Mid-infrared spectroscopy and machine learning for postconsumer plastics recycling
Mid-infrared spectroscopy and machine learning for postconsumer plastics recycling
复制标题
DOI：
10.1039/d3va00111c
复制
发表时间：
2023-08-01
期刊：
影响因子：
--
通讯作者：
Velarde，Luis
中科院分区：
文献类型：
--
作者：
Stavinski，Nicholas;Maheshkar，Vaishali;Velarde，Luis
如果要满足不断增长的回收需求，材料回收设施需要新的自动化技术。目前的光学筛选设备使用可见光（维斯）和近红外（NIR）波长，这些频率范围在消费后塑料废物（PCPW）的表征过程中可能会遇到挑战，因为染料和其他聚合物添加剂会过度吸收光谱带。这些技术瓶颈导致91%的塑料废物从未被回收利用。中红外（MIR）区域由于其相对于维斯和NIR的固有优势而引起了最近的关注。其中发现的基本振动模式使MIR频率有希望用于高保真机器学习（ML）分类。到目前为止，还没有对广泛的MIR光谱数据集进行ML评价，这些数据集反映了在MRF中会遇到的PCPW。本研究建立了可量化的指标，如模型准确性和预测时间，用于对综合MIR数据库进行分类，该数据库由五种具有经济意义的PCPW类别组成：聚对苯二甲酸乙二醇酯（PET #1），高密度聚乙烯（HDPE #2），低密度聚乙烯（LDPE #4），聚丙烯（PP #5）和聚苯乙烯（PS #6）。自动编码器是一种无监督的ML算法，应用于随机森林（RF），k-最近邻（KNN），支持向量机（SVM）和逻辑回归（LR）模型。RF模型在C-H伸缩区（2990 - 2820 cm − 1）和分子指纹区（1500 - 650 cm − 1）均达到100.0%的准确度。发现C-H伸缩区域不含导致其他区域错误分类的添加剂，使其成为未来PCPW分选技术的富有成效的频率范围。还首次评估了使用ML自动编码器对黑色塑料和聚乙烯PCPW进行MIR分类。
Materials recovery facilities (MRFs) require new automated technologies if growing recycling demands are to be met. Current optical screening devices use visible (VIS) and near-infrared (NIR) wavelengths, frequency ranges that can experience challenges during the characterization of postconsumer plastic waste (PCPW) because of the overly-absorbing spectral bands from dyes and other polymer additives. Technological bottlenecks such as these contribute to 91% of plastic waste never actually being recycled. The mid-infrared (MIR) region has attracted recent attention due to inherent advantages over the VIS and NIR. The fundamental vibrational modes found therein make MIR frequencies promising for high fidelity machine learning (ML) classification. To-date, there are no ML evaluations of extensive MIR spectral datasets reflecting PCPW that would be encountered at MRFs. This study establishes quantifiable metrics, such as model accuracy and prediction time, for classification of a comprehensive MIR database consisting of five PCPW classes that are of economic interest: polyethylene terephthalate (PET #1), high-density polyethylene (HDPE #2), low-density polyethylene (LDPE #4), polypropylene (PP #5), and polystyrene (PS #6). Autoencoders, an unsupervised ML algorithm, were applied to the random forest (RF), k-nearest neighbor (KNN), support vector machine (SVM), and logistic regression (LR) models. The RF model achieved accuracies of 100.0% in both the C–H stretching region (2990–2820 cm−1) and molecular fingerprint region (1500–650 cm−1). The C–H stretching region was found to be free from additives that were responsible for misclassification in other regions, making it a fruitful frequency range for future PCPW sorting technologies. The MIR classification of black plastics and polyethylene PCPW using ML autoencoders was also evaluated for the first time.