TWI848719B

This state quantity prediction device predicts a state quantity pertaining to a plant corresponding to an input parameter by using a prediction model that includes a machine learning model and a physical model. The device stores a first prediction model corresponding to a first plant, adjusts the fi...

Full description

Saved in:
Bibliographic Details
Main Authors HAZUI, YUSUKE, TATEISHI, KOKI, TACHIBANA, MISAKI, SUDO, JIN, GUNJI, SHUN, SAITO, TAKEHIRO
Format Patent
LanguageChinese
Published 11.07.2024
Subjects
CALCULATING
COMPUTING
CONTROL OR REGULATING SYSTEMS IN GENERAL
CONTROLLING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
FUNCTIONAL ELEMENTS OF SUCH SYSTEMS
MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS
PHYSICS
REGULATING
Online AccessGet full text

Cover

More Information
Summary:This state quantity prediction device predicts a state quantity pertaining to a plant corresponding to an input parameter by using a prediction model that includes a machine learning model and a physical model. The device stores a first prediction model corresponding to a first plant, adjusts the first prediction model by using measurement data pertaining to a second plant to thereby create a second prediction model corresponding to the second plant, and predicts a state quantity pertaining to the second plant by using the second prediction model. The second prediction model is created by normalizing and learning a difference between machine learning parameters of the first prediction model and the second prediction model.
Bibliography:Application Number: TW20230119280