基于近红外光谱建立PE、PP和PET的识别分类模型

被引：5

作者：

张毅民

王鹏

白家瑞

马冬雅

机构：

[1] 天津大学化工学院教育部绿色合成与转化重点实验室

来源：

现代化工 | 2016年 / 36卷 / 03期

关键词：

近红外高光谱; 塑料识别分类; 特征波长; 判别分析; 识别模型;

D O I：

10.16606/j.cnki.issn0253-4320.2016.03.046

中图分类号：

O657.33 [红外光谱分析法]; TQ320.77 [产品检验];

学科分类号：

070302 ; 081704 ; 0805 ; 080502 ;

摘要：

利用近红外高光谱成像仪在900～1 700 nm的范围采集PE、PP和PET样本的高光谱图像,并进行黑白校正,提取感兴趣区域的反射率光谱数据;利用主成分分析法对提取的数据去噪降维。结果表明,前3个主成分的累计贡献率达98.89%。把前3个主成分的载荷系数对波长作图,得到了6个特征波长;利用特征波长对应的反射率光谱数据进行判别分析,并建立了3种塑料的识别分类模型;用预测样本对模型进行检验,结果显示,预测样本的识别准确率为95.24%,表明该模型可准确有效地对PE、PP和PET进行识别分类。

引用

页码：182 / 186

页数：5

共 11 条

[1]

MATLAB工具箱应用[M]. 电子工业出版社 , 苏金明等编著, 2004

[2] Investigation of fungal development in maize kernels using NIR hyperspectral imaging and multivariate data analysis [J].

Williams, Paul J. ;

Geladi, Paul ;

Britz, Trevor J. ;

Manley, Marena .

JOURNAL OF CEREAL SCIENCE, 2012, 55 (03) :272-278

[3]

Classification of polyolefins from building and construction waste using NIR hyperspectral imaging system[J] . Silvia Serranti,Aldo Gargiulo,Giuseppe Bonifazi. Resources, Conservation & Recycling . 2012

[4] Characterization of post-consumer polyolefin wastes by hyperspectral imaging for quality control in recycling processes [J].

Serranti, Silvia ;

Gargiulo, Aldo ;

Bonifazi, Giuseppe .

WASTE MANAGEMENT, 2011, 31 (11) :2217-2227

[5]

Prediction of some quality attributes of lamb meat using near-infrared hyperspectral imaging and multivariate analysis[J] . Mohammed Kamruzzaman,Gamal ElMasry,Da-Wen Sun,Paul Allen. Analytica Chimica Acta . 2011

[6]

Quality classification of cooked, sliced turkey hams using NIR hyperspectral imaging system[J] . Gamal ElMasry,Abdullah Iqbal,Da-Wen Sun,Paul Allen,Paddy Ward. Journal of Food Engineering . 2010 (3)

[7]

Application of NIR hyperspectral imaging for discrimination of lamb muscles[J] . Mohammed Kamruzzaman,Gamal ElMasry,Da-Wen Sun,Paul Allen. Journal of Food Engineering . 2010 (3)

[8]

Thermolysis of waste plastics to liquid fuel[J] . Achyut K. Panda,R.K. Singh,D.K. Mishra. Renewable and Sustainable Energy Reviews . 2009 (1)

[9] Maize kernel hardness classification by near infrared (NIR) hyperspectral imaging and multivariate data analysis [J].

Williams, Paul ;

Geladi, Paul ;

Fox, Glen ;

Manley, Marena .

ANALYTICA CHIMICA ACTA, 2009, 653 (02) :121-130

[10] Classification of toxigenic and atoxigenic strains of Aspergillus flavus with hyperspectral imaging [J].

Jin, Jian ;

Tang, Lie ;

Hruska, Zuzana ;

Yao, Haibo .

COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2009, 69 (02) :158-164

← 1 2 →