Composition analysis and identification of ancient glass products

Abstract

In this paper, aiming at the problem of composition analysis and identification of ancient glass products, a correlation analysis model based on chi square test is established to solve the relationship between the surface weathering of cultural relics and glass types, patterns and colors; ARMA model is established to solve the statistical law of chemical composition content with or without weathering and the problem of predicting chemical composition content before weathering; A classification model based on K-means++clustering is established to solve the problem of classification rules; An evaluation model based on principal component analysis is established to solve the problem of type identification of glass relics.