Parameter correction apparatus, parameter correction method, and computer program

Abstract

(Project) Provides a technology that can reduce environmental burden while also rapidly modifying discharge characteristics. (Solution) The regression model construction unit (919) takes as input a feature difference (dF) which is the difference between a reference feature (F0) of a reference waveform (Wst) measured with a reference parameter (P0) and a peripheral feature (F1~Fm) of a peripheral waveform (W1~Wm) measured with peripheral parameters (P1~Pm) which have some values ​​of the reference parameter (P0) changed, and outputs a parameter difference (dP) which is the difference between the reference parameter (P0) and peripheral parameters (P1~Pm), and constructs a regression model (Y) by machine learning using supervised data. The correction unit (917) inputs the difference between the reference feature quantity (F0) of the reference waveform (Wst) and the target feature quantity (F0´) of the target waveform (Wst´) measured later than the time when the reference waveform (Wst) was measured, into the regression model (Y), and corrects the reference parameter (P0) according to the correction amount output from the regression model (Y).

Images