Classification of Black Plastics Waste Using Fluorescence Imaging and Machine Learning

Machine Learning Predictions of Oil Yields Obtained by Plastic Pyrolysis and Application to Thermodynamic Analysis

Chemical recycling via thermal processes such as pyrolysis is a potentially viable way to convert mixed streams of waste plastics into usable fuels and chemicals. Unfortunately, experimentally measuring product yields for real waste streams can be time- and cost-prohibitive, and the yields are very sensitive to feed composition, especially for certain types of plastics like poly(ethylene terephthalate) (PET) and polyvinyl chloride (PVC). Models capable of predicting yields and conversion from feed composition and reaction conditions have potential as tools to prioritize resources to the most promising plastic streams and to evaluate potential preseparation strategies to improve yields. In this study, a data set consisting of 325 data points for pyrolysis of plastic feeds was collected from the open literature. The data set was divided into training and test sub data sets; the training data were used to optimize the seven different machine learning regression methods, and the testing data were used to evaluate the accuracy of the resulting models. Of the seven types of models, eXtreme Gradient Boosting (XGBoost) predicted the oil yield of the test set with the highest accuracy, corresponding to a mean absolute error (MAE) value of 9.1%. The optimized XGBoost model was then used to predict the oil yields from real waste compositions found in Municipal Recycling Facilities (MRFs) and the Rhine River. The dependence of oil yields on composition was evaluated, and strategies for removing PET and PVC were assessed as examples of how to use the model. Thermodynamic analysis of a pyrolysis system capable of achieving oil yields predicted using the machine-learned model showed that pyrolysis of Rhine River plastics should be net exergy producing under most reasonable conditions.

Microbial Enzyme Biotechnology to Reach Plastic Waste Circularity: Current Status, Problems and Perspectives

The accumulation of synthetic plastic waste in the environment has become a global concern. Microbial enzymes (purified or as whole-cell biocatalysts) represent emerging biotechnological tools for waste circularity; they can depolymerize materials into reusable building blocks, but their contribution must be considered within the context of present waste management practices. This review reports on the prospective of biotechnological tools for plastic bio-recycling within the framework of plastic waste management in Europe. Available biotechnology tools can support polyethylene terephthalate (PET) recycling. However, PET represents only ≈7% of unrecycled plastic waste. Polyurethanes, the principal unrecycled waste fraction, together with other thermosets and more recalcitrant thermoplastics (e.g., polyolefins) are the next plausible target for enzyme-based depolymerization, even if this process is currently effective only on ideal polyester-based polymers. To extend the contribution of biotechnology to plastic circularity, optimization of collection and sorting systems should be considered to feed chemoenzymatic technologies for the treatment of more recalcitrant and mixed polymers. In addition, new bio-based technologies with a lower environmental impact in comparison with the present approaches should be developed to depolymerize (available or new) plastic materials, that should be designed for the required durability and for being susceptible to the action of enzymes.

Sensor-Based Technologies in Effective Solid Waste Sorting: Successful Applications, Sensor Combination, and Future Directions

The increase in global population and improvement of living standards have stirred up a continuous increase in solid waste generation, while simple incineration and landfilling bring about serious environmental and health concerns. In order to improve resource recovery and mitigate pollution, noncontacting and nondestructive sensor-based waste sorting systems are applied to enhance solid waste classification. In recent years, in addition to the rapid development of computer hardware, especially improvements of GPU computing capacity, complicated and efficient classification algorithms have emerged and been widely used in industrial sectors. These advances allow computers to process signals from sensors more quickly and accurately and to classify matters automatically. This article introduces widely applied sensor-based technologies in solid waste sorting and analyzes applicable conditions for each specific method. The latest developed algorithms are critically compared with competitive counterparts. Successful practices are described, and findings are highlighted. Though spectroscopic-based and vision-based waste classifications have achieved high performance in accuracy and detection speed, challenges and future directions can still provide wide development opportunities. Concretely, these opportunities generally comprise classification of indistinct plastics, application of the latest object detection algorithms, appropriate data set formulating, and sensor combination for multiple sorting tasks within a single system.

