Identification of different colored plastics by laser-induced breakdown spectroscopy combined with neighborhood component analysis and support vector machine

Nie, Junfei; Wen, Xuelin; Niu, Xuechen; Chu, Yanwu; Chen, Feng; Wang, Weiliang; Zhang, Deng; Hu, Zhenlin; Ji, Xiao; Guo, Lianbo

doi:10.1016/j.polymertesting.2022.107624

Cited by 8 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar approach was adopted by Nie et al who used LIBS incorporating a Nd:YAG laser operating at 532 nm to analyse six different plastic types of five different colours and then evaluated the data using several chemometric techniques. 105 The polymers tested were: polyethylene, polypropylene, polyamide, PVC, acrylonitrile-butadiene-styrene (ABS) and polyoxymethylene (POM) and the colours were different shades of: black, yellow, blue, white and brown. Several algorithms were tested including support vector machine (SVM), PCA and neighbourhood component analysis (a method developed from the K -nearest neighbour (KNN) algorithm).…”

Section: Organic Chemicals and Materialsmentioning

confidence: 99%

Atomic spectrometry update: review of advances in the analysis of metals, chemicals and materials

Clough,

Fisher,

Gibson

et al. 2023

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

Section: Organic Chemicals and Materialsmentioning

confidence: 99%

Atomic spectrometry update: review of advances in the analysis of metals, chemicals and materials

Clough,

Fisher,

Gibson

et al. 2023

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

“…Neighborhood component analysis (NCA) is one example for a non-paramagnetic feature selection algorithm introduced by Goldberger et al 7 It was improved through introduction of a regularization term by Yang et al, 8 and validated in real-world applications. 9,10 This algorithm can be used for feature selection but also simply to provide a gauge for importance of a feature for a particular response, as will be exploited herein.…”

Section: Introductionmentioning

confidence: 99%

Gauging the importance of structural parameters for hyperfine coupling constants in organic radicals

2023

View full text Add to dashboard Cite

show abstract

“…Recently, Sommer et al [35] studied the effect on the sample's surface and its depth profile for the weathering-induced oxidation of polystyrene target samples at different weathering times using the LIBS methodical tool. More recently, Nie et al [36] analyzed six various colored plastics such as POM, PP, ABS, PVC, PE, and PA using LIBS blended with (NCA) and support vector machine (SVM) statistical analysis. Therefore, the identification, classification, and characterization of polymers used in industries based on polymeric materials in different atmospheres and temperatures are significant.…”

Section: Introductionmentioning

confidence: 99%

Multi-Spectroscopic Characterization of MgO/Nylon (6/6) Polymer: Evaluating the Potential of LIBS and Statistical Methods

et al. 2023

View full text Add to dashboard Cite

The potential of using laser-induced breakdown spectroscopy (LIBS) in combination with various other spectroscopic and statistical methods was assessed for characterizing pure and MgO-doped nylon (6/6) organic polymer samples. The pure samples, obtained through a polycondensation chemical technique, were artificially doped with MgO prior to analysis for comparative purposes. These artificially doped samples served as crucial reference materials for comparative analysis and reference purposes. The LIBS studies were performed under local thermodynamic equilibrium (LTE) and optically thin plasma conditions. To assess the structural crystallinity of the nylon (6/6) polymer samples, X-ray diffraction (XRD) analysis, and Fourier transform infrared (FTIR) spectroscopy were employed to detect functional groups such as N-H, C-H, and C-N in the adsorbent polyamide nylon sample. Additionally, diffuse reflectance spectroscopy (DRS) analysis was conducted to investigate the effects of doping and temperature on the band gap and material reflectance across different sample temperatures. Chemical compositional analysis was performed using X-ray photoelectron spectroscopy (XPS) with the carbon C1s peak at 248.8 eV serving as a reference for spectrum calibration, along with energy-dispersive X-ray (EDX) analysis, which demonstrated good agreement between the techniques. To validate the different methodologies, the results obtained from CF-LIBS and EDX were compared with those from the standard inductively coupled plasma mass spectrometry (ICP-MS) technique. Finally, for classification analysis, principal component analysis (PCA) was applied to the LIBS spectral data at different sample temperatures (25 °C, 125 °C, 225 °C, and 325 °C). The analyses demonstrated that the combination of LIBS with PCA, along with other methods, presents a robust technique for polymer characterization.

show abstract

Identification of different colored plastics by laser-induced breakdown spectroscopy combined with neighborhood component analysis and support vector machine

Cited by 8 publications

References 15 publications

Atomic spectrometry update: review of advances in the analysis of metals, chemicals and materials

Atomic spectrometry update: review of advances in the analysis of metals, chemicals and materials

Gauging the importance of structural parameters for hyperfine coupling constants in organic radicals

Multi-Spectroscopic Characterization of MgO/Nylon (6/6) Polymer: Evaluating the Potential of LIBS and Statistical Methods

Contact Info

Product

Resources

About