Glass has a long history and was one of the first man-made materials invented by man. Since glass artifacts are highly susceptible to weathering, the surface composition of artifacts is easily altered. This situation affects the judgement of the type of artefact greatly. In this regard, this paper investigates the data of lead-barium glass and high potassium glass before and after weathering. Firstly, in order to demonstrate that the weathering of high potassium and lead-barium glass is related to the chemical composition of its surface, the relationship between the weathering of glass and the proportion of the chemical composition content of the glass surface needed to be investigated. In addition, it was decided to carry out an analysis using an independent sample rank sum test to obtain a pattern between weathered glass and the proportion of chemical composition content, as most of the data did not conform to a normal distribution. Finally, using the obtained information, a mechanism analysis model was designed based on the chemical kinetic theory, and a multi-objective optimization model was established using the NSGA-II Algorithm with Entropy Topsis Method. The resulting predictive equations for the chemical composition of lead-barium glass and high potassium glass before and after weathering were acquired. The results show that the discrimination between two types of glass based on the percentage of lead oxide content and the percentage of barium oxide content can procure reliable results in general.

Ying He. Identification of Weathered Glass Artifacts Components Based on NSGA-II Algorithm with Entropy TOPSIS Method. Academic Journal of Materials & Chemistry (2023) Vol. 4, Issue 3: 51-58. https://doi.org/10.25236/AJMC.2023.040308.

[1] Qun Wu, Congrong Xu, Bo Xiang. Composition analysis and identification of ancient glass products [J]. Journal of Materials, Processing and Design, 2022, 6(2).

[2] Hammes G.G. Principles of chemical kinetics [J]. Methods of Biochemical Analysis, 2007,50.

[3] Reşat ACAR, Youssef Alioui. An Evaluation of A Constrained Multi-Objective Genetic Algorithm [J]. Journal of Scientific Perspectives, 2020, 4(2).

[4] Mesquita-Cunha Mariana, Figueira José Rui, Barbosa-Póvoa Ana Paula. New [formula omitted] constraint methods for multi-objective integer linear programming: A Pareto front representation approach [J]. European Journal of Operational Research, 2023,306(1). 

[5] Ma Kunlong. Short term distributed load forecasting method based on big data [D]. Changsha: Hunan University, 2018.

[6] Li Yan, Liu Yifan, Li Shasha, Qi Leijie, Xie Jun, Xie Qing. A Novel Multi-Objective Optimal Design Method for Dry Iron Core Reactor by Incorporating NSGA-II, TOPSIS and Entropy Weight Method [J]. Energies, 2022, 15(19). 

[7] Fang Fang. Research on power load forecasting based on Improved BP neural network [D]. Harbin Institute of Technology, 2021.