Development of an inter-confirmatory plastic characterization system using spectroscopic techniques for waste management

Ever-accumulating amounts of plastic waste raises alarming concern over environmental and public health. A practical solution for addressing this threat is recycling, and the success of an industry-oriented plastic recycling system relies greatly on the accuracy of the waste sorting technique adapted. We propose a multi-modal spectroscopic sensor which combines laser-induced breakdown spectroscopy (LIBS) and Raman spectroscopy in a single optical platform for characterizing plastics based on elemental and molecular information to assist the plastic identification-sorting process in recycling industries. The unique geometry of the system makes it compact and cost-effective for dual spectroscopy. The performance of the system in classifying industrially important plastic classes counting PP, PC, PLA, Nylon-1 1, and PMMA is evaluated, followed by the application of the same in real-world plastics comprising PET, HDPE, and PP in different chemical-physical conditions where the system consumes less than 30 ms for acquiring LIBS-Raman signals. The evaluation of the system in characterizing commuting samples shows promising results to be applied in industrial conditions in future. The study on effect of physical-chemical conditions of plastic wastes in characterizing them using the system shows the necessity for combining multiple techniques together. The proposal is not to determine the paramount methodology to characterize and sort plastics, but to demonstrate the advantages of dual-spectroscopy sensors in such applications. The outcomes of the study suggest that the system developed herein has the potential of emerging as an industrial-level plastic waste sorting sensor.

Optical sensors and machine learning algorithms in sensor-based material flow characterization for mechanical recycling processes: A systematic literature review

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.

Prediction of the Quality of Thermally Sprayed Copper Coatings on Laser-Structured CFRP Surfaces Using Hyperspectral Imaging

With the progressive replacement of metallic parts by high-performance fiber-reinforced plastic (FRP) components, typical properties of metals are required to be placed on the material’s surface. A metallic coating applied to the FRP surface by thermal spraying, for instance, can fulfill these requirements, including electrical conductivity. In this work, laser pre-treatments are utilized for increasing the bond strength of metallic coatings. However, due to the high-precision material removal using pulsed laser radiation, the production-related heterogeneous fiber distribution in FRP leads to variations in the structuring result and consequently to different qualities of the subsequent coating. In this study, hyperspectral imaging (HSI) technologies in conjunction with deep learning were applied to carbon fiber-reinforced plastics (CFRP) structured by nanosecond pulsed laser. HSI-based prediction models could be developed, which allow for reliable prediction, with an accuracy of around 80%, of which laser-treated areas will successfully be coated and which will not. By using this objective and automatic evaluation, it is possible to avoid large amounts of rejects before further processing the parts and also to optimize the adhesion of coatings. Spatially resolved data enables local reworking during the laser process, making it feasible for the manufacturing process to achieve zero waste.

Waste Management 4.0: An Application of a Machine Learning Model to Identify and Measure Household Waste Contamination—A Case Study in Australia

Waste management directly and indirectly contributes to all sustainable development goals. Hence, the modernisation of the current ineffective management system through Industry 4.0-compatible technologies is urgently needed. Inspired by the fourth industrial revaluation, this study explores the potential application of waste management 4.0 in a local government area in Perth, Western Australia. The study considers a systematic literature review as part of an exploratory investigation of the current applications and practices of Industry 4.0 in the waste industry. Moreover, the study develops and tests a machine learning model to identify and measure household waste contamination as a waste management 4.0 case study application. The study reveals that waste management 4.0 offers various opportunities and sustainability benefits in reducing costs, improving efficiency in the supply chain and material flow, and reducing as well as eliminating waste by achieving holistic circular economy goals. The significant barriers and challenges involve initial investments in developing and maintaining waste management 4.0 technology, platform and data acquisition. The proof-of-concept case study on the machine learning model detects selected waste with considerable precision (over 70% for selected items). The number and quality of the labelled data significantly influences the model’s accuracy. The data on waste contamination are essential for local governments to explore household waste recycling practices besides developing effective waste education and communication methods. The study concludes that waste management 4.0 can be an effective tool for acquiring real-time data; however, overcoming the current limitations needs to be addressed before applying waste management 4.0 into practice.

