基于长波红外发射光谱的高光谱成像技术对黑色塑料类型进行分类

IF 5 2区材料科学 Q1 MATERIALS SCIENCE, CHARACTERIZATION & TESTING Polymer Testing Pub Date : 2024-11-07 DOI:10.1016/j.polymertesting.2024.108629

Mads Nibe Larsen , Anders Løchte Jørgensen , Victor Petrunin , Jakob Kjelstrup-Hansen , Bjarke Jørgensen , Mogens Hinge

{"title":"基于长波红外发射光谱的高光谱成像技术对黑色塑料类型进行分类","authors":"Mads Nibe Larsen , Anders Løchte Jørgensen , Victor Petrunin , Jakob Kjelstrup-Hansen , Bjarke Jørgensen , Mogens Hinge","doi":"10.1016/j.polymertesting.2024.108629","DOIUrl":null,"url":null,"abstract":"<div><div>Identification of black plastics poses a significant challenge in recycling due to the absorptive nature of carbon black additives. This work introduces a method where hyperspectral imaging in the long-wave infrared regime is used to distinguish between twelve samples of commercially available black plastics encompassing nine distinct polymer types. The spectral scanner comprises a scanning Fabry-Pérot interferometer and a thermal camera based on an uncooled microbolometer detector sensitive to wavelengths from 8 μm to 15 μm. A principal component model is combined with k-nearest neighbors to differentiate between plastic samples in hyperspectral images. The model successfully classifies five (PET, POM, PMMA, PA6, and PA66) out of nine black polymers, and the overall accuracy of the model is <span><math><mrow><mi>A</mi><mo>=</mo><mn>73.1</mn></mrow></math></span> %.</div></div>","PeriodicalId":20628,"journal":{"name":"Polymer Testing","volume":"141 ","pages":"Article 108629"},"PeriodicalIF":5.0000,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Classification of black plastic types by hyperspectral imaging based on long-wave infrared emission spectroscopy\",\"authors\":\"Mads Nibe Larsen , Anders Løchte Jørgensen , Victor Petrunin , Jakob Kjelstrup-Hansen , Bjarke Jørgensen , Mogens Hinge\",\"doi\":\"10.1016/j.polymertesting.2024.108629\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Identification of black plastics poses a significant challenge in recycling due to the absorptive nature of carbon black additives. This work introduces a method where hyperspectral imaging in the long-wave infrared regime is used to distinguish between twelve samples of commercially available black plastics encompassing nine distinct polymer types. The spectral scanner comprises a scanning Fabry-Pérot interferometer and a thermal camera based on an uncooled microbolometer detector sensitive to wavelengths from 8 μm to 15 μm. A principal component model is combined with k-nearest neighbors to differentiate between plastic samples in hyperspectral images. The model successfully classifies five (PET, POM, PMMA, PA6, and PA66) out of nine black polymers, and the overall accuracy of the model is <span><math><mrow><mi>A</mi><mo>=</mo><mn>73.1</mn></mrow></math></span> %.</div></div>\",\"PeriodicalId\":20628,\"journal\":{\"name\":\"Polymer Testing\",\"volume\":\"141 \",\"pages\":\"Article 108629\"},\"PeriodicalIF\":5.0000,\"publicationDate\":\"2024-11-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Polymer Testing\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0142941824003064\",\"RegionNum\":2,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATERIALS SCIENCE, CHARACTERIZATION & TESTING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Polymer Testing","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0142941824003064","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, CHARACTERIZATION & TESTING","Score":null,"Total":0}

引用次数: 0

摘要

由于炭黑添加剂的吸收特性，黑色塑料的识别成为回收利用中的一项重大挑战。这项工作介绍了一种方法，即利用长波红外高光谱成像来区分 12 种市售黑色塑料样品，包括 9 种不同的聚合物类型。光谱扫描仪包括一个扫描法布里-佩罗干涉仪和一个热像仪，热像仪基于对 8 μm 至 15 μm 波长敏感的非制冷微测辐射热计探测器。主成分模型与 k 近邻相结合，可区分高光谱图像中的塑料样品。该模型成功地对九种黑色聚合物中的五种（PET、POM、PMMA、PA6 和 PA66）进行了分类，模型的总体准确率为 A=73.1%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Classification of black plastic types by hyperspectral imaging based on long-wave infrared emission spectroscopy

Identification of black plastics poses a significant challenge in recycling due to the absorptive nature of carbon black additives. This work introduces a method where hyperspectral imaging in the long-wave infrared regime is used to distinguish between twelve samples of commercially available black plastics encompassing nine distinct polymer types. The spectral scanner comprises a scanning Fabry-Pérot interferometer and a thermal camera based on an uncooled microbolometer detector sensitive to wavelengths from 8 μm to 15 μm. A principal component model is combined with k-nearest neighbors to differentiate between plastic samples in hyperspectral images. The model successfully classifies five (PET, POM, PMMA, PA6, and PA66) out of nine black polymers, and the overall accuracy of the model is

A = 73.1

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Polymer Testing 工程技术-材料科学：表征与测试

CiteScore

10.70

自引率

5.90%

发文量

328

审稿时长

44 days

期刊介绍： Polymer Testing focuses on the testing, analysis and characterization of polymer materials, including both synthetic and natural or biobased polymers. Novel testing methods and the testing of novel polymeric materials in bulk, solution and dispersion is covered. In addition, we welcome the submission of the testing of polymeric materials for a wide range of applications and industrial products as well as nanoscale characterization. The scope includes but is not limited to the following main topics: Novel testing methods and Chemical analysis • mechanical, thermal, electrical, chemical, imaging, spectroscopy, scattering and rheology Physical properties and behaviour of novel polymer systems • nanoscale properties, morphology, transport properties Degradation and recycling of polymeric materials when combined with novel testing or characterization methods • degradation, biodegradation, ageing and fire retardancy Modelling and Simulation work will be only considered when it is linked to new or previously published experimental results.