Paper Contents
Abstract
The Piezoelectric Charge Coefficient, d33, is considered an important metric for assessing the performance of porous ferroelectric materials used in sensors, actuators, vitality collectors, etc. This study is about predicting the piezoelectric charge coefficient d33 values of porous ferroelectric materials using advanced machine learning techniques. The comprehensive dataset comprises numerous factors, counting relative thickness, clear open porosity, closed porosity, division of open porosity, and geometric measurements. This study focuses on barium Titanate (BTO) materials due to their well-established piezoelectric properties hence these findings may not be directly applicable to other ferromagnetic materials. After applying various machine learning models to this dataset we identified that the Random Forest regression model and the Gradient boosting model exhibited superior predictive accuracy. This discovery could replace the traditional methods to obtain d33 and reduce the reliance on extensive experimental trials.
Copyright
Copyright © 2024 Amisha Aman Batra . This is an open access article distributed under the Creative Commons Attribution License.
