Hyperspectral imaging applied to demolition waste: recycled products quality control

The development of innovative construction and demolition (C&D) waste recycling technology in order to create high-value "green concrete" and the replacement of primary raw materials through End-Of-Life (EOL) concrete are two of the most important problems to face and solve in the secondary raw materials sector. The possibility to realize, implement and set-up efficient sorting and/or quality control strategies for the collection of information concerning C&D waste materials, plays an important role to perform non-destructive, rapid and low cost analyses finalized to preliminary detect and characterize the materials constituting C&D waste stream. The main aim of this study is a C&D waste characterization adopting an HyperSpectral Imaging (HSI) based approach. This technique was specifically applied in order to recognize concrete aggregates and other materials considered as contaminants. The developed procedures are based on the utilization of a laboratory device working in the near infrared range (1000-1700 nm): NIR Spectral Camera™, embedding an ImSpector™ N17E (SPECIM Ltd, Finland). Acquired hyperspectral images were analyzed adopting the PLS_Toolbox (Version 7.8, Eigenvector Research, Inc.) running into the Matlab® environment (Version 7.11.1, The Mathworks, Inc.). Different chemometric methods were applied: Principal Component Analysis (PCA) for exploratory data approach and Partial Least Square- Discriminant Analysis (PLS-DA) to build classification models. Starting from a reference ‘training image set’, spectra representative of materials constituting the C&D waste stream have been preliminary collected in order to define the classification algorithm. The developed classification procedure was then validated using external datasets. Results showed as, with the proposed approach, recycled aggregates can be identified and distinguished from contaminants (e.g. bricks, gypsum, plastics, wood, foam, etc.). The developed procedure based on HSI in the NIR range can be applied for quality control of recycled aggregates to be used in new concrete production.