玻璃文物化学成分体系的统计分析  

Statistical Analysis of the Chemical Composition System of Ancient Glass

作　　者：周冒伟 黄佳怡 孙雪婷 刘芳[1] 

机构地区：[1]南京理工大学,数学与统计学院,江苏 南京

出　　处：《建模与仿真》2023年第2期1069-1082,共14页Modeling and Simulation

摘　　要：玻璃的起源历史悠久,作为中西方早期贸易、文化交流的宝贵物证之一,玻璃极大地丰富了人类的物质文化。分析玻璃文物类型和化学成分之间的关系,对玻璃制作工艺、来源等的研究具有非常重要的科学指导意义。本文对我国古代玻璃的化学成分进行了研究,首先使用线性回归分析和相关性分析确立了玻璃文物表面的风化化学成分,得到玻璃文物表面风化与类型的关系;然后使用K-means算法对玻璃文物进行亚类划分;最后综合均值法和偏最小二乘回归模型预测玻璃文物风化前化学成分含量,并基于决策树法鉴别未知玻璃文物所属的类型。本文对于古代玻璃文物的成分分析与类别鉴定具有一定的指导价值。Glass has a long history of origin. As one of the precious material evidence of the early trade and cultural exchanges between China and the West, glass has greatly enriched the material culture of human beings. The analysis of the relationship between the type and chemical composition of glass cultural relics is of great scientific guiding significance to the research of glass production technolo-gy and source. This paper studies the ancient Chinese glass. Firstly, we use the linear regression analysis and the correlation analysis to establish the weathering chemical composition of the glass artifact surface and obtain the relationship between surface weathering and type of glass cultural relics. Then, we use the K-means algorithm to subclassify the glass artifacts. Finally, we combine the mean method and partial least squares regression model to predict the pre-weathering chemical content of glass relics, and identify the type of unknown glass relics based on the decision tree method. This paper has certain guiding value for the composition analysis and category identifica-tion of ancient glass cultural relics.

关 键 词：偏最小二乘回归模型 化学成分含量 决策树法 统计分析 古代玻璃 文化交流 线性回归分析 文物 

分 类 号：K87[历史地理—考古学及博物馆学]