Development and application of comprehensive evaluation model based on correlation analysis algorithm, multiple logistic regression and clustering algorithm - Taking glass composition analysis and identification as an example

Abstract

Take glass as an example. In ancient times, when firing glass, in addition to the raw material quartz sand, chemical components such as stabilizer and flux need to be added. During the storage process of glass, the internal elements will exchange with the environmental elements in a large amount, resulting in the weathering of the glass surface. In this paper, the composition of ancient glass is analyzed and identified by establishing correlation analysis model, multiple logistic regression and cluster model. The results show that: (1) There is a high correlation between glass type and surface weathering. Lead barium glass is easy to be weathered, and high potassium glass is not easy to be weathered. (2) High-potassium glass and lead-barium glass have the highest classification accuracy when they are divided into two sub-categories. Therefore, glass can be divided into four categories: high-potassium I, high-potassium II, lead-barium I, and lead-barium II.