Portal de Periódicos da CAPES

Density of Bismuth Boro Zinc Glasses Using Machine Learning Techniques

2022; Springer Science+Business Media; Volume: 32; Issue: 3 Linguagem: Inglês

10.1007/s10904-021-02183-y

1574-1451

Shaik Amer Ahmed, Shaik Rajiya, M.A. Samee, Shaik Kareem Ahmmad, Kaleem Ahmed Jaleeli,

Pigment Synthesis and Properties

Machine learning techniques have been employed to predict the glass densities of xBi2O3–(70 − x)B2O3–20Li2O–5Sb2O3–5ZnO glasses using a data set of 2000 various B2O3 rich glasses using their chemical composition and ionic radius. The experimental density of present glasses strongly depends on Bi2O3 content which is increasing with bismuth content. The increasing density in bismuth doped glasses because the BO3 are converted into BO4 units, and besides BO3 units are less heavy than the BO4 units. The FTIR studies also confirm that the intensity of B–O–B bond decreasing with increasing Bi2O3 content which suggested that B–O–B bond in bond ring isolated to BO3 units transformed into BO4 units. In Raman Spectra the stretching vibrations of BO4 units shifting towards higher wavelengths with increasing Bi2O3 content. This shifting conforms that there is a structural changes in the glass-matrix and borate units converting from BO3 to BO4 units. The prepared glasses along with B2O3 rich glass data set train on various AI model such as gradient descent, Random Forest regression and Neural Networks to predict present density of glasses. Among the various models RF regression analysis model is successfully acceptable for the glass data with the highest R2 value 0.983 which end result conform that the predicted and experimental values correlated. ANNs stood the effective technique in prediction of glass density with the optimum performance resulting with Tanh as the activation function (R2 = 0.950). The minimum cost 0.018 obtained in the case of gradient decent function which also shows the better performance of regression model.