介电常数
钙钛矿(结构)
微波食品加热
反射(计算机编程)
材料科学
石墨烯
复合数
电介质
反射损耗
图形用户界面
介电损耗
复合材料
计算机科学
机器学习
算法
光电子学
纳米技术
化学工程
工程类
电信
程序设计语言
摘要
In this paper, a novel method is investigated wherein the theoretical and mathematical analysis of the perovskite-Reduced Graphene Oxide (RGO) based composite microwave absorber is used to form a machine learning model using linear regression to predict the reflection loss and the effective dielectric permittivity of a selected perovskite compound in an RGO-based composite. At first, the theoretical derivation is carried out to find a mathematical relationship between the reflection loss and the dielectric permittivity of the composite and the cationic radii of the perovskite structure, which is then used to form the base for the machine learning model to directly calculate the microwave absorption characteristics from the atomic parameters of the given composite structure. Linear regression is used for the machine learning algorithm which is verified with an R2 of 0.869 with the atomic radii as the input parameters. The model is further used to develop a Graphical User Interface (GUI) to make the prediction more appealing and user-friendly. The current paper provides a new approach to the integration of theoretical knowledge with advanced computing tools to form innovative predictive tools for current microwave-absorbing materials.
科研通智能强力驱动
Strongly Powered by AbleSci AI