerberg
Abstract: A method for performing an optimized control of a complex dynamical system using machine learned, scenario based control heuristics including: providing a simulation model for predicting a system state vector of the dynamical system in time based on a current scenario parameter vector and a control vector; using a Model Predictive Control, MPC, algorithm to provide the control vector during a simulation of the dynamical system using the simulation model for different scenario parameter vectors and initial system state vectors; calculating a scenario parameter vector and initial system state vector a resulting optimal control value by the MPC algorithm; generating machine learned control heuristics approximating the relationship between the corresponding scenario parameter vector and the initial system state vector for the resulting optimal control value using a machine learning algorithm; and using the generated machine learned control heuristics to control the complex dynamical system modelled by the simulation model.
-
公开(公告)号：US11567470B2
公开(公告)日：2023-01-31
申请号：US17310300
申请日：2019-12-17
Applicant: Siemens Aktiengesellschaft
Inventor： Dirk Hartmann , David Bitterolf , Hans-Georg Köpken , Birgit Obst , Florian Ulli Wolfgang Schnös , Sven Tauchmann
IPC: G05B19/402 , G05B19/31
Abstract: In order to be able to take into account machining configurations more flexibly, a method for optimizing numerically controlled machining of a workpiece includes ascertaining geometric interaction data. A relationship between a force to be expected and a configuration parameter of the machining is determined on the basis of the interaction data. The force is calculated during the machining on the basis of the relationship and a current value of the at least one configuration parameter. The machining is adapted depending on the calculated force.
-
Patent Agency Ranking
公开(公告)号：US20220382265A1
公开(公告)日：2022-12-01
申请号：US17775839
申请日：2020-11-18
Applicant: Siemens Aktiengesellschaft
Inventor： Dirk Hartmann , Michael Jaentsch , Tobias Kamps , Birgit Obst , Daniel Regulin , Florian Ulli Wolfgang Schnös , Sven Tauchmann
IPC: G05B19/418
Abstract: A method for operating a numerical controlled machine comprising receiving a sequence of control commands which, when executed by a numerical controlled machine, cause the numerical controlled machine to machine a workpiece to obtain a predetermined workpiece geometry, wherein the sequence of control commands includes while machining the workpiece based on the received sequence of control commands measuring a value of a first interaction parameter for a first position of the tool, comparing a measured value of the first interaction parameter for the first position of the tool with the simulated value of the first interaction parameter for the first position of the tool, and determining an adapted value of the second interaction parameter for a following position of the tool based on a result of the comparison.
-
公开(公告)号：US20220284153A1
公开(公告)日：2022-09-08
申请号：US17632481
申请日：2019-08-28
Applicant: SIEMENS AKTIENGESELLSCHAFT , Siemens Industry Software Inc.
Inventor： Stefan Gavranovic , Suraj Ravi Musuvathy , Dirk Hartmann , Peter Nanson , Richard Collins , Hiren Dedhia
Abstract: A computing system may include a geometry access engine configured to access geometries associated with a topology optimization process, including an original geometry that represents a design space upon which the topology optimization process applies to as well as a topology optimized geometry that represents an output of the topology optimization process performed for the original geometry. The system may also include geometry processing engine configured to generate a final geometry from the topology optimized geometry, including by conforming the topology optimized geometry to the original geometry at portions of the topology optimized geometry that correspond to fixed regions of the original geometry as well as smoothing the topology optimized geometry at portions that correspond to non-fixed regions of the original geometry.
-
8.发明申请公开(公告)号：US20220250324A1
公开(公告)日：2022-08-11
申请号：US17622264
申请日：2020-05-15
Applicant: Siemens Aktiengesellschaft
Inventor： Meinhard Paffrath , Dirk Hartmann , Christoph Kiener
Abstract: To separate excess material, the component moved by a movement device that is controlled by movement data, and a fill level of the component with material is measured. A process for emptying material from the component simulated for each different initial fill level with material, wherein movement data, which specify a simulated movement of the component, and a simulated fill level progression resulting from the simulated movement are assigned to the associated initial fill level. In addition, a corresponding initial fill level is selected in accordance with the measured fill level, and the movement device is controlled by movement data which are assigned to the selected initial fill level. The fill level is measured and compared to a simulated fill level progression assigned to the selected initial fill level. The steps of selecting a corresponding initial fill level (SAFG) and controlling the movement device (BV) are carried out.
-
公开(公告)号：US10953891B2
公开(公告)日：2021-03-23
申请号：US15963240
申请日：2018-04-26
Applicant: Siemens Aktiengesellschaft
Inventor： Dirk Hartmann , Birgit Obst , Erik Olof Johannes Wannerberg
Abstract: A method using machine learned, scenario based control heuristics including: providing a simulation model for predicting a system state vector of the dynamical system in time based on a current scenario parameter vector and a control vector; using a Model Predictive Control, MPC, algorithm to provide the control vector during a simulation of the dynamical system using the simulation model for different scenario parameter vectors and initial system state vectors; calculating a scenario parameter vector and initial system state vector a resulting optimal control value by the MPC algorithm; generating machine learned control heuristics approximating the relationship between the corresponding scenario parameter vector and the initial system state vector for the resulting optimal control value using a machine learning algorithm; and using the generated machine learned control heuristics to control the complex dynamical system modelled by the simulation model.
-
公开(公告)号：US20190325270A1
公开(公告)日：2019-10-24
申请号：US16388958
申请日：2019-04-19
Applicant: Siemens Aktiengesellschaft
Inventor： Stefan Gavranovic , Dirk Hartmann
Abstract: Provided is a method for determining a physical shape having a predefined physical target property that includes calculating a sensitivity landscape on the basis of a shape data record for the physical shape with the aid of a calculation device. The calculation device is a machine-taught artificial intelligence device. The shape data record identifies locations at or on the physical shape. For a plurality of these locations, the sensitivity landscape respectively indicates how the target property of the physical shape changes if the physical shape changes in the region of the location. Furthermore, the shape data record for the physical shape to be determined is changed on the basis of the sensitivity landscape in such a manner that the predefined physical target property is improved.
-
-
-
-
-
-
-
-
-
Search Results
18
records
(took 0.012 seconds)
