Hang Ren , Dan Zhao , Liqiang Dong , Shaogang Liu , Jinshui Yang
{"title":"用于预测磁流变弹性体磁诱导机械性能的物理引导深度学习模型:小型实验数据驱动","authors":"Hang Ren , Dan Zhao , Liqiang Dong , Shaogang Liu , Jinshui Yang","doi":"10.1016/j.compscitech.2024.110653","DOIUrl":null,"url":null,"abstract":"<div><p>Magnetorheological elastomer (MRE) is a novel intelligent material, which shows excellent potential in vibration control applications. Previous researches have fully demonstrated that the magneto-induced shear storage modulus of MRE largely determines the vibration control effect. However, both existing theoretical and experimental ways to measure the magneto-induced shear storage modulus of MRE face their own shortage. Therefore, a novel physics-guided deep learning model is proposed to efficient predict the magneto-induced mechanical properties of MRE based on Magnetic Dipole theory and data-driven methods. A small database is built by collecting the magneto-induced shear storage modulus of MRE with different material ratios tested on a special shear rheometer. The proposed model trained with small training samples and its prediction results fit well with experimental values (average R<sup>2</sup> of 0.99) which is superior to existing constitutive models. The training only takes 25 s, which significantly shortens the time compared to the experiment. Furthermore, the proposed model effectively predicts the magneto-induced storage modulus of MRE and has good generalization and superior transfer performance.</p></div>","PeriodicalId":283,"journal":{"name":"Composites Science and Technology","volume":null,"pages":null},"PeriodicalIF":8.3000,"publicationDate":"2024-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A physics-guided deep learning model for predicting the magneto-induced mechanical properties of magnetorheological elastomer: Small experimental data-driven\",\"authors\":\"Hang Ren , Dan Zhao , Liqiang Dong , Shaogang Liu , Jinshui Yang\",\"doi\":\"10.1016/j.compscitech.2024.110653\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Magnetorheological elastomer (MRE) is a novel intelligent material, which shows excellent potential in vibration control applications. Previous researches have fully demonstrated that the magneto-induced shear storage modulus of MRE largely determines the vibration control effect. However, both existing theoretical and experimental ways to measure the magneto-induced shear storage modulus of MRE face their own shortage. Therefore, a novel physics-guided deep learning model is proposed to efficient predict the magneto-induced mechanical properties of MRE based on Magnetic Dipole theory and data-driven methods. A small database is built by collecting the magneto-induced shear storage modulus of MRE with different material ratios tested on a special shear rheometer. The proposed model trained with small training samples and its prediction results fit well with experimental values (average R<sup>2</sup> of 0.99) which is superior to existing constitutive models. The training only takes 25 s, which significantly shortens the time compared to the experiment. Furthermore, the proposed model effectively predicts the magneto-induced storage modulus of MRE and has good generalization and superior transfer performance.</p></div>\",\"PeriodicalId\":283,\"journal\":{\"name\":\"Composites Science and Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":8.3000,\"publicationDate\":\"2024-05-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Composites Science and Technology\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0266353824002239\",\"RegionNum\":1,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATERIALS SCIENCE, COMPOSITES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Composites Science and Technology","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0266353824002239","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, COMPOSITES","Score":null,"Total":0}
A physics-guided deep learning model for predicting the magneto-induced mechanical properties of magnetorheological elastomer: Small experimental data-driven
Magnetorheological elastomer (MRE) is a novel intelligent material, which shows excellent potential in vibration control applications. Previous researches have fully demonstrated that the magneto-induced shear storage modulus of MRE largely determines the vibration control effect. However, both existing theoretical and experimental ways to measure the magneto-induced shear storage modulus of MRE face their own shortage. Therefore, a novel physics-guided deep learning model is proposed to efficient predict the magneto-induced mechanical properties of MRE based on Magnetic Dipole theory and data-driven methods. A small database is built by collecting the magneto-induced shear storage modulus of MRE with different material ratios tested on a special shear rheometer. The proposed model trained with small training samples and its prediction results fit well with experimental values (average R2 of 0.99) which is superior to existing constitutive models. The training only takes 25 s, which significantly shortens the time compared to the experiment. Furthermore, the proposed model effectively predicts the magneto-induced storage modulus of MRE and has good generalization and superior transfer performance.
期刊介绍:
Composites Science and Technology publishes refereed original articles on the fundamental and applied science of engineering composites. The focus of this journal is on polymeric matrix composites with reinforcements/fillers ranging from nano- to macro-scale. CSTE encourages manuscripts reporting unique, innovative contributions to the physics, chemistry, materials science and applied mechanics aspects of advanced composites.
Besides traditional fiber reinforced composites, novel composites with significant potential for engineering applications are encouraged.