Department of Anthropogenic Material Cycles, RWTH Aachen University, Germany.
Department of Anthropogenic Material Cycles, RWTH Aachen University, Germany.
Waste Manag. 2021 Dec;136:253-265. doi: 10.1016/j.wasman.2021.10.017. Epub 2021 Oct 26.
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-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-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-scores.
基于传感器的物料流特性（SBMC）有望通过实现自动质量监测或过程控制等新应用来提高下一代分拣厂的性能。这需要从基于像素的传感器数据推导出基于质量的物料流特性，这需要已知的单个颗粒质量。由于无法在线测量颗粒质量，因此研究了使用机器学习（ML）算法预测低密度包装（LWP）废物的颗粒质量。对五种 LWP 材料进行了采样、预处理和在定制的测试台上进行扫描，从而得到包含三维激光三角测量（3DLT）图像、RGB 图像和相应 n=3830 个颗粒质量的数据集。基于 66 个提取的形状测量值，为颗粒质量预测（PMP）训练了六个 ML 模型。使用（i）材料特定的平均颗粒质量和（ii）克重，将它们的性能与两个最先进的参考模型进行了比较。获得的颗粒质量在材料类别和颗粒尺寸类别之间具有很大的差异和显著差异。经过特征选择后，两个参考模型的 R 分数（i）为 0.422±0.121 和（ii）为 0.533±0.224，均优于所有研究的 ML 模型。随机森林回归器的 R 分数为 0.763±0.091，归一化平均绝对误差为 0.243±0.050，实现了最准确的 PMP。与对原始材料的研究相比，由于包装设计和消费后处理行为的影响，LWP 废物的 PMP 具有挑战性。ML 算法是一种很有前途的 PMP 方法，其 R 分数比最先进的方法高 43%。
