Glass Classification and Identification based on K-means++ Clustering Analysis and BP Neural Network Method

Guanfu Cai; Haojun Li; Jingming Huang

doi:10.54097/hset.v39i.6573

Authors

Guanfu Cai
Haojun Li
Jingming Huang

DOI:

https://doi.org/10.54097/hset.v39i.6573

Keywords:

K-means Clustering Analysis; BP Neural Network; Glass Artifacts.

Abstract

The weathering caused by the burial environment will cause the ancient glass to exchange material with the environment, and the weathering layer produced by the material exchange will have an impact on the class judgment of ancient glass. In this paper, we analyze the classification rules of high potassium glass and lead-barium glass; select the appropriate chemical composition for subclass division and establish the classification model of glass. After this, a binary classification (high potassium/lead-barium) model is established by BP neural network training, and the subclassified main components of each type of glass derived from the classification model are used as adjustment variables to analyze the chemical composition of unknown categories of glass artifacts and identify the types to which they belong by controlling a single variable.

Downloads

Download data is not yet available.

References

Wu B., Yu D. Deep convolutional neural network-based classification and detection of cell phone glass cover surface defects[J]. Software Engineering,2021,24(12):6-10. DOI:10.19644/j.cnki.issn2096-1472. 2021. 012.002.

Ren Ru. A study of dictionary learning in classification of defects in glass fiber cloth [D]. Xi'an University of Engineering, 2019. DOI: 10.27390/d.cnki.gxbfc.2019.000047.

Lu Yue. Deep learning-based classification and detection of cell phone glass defects[D]. Zhengzhou University,2019.

Xue Yuan. Research on glass defect classification and recognition based on machine vision[D]. Hefei University of Technology,2018.

Li Q., Zhou B. Research on neural network classification model of substrate glass defects based on cloud computing[J]. Computer and Digital Engineering,2017,45(07):1373-1376.

Dai Qun. Research on hybrid neural network based on ICBP model with diverse integration methods[D]. Nanjing University of Aeronautics and Astronautics, 2009.

Chen, Tianbao. Research on the classification algorithm of float glass defects based on BP network[D]. Huazhong University of Science and Technology, 2007.

Ai Jieyan. Research on color classification and defect detection of wall and floor tiles based on computer vision [D]. South China University of Technology, 2003.

Ai Jieyan, Zhu Xuefeng. Improved algorithm based ART2 network for color classification of microcrystalline glass[J]. Journal of South China University of Technology (Natural Science Edition), 2003 (01):74-78.

Liu C. X., Deng P. F., Pan S. H., Luo W. D., Zhang S. L., Li T. M. Classification and research status of fireproof glass [J]. Guangzhou Chemical Industry,2021,49(15):16-18.