S Saravanakumar, S Sathiyamurthy, P Pathmanaban, P Devi
{"title":"结合机器学习和响应面方法分析生物复合材料的各向异性力学性能","authors":"S Saravanakumar, S Sathiyamurthy, P Pathmanaban, P Devi","doi":"10.1080/09276440.2023.2260239","DOIUrl":null,"url":null,"abstract":"ABSTRACTThis study enhances the anisotropic mechanical properties of banana fiber-epoxy composites by optimizing fiber loading, orientation, and treatment using Response Surface Methodology (RSM) and Artificial Neural Network (ANN). RSM suggests optimal values: fiber loading at 33 wt%, NaOH treatment at 6.8 wt%, and fiber orientation at 15 degrees. This material has exceptional mechanical characteristics, including a maximum tensile strength (TLS) of 31.72 MPa, a maximum flexural strength (FLS) of 42.86 MPa, and a maximum impact strength (IPS) of 38.56 kJm-2. ANN effectively predicts strengths with high R2 scores of 0.969, 0.984, and 0.954 for tensile, flexural, and impact strengths. Incorporating batch normalization and dropout layers enhances robustness. The study concludes that NaOH treatment and fiber orientation significantly impact the composite’s anisotropy.KEYWORDS: ANNbiocompositesfiber orientationalkali treatmentanisotropic behaviormechanical propertiesresponse surface methodology (RSM) AcknowledgementsThe authors would like to acknowledge the scheme of Innovation, Technology Development, and Deployment (1819) of the Department of Science and Technology (DST) - Delhi.Disclosure statementNo potential conflict of interest was reported by the author(s).Author contributionAuthor 1: Corresponding AuthorAuthor 2: Research GuideAuthor 3: Machine Learning Prediction model developed.","PeriodicalId":10653,"journal":{"name":"Composite Interfaces","volume":"4 1","pages":"0"},"PeriodicalIF":2.1000,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Integrating machine learning and response surface methodology for analyzing anisotropic mechanical properties of biocomposites\",\"authors\":\"S Saravanakumar, S Sathiyamurthy, P Pathmanaban, P Devi\",\"doi\":\"10.1080/09276440.2023.2260239\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ABSTRACTThis study enhances the anisotropic mechanical properties of banana fiber-epoxy composites by optimizing fiber loading, orientation, and treatment using Response Surface Methodology (RSM) and Artificial Neural Network (ANN). RSM suggests optimal values: fiber loading at 33 wt%, NaOH treatment at 6.8 wt%, and fiber orientation at 15 degrees. This material has exceptional mechanical characteristics, including a maximum tensile strength (TLS) of 31.72 MPa, a maximum flexural strength (FLS) of 42.86 MPa, and a maximum impact strength (IPS) of 38.56 kJm-2. ANN effectively predicts strengths with high R2 scores of 0.969, 0.984, and 0.954 for tensile, flexural, and impact strengths. Incorporating batch normalization and dropout layers enhances robustness. The study concludes that NaOH treatment and fiber orientation significantly impact the composite’s anisotropy.KEYWORDS: ANNbiocompositesfiber orientationalkali treatmentanisotropic behaviormechanical propertiesresponse surface methodology (RSM) AcknowledgementsThe authors would like to acknowledge the scheme of Innovation, Technology Development, and Deployment (1819) of the Department of Science and Technology (DST) - Delhi.Disclosure statementNo potential conflict of interest was reported by the author(s).Author contributionAuthor 1: Corresponding AuthorAuthor 2: Research GuideAuthor 3: Machine Learning Prediction model developed.\",\"PeriodicalId\":10653,\"journal\":{\"name\":\"Composite Interfaces\",\"volume\":\"4 1\",\"pages\":\"0\"},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2023-09-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Composite Interfaces\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1080/09276440.2023.2260239\",\"RegionNum\":4,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MATERIALS SCIENCE, COMPOSITES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Composite Interfaces","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/09276440.2023.2260239","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, COMPOSITES","Score":null,"Total":0}
Integrating machine learning and response surface methodology for analyzing anisotropic mechanical properties of biocomposites
ABSTRACTThis study enhances the anisotropic mechanical properties of banana fiber-epoxy composites by optimizing fiber loading, orientation, and treatment using Response Surface Methodology (RSM) and Artificial Neural Network (ANN). RSM suggests optimal values: fiber loading at 33 wt%, NaOH treatment at 6.8 wt%, and fiber orientation at 15 degrees. This material has exceptional mechanical characteristics, including a maximum tensile strength (TLS) of 31.72 MPa, a maximum flexural strength (FLS) of 42.86 MPa, and a maximum impact strength (IPS) of 38.56 kJm-2. ANN effectively predicts strengths with high R2 scores of 0.969, 0.984, and 0.954 for tensile, flexural, and impact strengths. Incorporating batch normalization and dropout layers enhances robustness. The study concludes that NaOH treatment and fiber orientation significantly impact the composite’s anisotropy.KEYWORDS: ANNbiocompositesfiber orientationalkali treatmentanisotropic behaviormechanical propertiesresponse surface methodology (RSM) AcknowledgementsThe authors would like to acknowledge the scheme of Innovation, Technology Development, and Deployment (1819) of the Department of Science and Technology (DST) - Delhi.Disclosure statementNo potential conflict of interest was reported by the author(s).Author contributionAuthor 1: Corresponding AuthorAuthor 2: Research GuideAuthor 3: Machine Learning Prediction model developed.
期刊介绍:
Composite Interfaces publishes interdisciplinary scientific and engineering research articles on composite interfaces/interphases and their related phenomena. Presenting new concepts for the fundamental understanding of composite interface study, the journal balances interest in chemistry, physical properties, mechanical properties, molecular structures, characterization techniques and theories.
Composite Interfaces covers a wide range of topics including - but not restricted to:
-surface treatment of reinforcing fibers and fillers-
effect of interface structure on mechanical properties, physical properties, curing and rheology-
coupling agents-
synthesis of matrices designed to promote adhesion-
molecular and atomic characterization of interfaces-
interfacial morphology-
dynamic mechanical study of interphases-
interfacial compatibilization-
adsorption-
tribology-
composites with organic, inorganic and metallic materials-
composites applied to aerospace, automotive, appliances, electronics, construction, marine, optical and biomedical fields