Hardness prediction method, heat treatment method, hardness prediction device, heat treatment device, manufacturing method, manufacturing equipment, and hardness prediction model generation method for heat treatment track

• Main Authors: FUKUDA HIROYUKI, UEOKA SATOSHI, OSUGA KENICHI
• Format: Patent
• Language: Chinese; English
• Published: 04.04.2023
• Subjects: CHEMISTRY; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUSMETALS OR ALLOYS; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MAKING METAL MALLEABLE BY DECARBURISATION, TEMPERING OR OTHERTREATMENTS; MEASURING; METALLURGY; METALLURGY OF IRON; MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; PHYSICS; TESTING

The present invention enables heat treatment of a track having a stable hardness distribution. The hardness of the rail after forced cooling of the rail above the austenite range temperature by the cooling device (7) is predicted. A plurality of sets of learning data are acquired using a model that is calculated using, as input data, a cooling condition data set having at least the surface temperature of the rail before the start of cooling and the operating conditions of the cooling device (7), and using, as output data, the hardness of the interior of the rail after forced cooling. A hardness prediction model is generated in advance by machine learning using the plurality of sets of acquired learning data, said hardness prediction model having at least the cooling condition data set as input data and information relating to the hardness of the interior of the rail after forced cooling as output data. The hardness prediction model is used to predict the hardness of the rail on the basis of the hardness of th