FT-IR Spectral Model of Polyester-Cotton Fabrics with Corona Plasma Treatment using Artificial Neural Networks (ANNs)

I. Irwan, Valentinus Galih Vidia Utra, JulianyNingsih Mohamad
{"title":"FT-IR Spectral Model of Polyester-Cotton Fabrics with Corona Plasma Treatment using Artificial Neural Networks (ANNs)","authors":"I. Irwan, Valentinus Galih Vidia Utra, JulianyNingsih Mohamad","doi":"10.13057/ijap.v13i1.67837","DOIUrl":null,"url":null,"abstract":"Corona plasma technology has been studied as a surface modification for the adhesive bonding of polymers. Although corona plasma (C.P.) is becoming more popular in nanotechnology, the influence of corona plasma treatment parameters on the FT-IR spectra is a problem that has yet to be addressed. The purpose of this study is to use an artificial neural network to study the influence of corona plasma (C.P.) treatment parameters on textile polymer and evaluate the ability of this model to predict FT-IR spectral information from FT-IR measurements. In this study, polymers were modified under various corona plasma treatment conditions. We investigated FT-IR spectra information of polymers from FT-IR measurements by varying corona plasma treatment variables. We used three input parameters in this study: wavenumber, voltage, and exposure time—two output parameters: fabric roughness with SEM according to the degree of smoothness and percent transmission with FT-IR. The novel aspect of this study is that we used ANN to model the plasma treatment on polyester-cotton fabrics and the FT-IR spectra accurately enough for the first time. According to this study, the model that used four nodes (neurons) in the hidden layer, three input parameters (x1,x2,x3), and 20 iterations is appropriate for determining fabric surface roughness (S.R.) and percent transmission (T%). Based on this research, the values of R2 for determining fabric surface roughness (S.R.) and percent transmission (T%) were 99.79 percent and 67.18 percent, respectively. The results showed that the developed ANNs could accurately predict the experimental data in detail. This study is significant because it uses artificial intelligence to calculate and simulate the FT-IR spectra and fabric surface roughness of plasma treatment on textile fabrics. This study's scientific application is that it will help experts, researchers, and engineers understand the implications of plasma on the chemical structure of textile materials.","PeriodicalId":31930,"journal":{"name":"Indonesian Journal of Applied Physics","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Indonesian Journal of Applied Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.13057/ijap.v13i1.67837","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Corona plasma technology has been studied as a surface modification for the adhesive bonding of polymers. Although corona plasma (C.P.) is becoming more popular in nanotechnology, the influence of corona plasma treatment parameters on the FT-IR spectra is a problem that has yet to be addressed. The purpose of this study is to use an artificial neural network to study the influence of corona plasma (C.P.) treatment parameters on textile polymer and evaluate the ability of this model to predict FT-IR spectral information from FT-IR measurements. In this study, polymers were modified under various corona plasma treatment conditions. We investigated FT-IR spectra information of polymers from FT-IR measurements by varying corona plasma treatment variables. We used three input parameters in this study: wavenumber, voltage, and exposure time—two output parameters: fabric roughness with SEM according to the degree of smoothness and percent transmission with FT-IR. The novel aspect of this study is that we used ANN to model the plasma treatment on polyester-cotton fabrics and the FT-IR spectra accurately enough for the first time. According to this study, the model that used four nodes (neurons) in the hidden layer, three input parameters (x1,x2,x3), and 20 iterations is appropriate for determining fabric surface roughness (S.R.) and percent transmission (T%). Based on this research, the values of R2 for determining fabric surface roughness (S.R.) and percent transmission (T%) were 99.79 percent and 67.18 percent, respectively. The results showed that the developed ANNs could accurately predict the experimental data in detail. This study is significant because it uses artificial intelligence to calculate and simulate the FT-IR spectra and fabric surface roughness of plasma treatment on textile fabrics. This study's scientific application is that it will help experts, researchers, and engineers understand the implications of plasma on the chemical structure of textile materials.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于人工神经网络的电晕等离子体处理涤棉织物FT-IR光谱模型
研究了电晕等离子体技术作为聚合物粘接的表面改性技术。虽然电晕等离子体(C.P.)在纳米技术中越来越受欢迎,但电晕等离子体处理参数对FT-IR光谱的影响是一个尚未解决的问题。本研究的目的是利用人工神经网络研究电晕等离子体(C.P.)处理参数对纺织聚合物的影响,并评估该模型从FT-IR测量中预测FT-IR光谱信息的能力。在本研究中,聚合物在不同的电晕等离子体处理条件下进行了改性。我们通过改变电晕等离子体处理变量来研究聚合物的红外光谱信息。在这项研究中,我们使用了三个输入参数:波数、电压和曝光时间——两个输出参数:织物的粗糙度(根据平滑程度)和透射率(FT-IR)。本研究的新颖之处在于,我们首次使用人工神经网络对涤棉织物的等离子体处理进行了模拟,并获得了足够精确的FT-IR光谱。根据本研究,使用隐藏层中4个节点(神经元),3个输入参数(x1,x2,x3), 20次迭代的模型适合用于确定织物表面粗糙度(S.R.)和透射率(T%)。基于本研究,确定织物表面粗糙度(S.R.)和透射率(T%)的R2值分别为99.79%和67.18%。结果表明,所开发的人工神经网络能够准确地预测实验数据的细节。本研究利用人工智能计算和模拟了等离子体处理织物的FT-IR光谱和织物表面粗糙度,具有重要的意义。这项研究的科学应用是,它将帮助专家、研究人员和工程师了解等离子体对纺织材料化学结构的影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
28
审稿时长
12 weeks
期刊最新文献
A spin current detecting device working in the drift-diffusion and degenerate regimes Determining The Crystallite Size of TiO2/EG-Water XRD Data Using the Scherrer Equation Synthesis of Material Composite rGO-TIO2 From Coconut Shells by Sol-Gel Methods as Photocatalyst A Comparison of CNN-based Image Feature Extractors for Weld Defects Classification Optimizing the Composition of Basalt and Heat Treatment of Fly Ash-Based Mullite Ceramics Using the Taguchi Method
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1