Sensor-based particle mass prediction of lightweight packaging waste using machine learning algorithms. (December 2021)

• Record Type: Journal Article
• Authors: Kroell, Nils; Chen, Xiaozheng; Maghmoumi, Abtin; Koenig, Morgane; Feil, Alexander; Greiff, Kathrin
• Is Part Of: Waste management. Volume 136(2021)
• Page Start: 253
• Page End: 265
• Publication Date: 2021-12
• Subjects: Sensor-based material flow characterization -- Particle mass prediction -- Lightweight packaging waste -- 3D laser triangulation -- Machine learning -- Shape measurements; 3DLT 3D laser triangulation -- BC beverage carton -- CNN convolutional neural network -- DT decision tree regressor -- kNN k-nearest neighbor regressor -- LWP lightweight packaging -- MFC material flow characteristic -- ML machine Learning -- NF non-ferrous metals -- NIR near-infrared -- PCA principal component analysis -- PCC Pearson correlation coefficient -- PE polyethylene -- PLS partial least squares -- PMP particle mass prediction -- PP polypropylene -- PPC paper and cardboard -- PSC particle size class -- PSD particle size distribution -- RF random forest regressor -- RM reference model -- RQ research question -- SBMC sensor-based material flow characterization -- SCC Spearman correlation coefficient -- SRF solid recovered fuel -- SVR support vector regressor; Hazardous wastes -- Periodicals; Refuse and refuse disposal -- Periodicals; 363.728
• DOI: 10.1016/j.wasman.2021.10.017
• Languages: English
• ISSNs: 0956-053X

Abstract

Graphical abstract: Highlights: Dataset containing 3, 830 particles from lightweight packaging waste created. Particle masses vary significantly between material and particle size classes. Volume-equivalent diameter correlates best with particle mass. Best machine learning model outperforms state-of-the-art by 43% higher R 2 -score. Random forest regressor achieves best mass predictions with R 2 = 0.763 ± 0.091. Abstract: Sensor-based material flow characterization (SBMC) promises to improve the performance of future-generation sorting plants by enabling new applications like automatic quality monitoring or process control. Prerequisite for this is the derivation of mass-based material flow characteristics from pixel-based sensor data, which requires known individual particle masses. Since particle masses cannot be measured inline, the prediction of particle masses of lightweight packaging (LWP) waste using machine learning (ML) algorithms is investigated. Five LWP material classes were sampled, preprocessed, and scanned on a custom-made test rig, resulting in a dataset containing 3D laser triangulation (3DLT) images, RGB images, and corresponding masses of n = 3, 830 particles. Based on 66 extracted shape measurements, six ML models were trained for particle mass prediction (PMP). Their performance was compared with two state-of-the-art reference models using (i) material-specific mean particle masses and (ii) grammages. Obtained particle masses showed a high variation and significant differences between material classes and particle size classes. After feature selection, both reference models achieving R 2 -scores of (i) 0.422 ± 0.121 and (ii) 0.533 ± 0.224 were outperformed by all investigated ML models. A random forest regressor with an R 2 -score of 0.763 ± 0.091 and a normalized mean absolute error of 0.243 ± 0.050 achieved the most accurate PMP. In contrast to studies on primary raw materials, PMP of LWP waste is challenging due to influences of packaging design and post-consumer disposal behavior. ML algorithms are a promising approach for PMP that outperform state-of-the-art methods by 43% higher R 2 -scores.