Proceedings of the 3rd International Conference on Public Management and Big Data Analysis, PMBDA 2023, December 15–17, 2023, Nanjing, China

Research Article

Statistical Rule and Correlation Study of Chemical Composition of Glass Products Based on Machine Learning

Download56 downloads
  • @INPROCEEDINGS{10.4108/eai.15-12-2023.2345351,
        author={Yaodong  Zhang},
        title={Statistical Rule and Correlation Study of Chemical Composition of Glass Products Based on Machine Learning},
        proceedings={Proceedings of the 3rd International Conference on Public Management and Big Data Analysis, PMBDA 2023, December 15--17, 2023, Nanjing, China},
        publisher={EAI},
        proceedings_a={PMBDA},
        year={2024},
        month={5},
        keywords={surface weathering glass type significance test correlation analysis pearson correlation coefficient multiple linear regression},
        doi={10.4108/eai.15-12-2023.2345351}
    }
    
  • Yaodong Zhang
    Year: 2024
    Statistical Rule and Correlation Study of Chemical Composition of Glass Products Based on Machine Learning
    PMBDA
    EAI
    DOI: 10.4108/eai.15-12-2023.2345351
Yaodong Zhang1,*
  • 1: Shanxi University of Finance and Economics
*Contact email: 19511426889@163.com

Abstract

In this paper, the relationship between surface weathering of glass products and glass-related elements and relationship between various chemical components were analyzed by data preprocessing and mathematical model. Firstly, a correlation analysis model was established, Pearson correlation coefficient was used. The significance test and correlation coefficient were used to conclude that the surface weathering was related to the type of glass and had a strong correlation, but had no correlation with tattoo and color. Secondly, establish the multiple linear regression model, and the statistical rule of the chemical composition content of the two kinds of glass before weathering was obtained by using the least square method. Finally, the chemical composition contents of two types of glass were taken as variables, and establish a correlation analysis model. Significance test was used to determine whether there was a correlation between the variables. The correlation coefficient was used to determine the strength of the relationship between the two variables, and the correlation relationship between the chemical composition of the same type of glass products was found.