DETECTING CONTAMINANTS IN POST-CONSUMER PLASTIC PACKAGING WASTE BY A NIR HYPERSPECTRAL IMAGING-BASED CASCADE DETECTION APPROACH

Recycling of post-consumer packaging wastes involves a complex chain of activities, usually based on three main stages, that is: i) collection from households or recovery from Municipal solid waste (MSW), ii) sorting and, finally, iii) mechanical recycling. The systematic identification of impurities inside plastic packaging waste streams, and the assessment of the different occurring materials, can be considered as one of the key issues to certify and to classify waste materials fed to recycling plants and to perform a full control of the resulting processed fractions and byproducts, that have to comply with market demands. The utilization of a Near InfraRed (NIR) – HyperSpectral Imaging (HSI) based methods, along with chemometrics and machine learning techniques, can fulfill these goals. In this paper, the HSI-based sorting logics, to apply, to implement and to set up to perform an automatic separation of paper, cardboard, plastics and multilayer packaging are investigated.

Download Full-text

Hierarchical modelling for recycling-oriented classification of shredded spent flat monitor products based on HyperSpectral Imaging

Detritus ◽

10.31025/2611-4135/2020.14031 ◽

2020 ◽

pp. 122-130

Author(s):

Giuseppe Bonifazi ◽

Riccardo Gasbarrone ◽

Roberta Palmieri ◽

Silvia Serranti

Keyword(s):

Hyperspectral Imaging ◽

High Performance ◽

Near Infrared ◽

Low Cost ◽

Volume Growth ◽

Growth Trend ◽

Hierarchical Modelling ◽

Physical Chemical ◽

Chemical Attributes ◽

Set Up

The number of flat monitors from televisions, notebooks and tablets has increased dramatically in recent years, thus resulting in a corresponding rise in Waste from Electrical and Electronic Equipment (WEEE). This fact is linked to the production of new high-performance electronic devices. Taking into account a future volume growth trend of WEEE, the implementation of adequate recycling architectures embedding recognition/classification logics to handle the collected WEEE physical-chemical attributes, is thus necessary. These integrated hardware and software architectures should be efficient, reliable, low cost, and capable of performing detection/control actions to assess: i) WEEE composition and ii) physical-chemical attributes of the resulting recovered flow streams. This information is fundamental in setting up and implementing appropriate recycling actions. In this study, a hierarchical classification modelling approach, based on Near InfraRed (NIR) - Hyperspectral Imaging (HSI), was carried out. More in detail, a 3-step hierarchical modelling procedure was designed, implemented and set up in order to recognize different materials present in a specific WEEE stream: End-of-Life (EoL) shredded monitors and flat screens. By adopting the proposed approach, different categories are correctly recognized. The results obtained showed how the proposed approach not only allows the set up of a “one shot” quality control system, but also contributes towards improving the sorting process.

Download Full-text

Near infrared hyperspectral imaging-based approach for end-of-life flat monitors recycling

at - Automatisierungstechnik ◽

10.1515/auto-2019-0058 ◽

2020 ◽

Vol 68 (4) ◽

pp. 265-276 ◽

Cited By ~ 1

Author(s):

Giuseppe Bonifazi ◽

Riccardo Gasbarrone ◽

Roberta Palmieri ◽

Silvia Serranti

Keyword(s):

End Of Life ◽

Hyperspectral Imaging ◽

Near Infrared ◽

Low Cost ◽

Rapid Change ◽

Identification Approach ◽

Important Amount ◽

Chemical Attributes ◽

Improved Performance ◽

Set Up

AbstractThe technological innovation and the relentless marketing of new electronic products with improved performance generate increasing quantities of Waste from Electrical and Electronic Equipment (WEEE). In this scenario, End-Of-Life (EOL) flat monitors and screens represent a category generating, as a consequence of the rapid change in technology, an important amount of waste. Considering future estimations, the implementation of an adequate recycling infrastructure is necessary. An efficient, reliable and low-cost analytical tool is thus needed to perform detection/control actions in order to assess: i) waste composition and ii) physical-chemical attributes of the resulting materials. The knowledge of these information is a requirement to set-up and to implement correct recycling actions.In this study, a cascade identification approach, based on Near InfraRed (NIR) – HyperSpectral Imaging (HSI), was carried out. More in detail, a four-steps classification was designed, implemented and set-up in order to recognize different materials occurring in a specific WEEE stream: EOL milled monitors and flat screens. Adopting the proposed approach, different material categories are correctly recognized and classified. Obtained results can be useful not only to set-up a quality control system, but also to improve sorting actions in this specific recycling sector.

