Processing

Please wait...

Settings

Settings

Goto Application

1. EP3587046 - METHOD AND DEVICE FOR THE COMPUTER-AIDED DETERMINATION OF CONTROL PARAMETERS FOR FAVOURABLE HANDLING OF A TECHNICAL SYSTEM

Office
European Patent Office
Application Number 18180479
Application Date 28.06.2018
Publication Number 3587046
Publication Date 01.01.2020
Publication Kind A1
IPC
B25J 9/16
BPERFORMING OPERATIONS; TRANSPORTING
25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; HANDLES FOR HAND IMPLEMENTS; WORKSHOP EQUIPMENT; MANIPULATORS
JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
9Programme-controlled manipulators
16Programme controls
G05B 13/02
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
13Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
02electric
CPC
B25J 9/1671
BPERFORMING OPERATIONS; TRANSPORTING
25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
9Programme-controlled manipulators
16Programme controls
1656characterised by programming, planning systems for manipulators
1671characterised by simulation, either to verify existing program or to create and verify new program, CAD/CAM oriented, graphic oriented programming systems
G05B 2219/39406
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
2219Program-control systems
30Nc systems
39Robotics, robotics to robotics hand
39406Obtain optimal parameters of model of system
G05B 2219/40494
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
2219Program-control systems
30Nc systems
40Robotics, robotics mapping to robotics vision
40494Neural network for object trajectory prediction, fuzzy for robot path
B25J 9/163
BPERFORMING OPERATIONS; TRANSPORTING
25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
9Programme-controlled manipulators
16Programme controls
1628characterised by the control loop
163learning, adaptive, model based, rule based expert control
G05B 13/0265
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
13Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
02electric
0265the criterion being a learning criterion
G05B 13/042
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
13Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
02electric
04involving the use of models or simulators
042in which a parameter or coefficient is automatically adjusted to optimise the performance
Applicants SIEMENS AG
Inventors BISCHOFF MARTIN
TOKIC MICHEL
Designated States
Priority Data 18180479 28.06.2018 EP
Title
(DE) VERFAHREN UND VORRICHTUNG ZUM RECHNERGESTÜTZTEN ERMITTELN VON REGELPARAMETERN FÜR EINE GÜNSTIGE HANDLUNG EINES TECHNISCHEN SYSTEMS
(EN) METHOD AND DEVICE FOR THE COMPUTER-AIDED DETERMINATION OF CONTROL PARAMETERS FOR FAVOURABLE HANDLING OF A TECHNICAL SYSTEM
(FR) PROCÉDÉ ET APPAREIL DE DÉTERMINATION PAR ORDINATEUR DES PARAMÈTRES DE RÉGLAGE POUR UNE ACTION FAVORABLE D'UN SYSTÈME TECHNIQUE
Abstract
(DE) Die Erfindung betrifft ein Verfahren und eine Vorrichtung zum rechnergestützten Ermitteln von Regelparametern für eine günstige Handlung eines technischen Systems. Mittels mindestens eines Sensors (101) wird ein Ausgangszustand (AZ) und eine Umgebung (UM) des technischen Systems (TS) erfasst und damit ein physikalisches Simulationsmodell (SIM) des technischen Systems erstellt. Mittels des Simulationsmodells (SIM) und ausgehend vom Ausgangszustand (AZ) und in Bezug auf einen vorgegebenen Zielzustand (ZZ), werden verschiedene Kombinationen aus Handlungsschritten des technischen Systems (TS) simuliert, wobei Regelparameter des technischen Systems zum Ausführen der Handlungsschritte variiert werden. Anhand der Simulationsdaten und mittels einer Bewertung eines jeweiligen Handlungsschrittes wird eine maschinelle Lernroutine trainiert und mit der trainierten maschinellen Lernroutine eine optimierte Kombination aus Handlungsschritten ermittelt. Die Regelparameter der optimierten Kombination aus Handlungsschritten werden zum Steuern des technischen Systems (TS) ausgegeben.