{"title":"An ANN model of polymer based MEMS structures: A modal analysis approach","authors":"Ajayakumar Katageri, B. G. Sheeparamatti","doi":"10.1109/ICSSS.2014.7006184","DOIUrl":null,"url":null,"abstract":"Use of polymer material in manufacturing of microstructures has been a trend in recent MEMS technology. One such trend is employed in this paper where in four different micro structures are designed and simulated using SU8 polymer material. All the architectures are simulated using COMSOL Multi physics to compute modal frequency. The simulation results are verified analytically using a standard mathematical equations. The simulated architectures are then modelled using neural network to compute the dimensions of a given architecture for a desired modal frequency. Also the simulation results, the analytical results and the ANN results are compared for the various architectures.","PeriodicalId":354879,"journal":{"name":"2014 International Conference on Smart Structures and Systems (ICSSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 International Conference on Smart Structures and Systems (ICSSS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSSS.2014.7006184","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
Use of polymer material in manufacturing of microstructures has been a trend in recent MEMS technology. One such trend is employed in this paper where in four different micro structures are designed and simulated using SU8 polymer material. All the architectures are simulated using COMSOL Multi physics to compute modal frequency. The simulation results are verified analytically using a standard mathematical equations. The simulated architectures are then modelled using neural network to compute the dimensions of a given architecture for a desired modal frequency. Also the simulation results, the analytical results and the ANN results are compared for the various architectures.