Polymer raw material data analysis device and polymer raw material data analysis method

Abstract

To provide a high polymer material data analysis device and a high polymer material data analysis method in which a structure and composition of a high polymer material can be predicted with high prediction accuracy based on actually measured one-dimensional spectral information of the high polymer material.SOLUTION: A high polymer material data analysis method comprises the steps of: obtaining actually measured one-dimensional spectral information of plural kinds of high polymer materials; normalizing the one-dimensional spectral information for each high polymer material; obtaining composition information and structure information of the high polymer material and normalizing them for each piece of structure information of the high polymer material; calculating a correlation coefficient by correlation analysis based on the normalized one-dimensional spectral information and the normalized structure information; creating a learning model in which the one-dimensional spectral information is used as explanatory variable, and either one of the composition information or the structure information of the high polymer material is used as objective variable; repeatedly creating the learning model until an outcome of the learning model satisfies determination conditions; and predicting either one of structure or composition of the high polymer material by the learning model satisfying the determination conditions, using the one-dimensional spectral information.SELECTED DRAWING: Figure 2

Images