Predictive modeling of Young's modulus for alpha alumina using artificial neural network and multiple linear regression
No Thumbnail Available
Date
2021
Journal Title
Journal ISSN
Volume Title
Publisher
University of Oum El Bouaghi
Abstract
In the present work, we have constructed a predictive model for one of the important mechanical properties in the study of the mechanical and thermal behavior of materials, this property is Young's modulus. The samples on which the experiments to determine the above property of
alumina (α-Al2O3) were performed were made by Spark Plasma Sintering (SPS). The experimental results were exploited using the radial basis function (RBF) neural network model and multiple linear regression (MLR) to predict and construct the mathematical model. A comparison was made of the multiple linear regression model with the radial basis function (RBF) neural network model. Then, the two proposed models were compared with the experimental results. The study obtained showed good agreement between the experimental results and the proposed RBFNN models. But the MLR models were modest in predicting the studied mechanical property.
Description
Keywords
SPS : Alumina Spark Plasma Sintering ; RBF : Neural
network ; MLR : Multiple linear regression