Artificial intelligence density model for oxide glasses

Ahmmad, Shaik Kareem; Jabeen, Nameera; Ahmed, Syed Taqi Uddin; Ahmed, Shaik Amer; Rahman, Syed

doi:10.1016/j.ceramint.2020.11.144

Cited by 33 publications

(24 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inaba’s formulation was based on the packing fraction which was also used by Makishima and Mackenzie [ 35 ] to theoretically compute Young’s modulus using Pauling’s ionic radii. It has been observed from previous study [ 16 ] there is no proper relation established between the exp.glass density to the fraction of volume to the molar weight i.e . here packing ratio assumed to be unchanged, the Eq.…”

Section: Resultsmentioning

confidence: 92%

“…The results of this distinctive study also produced the best results as compared to the previous literature available employing large glass datasets, thus enabling the findings of this work to future glass research employing Artificial Intelligence. Previous studies [ 13 – 16 ] also proved ANNs to perform better than other algorithms for prediction using glass datasets.…”

Section: Resultsmentioning

confidence: 94%

“…The author claim that Lasso linear regression performs the best for prediction of density although to achieve the best R 2 value around 0.7 with random forest is difficult only with the poisson’s ratio. More recently the Artificial density model was developed [ 16 ] based on the chemical composition and exp. Density using large data set 6630 oxide glass samples.…”

Section: Resultsmentioning

confidence: 99%

“…It would be logical if the behavior of glass properties are defined based on an ‘intermediate’ factor that is in turn defined by the atomic network of the glass composition. Recently, several Artificial Intelligence techniques have been successfully applied in predicting glass density in relation to ‘Atomic Packing Fraction’ factor used in the Makishima Mackenzie-model using a dataset compiled from published works which resulted in efficient density prediction correlating to the experimental results [ 16 ]. Recently, an improvement in the packing fraction model [ 17 ] was proposed with a new packing factor to account for the drawbacks in the previous APF-model based on the oxygen-atom packing fraction called the “Rigid-Unit Packing Fraction” (RUPF).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Density of Bismuth Boro Zinc Glasses Using Machine Learning Techniques

Ahmed

Rajiya

Samee

et al. 2022

J Inorg Organomet Polym

Self Cite

View full text Add to dashboard Cite

Machine learning techniques have been employed to predict the glass densities of xBi 2 O 3 –(70 − x)B 2 O 3 –20Li 2 O–5Sb 2 O 3 –5ZnO glasses using a data set of 2000 various B 2 O 3 rich glasses using their chemical composition and ionic radius. The experimental density of present glasses strongly depends on Bi 2 O 3 content which is increasing with bismuth content. The increasing density in bismuth doped glasses because the BO 3 are converted into BO 4 units, and besides BO 3 units are less heavy than the BO 4 units. The FTIR studies also confirm that the intensity of B–O–B bond decreasing with increasing Bi 2 O 3 content which suggested that B–O–B bond in bond ring isolated to BO 3 units transformed into BO 4 units. In Raman Spectra the stretching vibrations of BO 4 units shifting towards higher wavelengths with increasing Bi 2 O 3 content. This shifting conforms that there is a structural changes in the glass-matrix and borate units converting from BO 3 to BO 4 units. The prepared glasses along with B 2 O 3 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 R 2 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 (R 2 = 0.950). The minimum cost 0.018 obtained in the case of gradient decent function which also shows the better performance of regression model.

show abstract

Section: Resultsmentioning

confidence: 92%

Section: Resultsmentioning

confidence: 94%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Density of Bismuth Boro Zinc Glasses Using Machine Learning Techniques

Ahmed

Rajiya

Samee

et al. 2022

J Inorg Organomet Polym

Self Cite

View full text Add to dashboard Cite

show abstract

“…Due to the toxicity, high cost, and heavy weight of lead and lead glass materials several studies were conducted to develop alternative materials that replace lead such as tellurite-base glasses, phosphate-based materials, metal alloy, polymers [15][16][17][18][19][20][21][22][23][24][25][26][27][28]. These studies showed a good shielding performance in terms of high shielding efficiency without loss of transparency, good physical properties, thermal stability and good optical properties.…”

Section: Introductionmentioning

confidence: 99%

An Evaluation of the Shielding Effectiveness of Tellurite Glass with Composition 85TeO2-5Nb2O5-5ZnO-5Ag2O for Diagnostic Radiology Application

Hussein

2021

CJAST

View full text Add to dashboard Cite

The metal oxide glasses have attracted huge interest as promising types of shielding materials to replace the toxic, heavy and costly conventional shielding materials. In this work, the physical and the shielding effectiveness of Tellurite glass sample (S1) contain host metal oxides (85TeO2-5Nb2O5-5ZnO-5Ag2O) were evaluatedatphoton energies range between 15keVand1MeV.The shielding parameters of the proposed glass system such as linear attenuation coefficients, HVL, MFP, Zeff, and Neffwere evaluated. The proposed samples showed a superior performance at the diagnostic energy range between 40 and 90 keV and a comparable shielding effectiveness above 90keV when compared with other commercial standard shielding materials.

show abstract