近红外光谱的通用聚苯乙烯牌号在线识别方法

doi:10.3964/j.issn.1000-0593(2021)09-2759-05

Abstract
References
Related Citation (15)

Download: PDF (2815 KB)
Export: BibTeX | EndNote (RIS)

Abstract Misusing the wrong grades polymer during the polymer processing in the same production line may lead to poorer product performance and a lower qualification ratio. The traditional methods identifying the grades from same kind of polymer are usually time consuming and hysteretic. There has not yet been discovered a fast and real time method for grade identification. In this work, 5 different grades of GPPS were the research object. An in-line near-infrared spectral measurement system installed on the extruder was developed. Near-infrared spectroscopy was combined with chemometrics and machine learning algorithms. The different grades of GPPS could be fast and in-line identified during the extrusion process. First, the in- line near-infrared spectra of GPPS melts of 5 different grades were collected in real time by the developed system with a spectral range of 900~1 700 nm. After spectrum analysis, a K-means clustering algorithm in combination with PCA was performed to verify the distinguishability of in-line near-infrared spectra for different grades. Last, PLS-DA and RF algorithm were used to establish the grade identification models respectively, and the identification ability of these two models was compared. The results show that: ①After baseline correction, maximum and minimum normalization, and 7-point moving average smoothing, the characteristic peak values at 1 207，1 388，1 407, 1 429 nm of the in-line near-infrared spectra change in a step-like manner with the change of grades. With the first three principal components scores as input variables, the clustering accuracy by K-means can reach 88%. It shows the distinguishability of the in-line near-infrared spectral data of different grades of GPPS; ②The two prediction models established by PLS-DA and RF can both effectively identify the grades of GPPS. The classification accuracy on the validation set of the PLS-DA model with the optimal principal components of 3 can reach 90.4%. The classification accuracy on the validation set of the RF model with the first five principal components as input variables can reach 95.6%. The RF model shows better grade identification performance than that of the PLS-DA model. Therefore, combined with chemometrics and machine learning algorithms, the in-line near-infrared spectral measurement system can realize the rapid and in-line identification of GPPS grades. It provides a reference for the in-line identification of different grades of the same kind of polymer by near-infrared spectroscopy in a production line.

Key words：Near-infrared spectroscopy; Grade identification; General purpose polystyrene; Partial least square-discriminant analysis; Random forest

Received: 2020-08-24 Accepted: 2020-12-21

ZTFLH:

O657

Corresponding Authors: JIN Gang E-mail: pmrdd@scut.edu.cn

Cite this article:

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2021)09-2759-05 OR https://www.gpxygpfx.com/EN/Y2021/V41/I09/2759

[1] CHEN Le-yi(陈乐怡). Synthetic Resins and Plastic Grades Manual(合成树脂及塑料牌号手册). Beijing: China Petrochemical Press(北京: 中国石化出版社), 2003.
[2] CHU Xiao-li(褚小立). Molecular Spectroscopy Analytical Technology Combined With Chemometrics and Its Application(化学计量学方法与分子光谱分析技术). Beijing: Chemical Industry Press(北京: 化学工业出版社), 2011. 10+259.
[3] Mclauchlin A R, Ghita O, Gahkani A. Polymer Testing, 2014, 38(18): 46.
[4] LI Wen-huan, JIN Shang-zhong, CHEN Ling-ling, et al(李文环, 金尚忠, 陈玲玲, 等). China Plastics Indusrty(塑料工业), 2016, 44(12): 124.
[5] Rani M, Marchesi C, Federici S, et al. Materials, 2019, 12(17): 2740.
[6] Kaihara M, Satoh M. Analytical Sciences, 2007, 23(7): 921.
[7] HAO Yong, WEN Qin-hua, RAO Min, et al(郝勇, 温钦华, 饶敏, 等). Food and Machinery(食品与机械), 2018, 34(4): 124.
[8] ZHU Shi-chao, YOU Jian, JIN Gang, et al(朱世超, 游剑, 晋刚, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(10): 71.
[9] WU Xiao-yu, LI Jia, YAO Lin-ping, et al. Journal of Cleaner Production, 2020, 246: 118732.
[10] Camastra F, Verri A. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5): 801.
[11] SUN Cheng, WANG Wei, LIU Fang-tian, et al(孙成, 王卫, 刘方田, 等). Research of Environmental Sciences(环境科学研究), 2019, 32(9): 1500.
[12] Zacharis N Z. International Journal of Intelligent Systems and Applications, 2018, 10(3): 1.
[13] Yariyan P, Janizadeh S, Phong T V, et al. Water Resources Management, 2020, 34: 3037.
[14] Breiman L. Machine Learning, 2001, 45(1): 5.
[15] Ballabio D, Consonni V. Analytical Methods, 2013, 5(16): 3790.
[16] XU Hao-ran, XU Bo, XU Ke-wen(徐浩然, 许波, 徐可文). Computer Engineering and Applications(计算机工程与应用), 2020, 56(12): 19.