{"title":"Deep Artificial Neural Network Method for Magnetic Hysteresis Loop Prediction of Polyvinyl Alcohol@CoFe2O4 Nanocomposites","authors":"Sharareh Mirzaee, Kamran Sabahi","doi":"10.1007/s12666-024-03349-1","DOIUrl":null,"url":null,"abstract":"<p>In this work, the magnetic hysteresis loop of the polyvinyl alcohol@CoFe<sub>2</sub>O<sub>4</sub> nanocomposite has been predicted and simulated using a deep artificial neural network (ANN) and Monte Carlo (MC) methods. To increase the capability of the traditional neural networks in modeling and forecasting problems, the proposed deep ANN has two hidden layers that benefit from deep learning techniques to overcome well-known issues such as overfitting and gradient vanishing. The deep ANN predicted results were compared with the simulated and experimental hysteresis loops of the synthesized polyvinyl alcohol@CoFe<sub>2</sub>O<sub>4</sub> nanocomposites obtained from the vibrating sample magnetometer and MC method. The interaction between polymer and nanoparticles, their structure, and morphology were analyzed employing Fourier transform infrared spectroscopy, X-ray diffraction spectroscopy, and field emission scanning electron microscopy. Comparison between the hysteresis loops revealed that the deep ANN method that has been trained with the previous published data was successful in the prediction of the shape and coercive field of particles in a polymer matrix relative to the MC method, which considered only the uniaxial anisotropy and Zeeman energy of the nanoparticles. The coercivity and remanence magnetization measured with the accuracy of about 93.33% and 62.23% for deep ANN method and 80.76% and 66.66% for MC method, respectively.</p>","PeriodicalId":23224,"journal":{"name":"Transactions of The Indian Institute of Metals","volume":"16 1","pages":""},"PeriodicalIF":1.6000,"publicationDate":"2024-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transactions of The Indian Institute of Metals","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1007/s12666-024-03349-1","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Materials Science","Score":null,"Total":0}
引用次数: 0
Abstract
In this work, the magnetic hysteresis loop of the polyvinyl alcohol@CoFe2O4 nanocomposite has been predicted and simulated using a deep artificial neural network (ANN) and Monte Carlo (MC) methods. To increase the capability of the traditional neural networks in modeling and forecasting problems, the proposed deep ANN has two hidden layers that benefit from deep learning techniques to overcome well-known issues such as overfitting and gradient vanishing. The deep ANN predicted results were compared with the simulated and experimental hysteresis loops of the synthesized polyvinyl alcohol@CoFe2O4 nanocomposites obtained from the vibrating sample magnetometer and MC method. The interaction between polymer and nanoparticles, their structure, and morphology were analyzed employing Fourier transform infrared spectroscopy, X-ray diffraction spectroscopy, and field emission scanning electron microscopy. Comparison between the hysteresis loops revealed that the deep ANN method that has been trained with the previous published data was successful in the prediction of the shape and coercive field of particles in a polymer matrix relative to the MC method, which considered only the uniaxial anisotropy and Zeeman energy of the nanoparticles. The coercivity and remanence magnetization measured with the accuracy of about 93.33% and 62.23% for deep ANN method and 80.76% and 66.66% for MC method, respectively.
在这项工作中,使用深度人工神经网络(ANN)和蒙特卡罗(MC)方法预测和模拟了聚乙烯醇@CoFe2O4纳米复合材料的磁滞回线。为了提高传统神经网络在建模和预测问题上的能力,所提出的深度人工神经网络有两个隐藏层,受益于深度学习技术,克服了众所周知的问题,如过拟合和梯度消失。将深度神经网络的预测结果与振动样品磁力计和 MC 方法获得的合成聚乙烯醇@CoFe2O4 纳米复合材料的模拟和实验磁滞回线进行了比较。利用傅立叶变换红外光谱、X 射线衍射光谱和场发射扫描电子显微镜分析了聚合物与纳米粒子之间的相互作用、它们的结构和形态。滞后环之间的比较显示,与只考虑纳米粒子的单轴各向异性和泽曼能量的 MC 方法相比,利用以前公布的数据训练的深度 ANN 方法在预测聚合物基体中粒子的形状和矫顽力场方面取得了成功。深度 ANN 方法测得的矫顽力和剩磁的准确率分别为 93.33% 和 62.23%,MC 方法为 80.76% 和 66.66%。
期刊介绍:
Transactions of the Indian Institute of Metals publishes original research articles and reviews on ferrous and non-ferrous process metallurgy, structural and functional materials development, physical, chemical and mechanical metallurgy, welding science and technology, metal forming, particulate technologies, surface engineering, characterization of materials, thermodynamics and kinetics, materials modelling and other allied branches of Metallurgy and Materials Engineering.
Transactions of the Indian Institute of Metals also serves as a forum for rapid publication of recent advances in all the branches of Metallurgy and Materials Engineering. The technical content of the journal is scrutinized by the Editorial Board composed of experts from various disciplines of Metallurgy and Materials Engineering. Editorial Advisory Board provides valuable advice on technical matters related to the publication of Transactions.