Plastic solid waste identification system based on near infrared spectroscopy in combination with support vector machine

被引:86
作者
Zhu S. [1 ,2 ,3 ]
Chen H. [1 ,2 ,3 ]
Wang M. [1 ,2 ,3 ]
Guo X. [1 ,2 ,3 ]
Lei Y. [1 ,2 ,3 ]
Jin G. [1 ,2 ,3 ]
机构
[1] National Engineering Research Center of Novel Equipment for Polymer Processing, South China University of Technology, Guangzhou
[2] Key Laboratory of Polymer Processing Engineering of Ministry of Education, South China University of Technology, Guangzhou
[3] Guangdong Provincial Key Laboratory of Technique and Equipment for Macromolecular Advanced Manufacturing, South China University of Technology
来源
Advanced Industrial and Engineering Polymer Research | 2019年 / 2卷 / 02期
基金
中国国家自然科学基金;
关键词
Near-infrared spectroscopy; Plastic identification; Principal component analysis; Support vector machine;
D O I
10.1016/j.aiepr.2019.04.001
中图分类号
学科分类号
摘要
In this paper, identification system of plastic solid waste (PSW) based on near-infrared (NIR) reflectance spectroscopy in combination with Support Vector Machine (SVM) was presented. A device applied to obtain NIR spectra of plastics in the detection platform was developed. After pre-processing (normalized, 1st derivative and smooth), the repeatability of spectral absorption features was improved, which would assist the identification. A “principal component analysis (PCA)[sbnd]SVM” identification method was proposed to identify polypropylene (PP), polystyrene (PS), polyethylene (PE), poly(methyl methacrylate) (PMMA), acrylonitrile butadiene styrene (ABS) and polyethylene terephthalate (PET) among plastics, and its identification accuracy can reach 97.5%. The type of samples could clearly be identified and the shape of samples could also be roughly discerned. It is clearly shown that this system can achieve good identification results while reducing costs considerably, which has great potential in industrial recycling. © 2019 Kingfa SCI. & TECH. CO., LTD.
引用
收藏
页码:77 / 81
页数:4
相关论文
共 17 条
  • [1] Carvalho M.T., Ferreira C., Portela A., Et al., Application of fluidization to separate packaging waste plastic, Waste Manag., 29, 3, pp. 1138-1143, (2009)
  • [2] Matsumoto T., Tanabe K., Kakurata K., Et al., Rapid discrimination between biodegradable and non-biodegradable plastic by combining near-infrared spectra measurement and chemometrics analysis, Chem. Softw., 22, (2000)
  • [3] Kamagai M., Suyama H., Sato T., Et al., Discrimination of plastic using a portable near infrared spectrometer, J. Near Infrared Spectrosc., 10, 1, pp. 247-255, (2002)
  • [4] Mcclure W.F., Near-infrared spectroscopy. The giant is running strong, Anal. Chem., 66, 1, (1994)
  • [5] Kaihara M., Satoh M., Satoh M., Systematization method for distinguishing plastic groups by using NIR spectroscopy, Anal. Sci. Int. J. Jpn. Soc. Anal. Chem., 23, 7, pp. 921-924, (2007)
  • [6] Tachwali Y., Al-Assaf Y., Al-Ali A.R., Automatic multistage classification system for plastic bottles recycling, Resour. Conserv. Recycl., 52, 2, pp. 266-285, (2008)
  • [7] Leitner R., Detecting and discriminating PE and PP polymers for plastic recycling using NIR imaging spectroscopy, Proc. SPIE Int. Soc. Opt. Eng., 7661, 4, pp. 221-247, (2010)
  • [8] Masoumi H., Safavi S.M., Khani Z., Identification and classification of plastic resins using near infrared reflectance spectroscopy, Int. J. Mech. Ind. Eng., 6, pp. 213-220, (2012)
  • [9] Kulcke A., Gurschler C., Spock G., Et al., On-line classification of synthetic polymers using near infrared spectral imaging, J. Near Infrared Spectrosc., 11, 1, pp. 71-81, (2003)
  • [10] Bearman G.H., Cabib D., Levenson R.M., Spectral Imaging: Instrumentation, Applications, and Analysis Spectral Imaging: Instrumentation, Applications, and Analysis III, (2000)