Extending Effective Dynamic Range of Hyperspectral Line Cameras for Short Wave Infrared Imaging

In this work, a multi-exposure method is proposed to increase the dynamic range (DR) of hyperspectral imaging using an InGaAs-based short-wave infrared (SWIR) hyperspectral line camera. Spectral signatures of materials were captured for scenarios in which the DR of a scene was greater than the DR of a line camera. To demonstrate the problem and test the proposed multi-exposure method, plastic detection in food waste and polymer sorting were chosen as the test application cases. The DR of the hyperspectral camera and the test samples were calculated experimentally. A multi-exposure method is proposed to create high-dynamic-range (HDR) images of food waste and plastic samples. Using the proposed method, the DR of SWIR imaging was increased from 43 dB to 73 dB, with the lowest allowable signal-to-noise ratio (SNR) set to 20 dB. Principal Component Analysis (PCA) was performed on both HDR and non-HDR image data from each test case to prepare the training and testing data sets. Finally, two support vector machine (SVM) classifiers were trained for each test case to compare the classification performance of the proposed multi-exposure HDR method against the single-exposure non-HDR method. The HDR method was found to outperform the non-HDR method in both test cases, with the classification accuracies of 98% and 90% respectively, for the food waste classification, and with 95% and 35% for the polymer classification.

Forecasting plastic waste generation and interventions for environmental hazard mitigation

Plastic waste and its environmental hazards have been attracting public attention as a global sustainability issue. This study builds a neural network model to forecast plastic waste generation of the EU-27 in 2030 and evaluates how the interventions could mitigate the adverse impact of plastic waste on the environment. The black-box model is interpreted using SHapley Additive exPlanations (SHAP) for managerial insights. The dependence on predictors (i.e., energy consumption, circular material use rate, economic complexity index, population, and real gross domestic product) and their interactions are discussed. The projected plastic waste generation of the EU-27 is estimated to reach 17 Mt/y in 2030. With an EU targeted recycling rate (55%) in 2030, the environmental impacts would still be higher than in 2018, especially global warming potential and plastic marine pollution. This result highlights the importance of plastic waste reduction, especially for the clustering algorithm-based grouped countries with a high amount of untreated plastic waste per capita. Compared to the other assessed scenarios, Scenario 4 with waste reduction (50% recycling, 47.6% energy recovery, 2.4% landfill) shows the lowest impact in acidification, eutrophication, marine aquatic toxicity, plastic marine pollution, and abiotic depletion. However, the global warming potential (8.78 Gt CO₂eq) is higher than that in 2018, while Scenario 3 (55% recycling, 42.6% energy recovery, 2.4% landfill) is better in this aspect than Scenario 4. This comprehensive analysis provides pertinent insights into policy interventions towards environmental hazard mitigation.

Review on the photonic techniques suitable for automatic monitoring of the composition of multi-materials wastes in view of their posterior recycling

In the increasingly pressing context of improving recycling, optical technologies present a broad potential to support the adequate sorting of plastics. Nevertheless, the commercially available solutions (for example, employing near-infrared spectroscopy) generally focus on identifying mono-materials of a few selected types which currently have a market-interest as secondary materials. Current progress in photonic sciences together with advanced data analysis, such as artificial intelligence, enable bridging practical challenges previously not feasible, for example in terms of classifying more complex materials. In the present paper, the different techniques are initially reviewed based on their main characteristics. Then, based on academic literature, their suitability for monitoring the composition of multi-materials, such as different types of multi-layered packaging and fibre-reinforced polymer composites as well as black plastics used in the motor vehicle industry, is discussed. Finally, some commercial systems with applications in those sectors are also presented. This review mainly focuses on the materials identification step (taking place after waste collection and before sorting and reprocessing) but in outlook, further insights on sorting are given as well as future prospects which can contribute to increasing the circularity of the plastic composites' value chains.

Technical Limits in Circularity for Plastic Packages

The current Dutch recycling value chain for plastic packaging waste (PPW) has not reached its full circularity potential, as is apparent from two Circular Performance Indicators (CPIs): net packaging recycling rate and average polymer purity of the recycled plastics. The performance of the recycling value chain can be optimised at four stages: packaging design, collection, sorting, and recycling. This study explores the maximally achievable performance of a circular PPW recycling value chain, in case all stakeholders would implement the required radical improvement measures in a concerted action. The effects of the measures were modelled with material flow analysis. For such a utopic scenario, a net plastic packaging recycling rate of 72% can be attained and the produced recycled plastics will have an average polymeric purity of 97%. This is substantially more than the net packaging recycling rate of 37% for 2017 and will exceed the EU target of 50% for 2025. In such an ideal circular value chain more recycled plastics are produced for more demanding applications, such as food packaging, compared to the current recycling value chain. However, all stakeholders would need to implement drastic and coordinated changes, signifying unprecedented investments, to achieve this optimal circular PPW recycling value chain.