Remaining lifespan prediction device, remaining lifespan prediction method, and program

In the present invention, a learning model is trained by using: creep rupture strength values and creep rupture times of a plurality of metal materials manufactured using the identical standard but different heats; and material condition data indicating conditions of the respective metal materials....

Full description

Saved in:
Bibliographic Details
Main Authors NAKAMURA, TADAAKI, HASHIMOTO, KEITA, SAITO, NOBUHIKO, HONDA, TAKASHI, SHIRANE, TAKAHIRO, TOMINAGA, KIMIHIKO, KOMAI, NOBUYOSHI
Format Patent
LanguageChinese
English
Published 16.10.2023
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:In the present invention, a learning model is trained by using: creep rupture strength values and creep rupture times of a plurality of metal materials manufactured using the identical standard but different heats; and material condition data indicating conditions of the respective metal materials. An output value of the learning model is acquired by inputting, to the learning model, a prescribed length of time and material condition data for a metal material in current use that is a metal material of said standard. If the acquired output value is plugged in as a load stress to a predictive formula, and if a prescribed temperature that is determined in advance is plugged in to the predictive formula, the predictive formula is adjusted so that a creep rupture time calculated by the predictive formula will match the prescribed length of time. An actual temperature used and actual load stress are plugged in to the adjusted predictive formula to calculate the creep rupture time of the metal material in current us
Bibliography:Application Number: TW202211141042