Artificial intelligence density model for oxide glasses. Issue 6 (15th March 2021)

• Record Type: Journal Article
• Authors: Ahmmad, Shaik Kareem; Jabeen, Nameera; Uddin Ahmed, Syed Taqi; Ahmed, Shaik Amer; Rahman, Syed
• Is Part Of: Ceramics international. Volume 47:Issue 6(2021)
• Page Start: 7946
• Page End: 7956
• Publication Date: 2021-03-15
• Subjects: Oxide glasses -- Density -- Ionic packing ratio -- Artificial intelligence; Ceramics -- Periodicals; Céramique industrielle -- Périodiques; Ceramics; Periodicals; Electronic journals; 666
• DOI: 10.1016/j.ceramint.2020.11.144
• Languages: English
• ISSNs: 0272-8842

Abstract

Abstract: A comprehensive study to perform glass density prediction employing artificial intelligence using a dataset of 6630 oxide glass samples. The prediction is done based on Ionic packing ratio as the independent variable and experimental densities from the dataset as the dependent variable. Random forest regression and artificial neural networks were observed as the best models training the density datasets. The random forest regression had the least average R 2 score for large datasets. Artificial neural networks employing sigmoid and ReLU activation functions dominate in predicting the glass density as compared to tanh and identity activation functions. Based on this study we can theoretically predict the density of any oxide glass to an extent of maximum accuracy for a known glass composition.