Method for generating deposition quantity prediction model, method for predicting plating deposition amount, method for controlling deposition amount of plating, method for manufacturing hot-coated steel sheet, apparatus for executing the same, and generation method of quality prediction model

摘要

Problem to be solved: to provide a technology capable of improving the prediction accuracy of the plating adhesion amount.Data to be selected from the steel plate information on the plated steel plate 10 and input operation information data including the data of nozzle operation information concerning the wiping nozzle 6 andThe data for the learning with the result data of the deposition amount of the plating using the data of the input operation informationMultiple setsAcquireBy machine learning using acquired learning dataContains at least a portion of the input operation information data in the input dataAn adhesion amount prediction model 34 using the deposition amount of plating as output data is generated.One of the input data by machine learning includes one or more data selected from the steel plate information and one or more data selected from the nozzle operation information in the input data. It is also possible to use a calculation formula based on a physical model to calculate the deposition amount of plating as output data.Diagram