Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020193148 - MACHINE CONTROL BASED ON AUTOMATED LEARNING OF SUBORDINATE CONTROL SKILLS

Publication Number WO/2020/193148
Publication Date 01.10.2020
International Application No. PCT/EP2020/056558
International Filing Date 11.03.2020
IPC
F02C 9/00 2006.01
FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
02COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
CGAS-TURBINE PLANTS; AIR INTAKES FOR JET-PROPULSION PLANTS; CONTROLLING FUEL SUPPLY IN AIR-BREATHING JET-PROPULSION PLANTS
9Controlling gas-turbine plants; Controlling fuel supply in air-breathing jet-propulsion plants
G05B 13/02 2006.01
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
F02C 9/00
FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
02COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
CGAS-TURBINE PLANTS; AIR INTAKES FOR JET-PROPULSION PLANTS; CONTROLLING FUEL SUPPLY IN AIR-BREATHING JET-PROPULSION PLANTS
9Controlling gas-turbine plants; Controlling fuel supply in air- breathing jet-propulsion plants
F05D 2270/082
FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
05INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
DINDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
2270Control
01Purpose of the control system
08to produce clean exhaust gases
082with as little NOx as possible
F05D 2270/44
FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
05INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
DINDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
2270Control
40Type of control system
44active, predictive, or anticipative
F05D 2270/71
FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
05INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
DINDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
2270Control
70Type of control algorithm
71synthesized, i.e. parameter computed by a mathematical model
G05B 13/027
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
027using neural networks only
Applicants
  • SIEMENS AKTIENGESELLSCHAFT [DE]/[DE]
Inventors
  • HEIN, Daniel
  • MOSANDL, Judith
  • UDLUFT, Steffen
  • WEBER, Marc Christian
Priority Data
19165521.627.03.2019EP
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) MACHINE CONTROL BASED ON AUTOMATED LEARNING OF SUBORDINATE CONTROL SKILLS
(FR) COMMANDE DE MACHINE BASÉE SUR L'APPRENTISSAGE AUTOMATISÉ DE COMPÉTENCES DE COMMANDE SUBORDONNÉES
Abstract
(EN)
Machine control based on automated learning of subordinate control skills For controlling a machine (100) according to multiple control objectives, a device (200) provides multiple subordinate control skills (221, 222, 223, 224, 225), each of the control skills being assigned to a different one of the multiple control objectives. Further, the device (200) provides multiple learning processes (211, 212, 213, 214, 215), in particular reinforcement learning (RL) processes. Each of the learning processes (211, 212, 213, 214, 215) is assigned to a different one of the multiple control objectives and being configured to optimize the corresponding subordinate control skill (221, 222, 223, 224, 225) based on input data received from the machine (100). Further, the device (200) is configured to determine a superordinate control skill (240) based on the subordinate control skills (221, 222, 223, 224, 225) and to control the machine (100) based on the superordinate control skill.
(FR)
La présente invention concerne une commande de machine basée sur l'apprentissage automatisé de compétences de commande subordonnées. Pour commander une machine (100) selon de multiples objectifs de commande, un dispositif (200) fournit de multiples compétences de commande subordonnées (221, 222, 223, 224, 225), chacune des compétences de commande étant attribuée à un objectif différent parmi les multiples objectifs de commande. En outre, le dispositif (200) fournit de multiples processus d'apprentissage (211, 212, 213, 214, 215), en particulier des processus d'apprentissage de renfort (RL). Chacun des processus d'apprentissage (211, 212, 213, 214, 215) est attribué à un objectif différent parmi les multiples objectifs de commande et est conçu pour optimiser la compétence de commande subordonnée (221, 222, 223, 224, 225) correspondante sur la base de données d'entrée reçues en provenance de la machine (100). En outre, le dispositif (200) est conçu pour déterminer une compétence de commande superordonnée (240) sur la base des compétences de commande subordonnées (221, 222, 223, 224, 225) et pour commander la machine (100) sur la base de la compétence de commande superordonnée.
Also published as
Latest bibliographic data on file with the International Bureau