Composition analysis and identification of glass products based on Pearson correlation analysis

Abstract

Ancient glass objects record the cultural exchanges between East and West along the Silk Road, but they have been subjected to varying degrees of weathering over time. First, to investigate the relationship between surface weathering and glass type, decoration and color of glass artifacts, this paper investigated the correlation using Kappa consistency test and judged the difference using chi-square test, and found that there was significant correlation and difference between surface weathering and glass type. For the statistical pattern between the presence or absence of weathering on the surface and the chemical composition content, the content of each chemical composition was compared between weathered and unweathered on the surface by visualizing its chemical composition content. Secondly, to analyze the classification pattern of high potassium and lead-barium glass, it is subclassed. In this paper, the chemical constituents relevant to the classification were first selected by Pearson correlation analysis, followed by subclassification of the two types of glass artifacts by establishing a K-Means clustering subclassification model based on the elbow method to determine the number of cluster centroids. Thirdly, in order to identify the unknown types of glass artifacts, this paper establishes a random forest regression algorithm for glass type identification model and derives the results by prediction. Finally, different categories of glass artifacts are analyzed to distinguish glass from four specific categories in terms of decoration, type, color and surface weathering, and the differences in chemical composition correlation relationships between different categories are obtained by comparing the chemical composition correlation tables of different categories.