This article aims to establish an interpretable machine-learning classification model and use various SPSSPRO algorithms for computational analysis. Ancient glass is highly susceptible to weathering, which in turn leads to changes in its chemical composition. This article is based on this and studies the correlation between various variables, the classification rules of high potassium glass and lead barium glass, the analysis of weathering components, and the identification of categories. This provides relevant references and a basis for relevant departments to identify ancient glass and protect glass relics.