EP 4111382 A1 20230104 - CONTROL DEVICE FOR CONTROLLING A TECHNICAL SYSTEM, AND METHOD FOR CONFIGURING THE CONTROL DEVICE
Title (en)
CONTROL DEVICE FOR CONTROLLING A TECHNICAL SYSTEM, AND METHOD FOR CONFIGURING THE CONTROL DEVICE
Title (de)
STEUEREINRICHTUNG ZUM STEUERN EINES TECHNISCHEN SYSTEMS UND VERFAHREN ZUM KONFIGURIEREN DER STEUEREINRICHTUNG
Title (fr)
DISPOSITIF DE COMMANDE POUR COMMANDER UN SYSTÈME TECHNIQUE ET PROCÉDÉ POUR CONFIGURER LE DISPOSITIF DE COMMANDE
Publication
Application
Priority
- EP 20168995 A 20200409
- EP 2021059262 W 20210409
Abstract (en)
[origin: WO2021204983A1] The invention relates to a time sequence of control signals (CS) and a time sequence of measured status data (SD) of the technical system (TS). The time sequence of the control signals (CS) is fed into a neural network (NN), and output data (PD) of the neural network (NN) is fed into the simulation module (SIM) as simulation input data. Using the simulation module (SIM), based on the output data (PD) of the neural network (NN), a physical simulation is carried out, wherein simulated status data (SSD) of the technical system (TS) is determined. The neural network (NN) is then trained to reduce a gap between the measured status data (SD) and the simulated status data (SSD). The trained neural network (NN) and the simulation module (SIM) form a hybrid simulator (HSIM). A plurality of further different control signals (CSG) are generated and fed into the hybrid simulator (HSIM) and a further neural network (NNS). The further neural network (NNS) is trained to reduce a gap between the status data (SSO) of the technical system (TS) simulated by the hybrid simulator (HSIM) and the output data (NNO) of the further neural network (NNS). The further neural network (NNS) that has been trained in this way can now be used by the control device (CTL) in order to predict the expected reaction of the technical system (TS) to any control signals (CS). In this way, the control device (CTL) is able to control the technical system (TS) in an anticipatory manner, taking into consideration the prediction for any control signals without a large spread of prediction errors.
IPC 8 full level
G06N 3/08 (2006.01); G06N 3/04 (2006.01); G06N 7/00 (2006.01)
CPC (source: EP)
G06N 3/044 (2023.01); G06N 3/047 (2023.01); G06N 3/084 (2013.01); G06N 7/00 (2013.01); Y02E 10/72 (2013.01)
Designated contracting state (EPC)
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
Designated extension state (EPC)
BA ME
Designated validation state (EPC)
KH MA MD TN
DOCDB simple family (publication)
EP 3893161 A1 20211013; CN 115668228 A 20230131; EP 4111382 A1 20230104; WO 2021204983 A1 20211014
DOCDB simple family (application)
EP 20168995 A 20200409; CN 202180041457 A 20210409; EP 2021059262 W 20210409; EP 21721849 A 20210409