Optical sensors and machine learning algorithms in sensor-based material flow characterization for mechanical recycling processes: A systematic literature review. (15th July 2022)

• Record Type: Journal Article
• Authors: Kroell, Nils; Chen, Xiaozheng; Greiff, Kathrin; Feil, Alexander
• Is Part Of: Waste management. Volume 149(2022)
• Page Start: 259
• Page End: 290
• Publication Date: 2022-07-15
• Subjects: Sensor-based material flow characterization -- Sensor-based sorting -- Mechanical recycling -- Optical sensors -- Machine learning -- Digitalization; 1D One-dimensional -- 3DLT 3D laser triangulation -- ABS Acrylonitrile butadiene styrene -- Al Aluminum -- ANN Artificial neural network -- ASR Automotive shredder residue -- Au Gold -- BC Beverage carton -- BN Bayesian network -- CBR Case based reasoning -- CDW Construction and demolition waste -- CNN Convolutional neural network -- CRF Conditional random field -- CT Complementary troubleshooting -- Cu Copper -- CuZn Brass -- CVA Canonical variate analysis -- DBC Dissimilarity-based classifier -- DT Decision tree -- ELV End-of-life vehicles -- eMFC Extensive MFC -- F False -- Fe Iron -- Fuzzy Fuzzy based algorithm -- GA Genetic algorithm -- GMM Gaussian mixture models -- GPC Gaussian process classifier -- HD High-density -- HIPS High Impact PS -- HSI Hyperspectral imaging -- ICA Independent component analysis -- iMFC Intensive MFC -- IR Infrared -- kNN k nearest neighbors -- LD Low-density -- LDA Linear discriminant analysis -- LEMAP Laplacian Eigenmaps -- LIBS Laser-induced breakdown spectroscopy -- LIDAR Light detection and ranging -- LIF Laser-induced fluorescence -- Linear Linear regression -- LWP Lightweight packaging waste -- MAE Mean absolute error -- MAP Maximum a posteriori estimation -- MCW Mixed commercial waste -- MFC Material flow characteristic -- MIR Mid-infrared -- ML Machine learning -- MLR Multinomial logistic regression -- MSW Mixed solid waste -- N Negative -- NC Nearest centroid -- Ni Nickel -- NIR Near-infrared -- P Positive -- PA Polyamide -- PBT Polybutylene terephthalate -- PC Polycarbonate -- PCA Principal component analysis -- PE Polyethylene -- PET Polyethylene terephthalate -- PLS Partial least squares -- PMMA Polymethylmethacrylate -- POM Polyoxymethylene -- PP Polypropylene -- PPC Paper, paperboard, and cardboard -- PPS Polyphenylene sulfide -- PS Polystyrene -- PSD Particle size distribution -- PVC Polyvinylchloride -- PVDF Polyvinyliden fluoride -- QA Quality assessment -- QDA Quadratic discriminant analysis -- RAMAN Raman spectroscopy -- RDA Resemblance discriminate analysis -- RF Random forest -- RGB Red green blue -- RMSE Root mean square error -- RQ Research question -- SAM Spectral angle mapper -- SBMC sensor-based material flow characterization -- SBMM sensor-based material flow monitoring -- SBPC Sensor-based process control -- SBPM Sensor-based process monitoring -- SBPM/C SBPM or SBPC -- SBQC Sensor-based quality control -- SBR Styrene-butadiene rubber -- SBS sensor-based sorting -- SCC Spectral cross-correlation -- SIMCA Soft independent modelling by class analogy -- SOM Self-organized map -- SVD Singular value decomposition -- SVM Support vector machine -- T True -- TEEE Thermoplastic elastomer-ether-ester -- THz Terahertz -- TPE Thermoplastic elastomers -- TPU Thermoplastic polyurethane -- TRL Technological readiness level -- UV Ultraviolet -- VIS Visible -- ViT Vision transformer -- VNIR VIS-NIR -- WEEE Waste from electrical and electronic equipment; Hazardous wastes -- Periodicals; Refuse and refuse disposal -- Periodicals; 363.728
• DOI: 10.1016/j.wasman.2022.05.015
• Languages: English
• ISSNs: 0956-053X

Abstract

Highlights: Systematic literature review of 198 peer-reviewed journal articles. Proposal of unified sensor-based material flow characterization (SBMC) terminology. Elaborate overview on machine learning (ML) implementation in SBMC. Innovative ML algorithm comparison based on Elo ratings adapted from chess games. Identification and discussion of ten future research potentials in SBMC. Abstract: Digital technologies hold enormous potential for improving the performance of future-generation sorting and processing plants; however, this potential remains largely untapped. Improved sensor-based material flow characterization (SBMC) methods could enable new sensor applications such as adaptive plant control, improved sensor-based sorting (SBS), and more far-reaching data utilizations along the value chain. This review aims to expedite research on SBMC by (i) providing a comprehensive overview of existing SBMC publications, (ii) summarizing existing SBMC methods, and (iii) identifying future research potentials in SBMC. By conducting a systematic literature search covering the period 2000 – 2021, we identified 198 peer-reviewed journal articles on SBMC applications based on optical sensors and machine learning algorithms for dry-mechanical recycling of non-hazardous waste. The review shows that SBMC has received increasing attention in recent years, with more than half of the reviewed publications published between 2019 and 2021. While applications were initially focused solely on SBS, the last decade has seen a trend toward new applications, including sensor-based material flow monitoring, quality control, and process monitoring/control. However, SBMC at the material flow and process level remains largely unexplored, and significant potential exists in upscaling investigations from laboratory to plant scale. Future research will benefit from a broader application of deep learning methods, increased use of low-cost sensors and new sensor technologies, and the use of data streams from existing SBS equipment. These advancements could significantly improve the performance of future-generation sorting and processing plants, keep more materials in closed loops, and help paving the way towards circular economy.