Download Full-text

Application of Visible/Infrared Spectroscopy and Hyperspectral Imaging With Machine Learning Techniques for Identifying Food Varieties and Geographical Origins

Frontiers in Nutrition ◽

10.3389/fnut.2021.680357 ◽

2021 ◽

Vol 8 ◽

Author(s):

Lei Feng ◽

Baohua Wu ◽

Susu Zhu ◽

Yong He ◽

Chu Zhang

Keyword(s):

Machine Learning ◽

Infrared Spectroscopy ◽

Hyperspectral Imaging ◽

Food Quality ◽

Near Infrared ◽

Imaging Techniques ◽

Machine Learning Techniques ◽

Research Progress ◽

Food Fraud ◽

Learning Techniques

Food quality and safety are strongly related to human health. Food quality varies with variety and geographical origin, and food fraud is becoming a threat to domestic and global markets. Visible/infrared spectroscopy and hyperspectral imaging techniques, as rapid and non-destructive analytical methods, have been widely utilized to trace food varieties and geographical origins. In this review, we outline recent research progress on identifying food varieties and geographical origins using visible/infrared spectroscopy and hyperspectral imaging with the help of machine learning techniques. The applications of visible, near-infrared, and mid-infrared spectroscopy as well as hyperspectral imaging techniques on crop food, beverage, fruits, nuts, meat, oil, and some other kinds of food are reviewed. Furthermore, existing challenges and prospects are discussed. In general, the existing machine learning techniques contribute to satisfactory classification results. Follow-up researches of food varieties and geographical origins traceability and development of real-time detection equipment are still in demand.

Download Full-text

Techno-economic assessment of mechanical recycling of challenging post-consumer plastic packaging waste

Resources Conservation and Recycling ◽

10.1016/j.resconrec.2021.105607 ◽

2021 ◽

Vol 170 ◽

pp. 105607

Author(s):

Macarena Larrain ◽

Steven Van Passel ◽

Gwenny Thomassen ◽

Bart Van Gorp ◽

Trang T. Nhu ◽

...

Keyword(s):

Economic Assessment ◽

Mechanical Recycling ◽

Plastic Packaging ◽

Packaging Waste

Download Full-text

First steps to set up a methodology for the citrus yield estimation using a visible/near infrared hyperspectral imaging system

Sensing for Agriculture and Food Quality and Safety XII ◽

10.1117/12.2559102 ◽

2020 ◽

Author(s):

Irina Torres ◽

María-Teresa Sánchez ◽

Byoung-Kwan Cho ◽

Ana Garrido-Varo ◽

Dolores C. Pérez-Marín

Keyword(s):

Hyperspectral Imaging ◽

Near Infrared ◽

Imaging System ◽

Yield Estimation ◽

Set Up

Download Full-text

Pork Tissue Recognition Using Visible and Near Infrared Hyperspectral Imaging

2020 International Computer Symposium (ICS) ◽

10.1109/ics51289.2020.00084 ◽

2020 ◽

Author(s):

Chih-Cheng Pai ◽

Yang-Chu Chen ◽

Keng-Hao Liu ◽

Yuan-Hsun Tsai ◽

Po-Chi Hu ◽

...

Keyword(s):

Hyperspectral Imaging ◽

Near Infrared

Download Full-text

Green recycling of aluminum plastic packaging waste by solid‐state shear milling and 3D printing for thermal conductive composites

Polymers for Advanced Technologies ◽

10.1002/pat.5289 ◽

2021 ◽

Author(s):

Baojie Wei ◽

Shuangqiao Yang ◽

Qi Wang

Keyword(s):

Solid State ◽

3D Printing ◽

Plastic Packaging ◽

Conductive Composites ◽

Packaging Waste

Download Full-text

Identification of peat type and humification by laboratory VNIR/SWIR hyperspectral imaging of peat profiles with focus on fen-bog transition in aapa mires

Plant and Soil ◽

10.1007/s11104-020-04775-y ◽

2020 ◽

Author(s):

L. Granlund ◽

M. Keinänen ◽

T. Tahvanainen

Keyword(s):

Hyperspectral Imaging ◽

Near Infrared ◽

Support Vector ◽

High Resolution Imaging ◽

Factors Affecting ◽

Vector Machines ◽

Resolution Imaging ◽

Shortwave Infrared ◽

Type Classification ◽

Wide Potential

Abstract Aims Hyperspectral imaging (HSI) has high potential for analysing peat cores, but methodologies are deficient. We aimed for robust peat type classification and humification estimation. We also explored other factors affecting peat spectral properties. Methods We used two laboratory setups: VNIR (visible to near-infrared) and SWIR (shortwave infrared) for high resolution imaging of intact peat profiles with fen-bog transitions. Peat types were classified with support vector machines, indices were developed for von Post estimation, and K-means clustering was used to analyse stratigraphic patterns in peat quality. With separate experiments, we studied spectral effects of drying and oxidation. Results Despite major effects, oxidation and water content did not impede robust HSI classification. The accuracy between Carex peat and Sphagnum peat in validation was 80% with VNIR and 81% with SWIR data. The spectral humification indices had accuracies of 82% with VNIR and 56%. Stratigraphic HSI patterns revealed that 36% of peat layer shifts were inclined by over 20 degrees. Spectral indices were used to extrapolate visualisations of element concentrations. Conclusions HSI provided reliable information of basic peat quality and was useful in visual mapping, that can guide sampling for other analyses. HSI can manage large amounts of samples to widen the scope of detailed analysis beyond single profiles and it has wide potential in peat research beyond the exploratory scope of this paper. We were able to confirm the capacity of HSI to reveal shifts of peat quality, connected to ecosystem-scale change.

Download Full-text