Giuseppe Bonifazi

Classification of oat and groat kernels using NIR hyperspectral imaging.

An innovative procedure to classify oat and groat kernels based on coupling hyperspectral imaging (HSI) in the near infrared (NIR) range (1006-1650 nm) and chemometrics was designed, developed and validated. According to market requirements, the amount of groat, that is the hull-less oat kernels, is one of the most important quality characteristics of oats. Hyperspectral images of oat and groat samples have been acquired by using a NIR spectral camera (Specim, Finland) and the resulting data hypercubes were analyzed applying Principal Component Analysis (PCA) for exploratory purposes and Partial Least Squares-Discriminant Analysis (PLS-DA) to build the classification models to discriminate the two kernel typologies. Results showed that it is possible to accurately recognize oat and groat single kernels by HSI (prediction accuracy was almost 100%). The study demonstrated also that good classification results could be obtained using only three wavelengths (1132, 1195 and 1608 nm), selected by means of a bootstrap-VIP procedure, allowing to speed up the classification processing for industrial applications. The developed objective and non-destructive method based on HSI can be utilized for quality control purposes and/or for the definition of innovative sorting logics of oat grains.

Characterisation of flotation froth colour and structure by machine vision

It is well known and well recognised that flotation is a process that is complex to monitor and study if a classical approach based on the evaluation of the signals resulting from sensors is adopted. Sensors are usually strategically positioned in the bank cells and detect global process variables such as pH, reagent addition, froth level, on-stream chemical analysis, particle size distribution, etc. In the last ten years several studies have been carried out with the main goal to utilise imaging techniques to detect froth bubbles characteristics and to evaluate the flotation process performance. In this paper an approach of this type is described. More specifically, image processing techniques to automatically measure the colour and the structure of the froth bubbles are presented and the results are discussed. All the investigations are carried out on digital sample images collected in an industrial flotation plant operating in steady-state conditions. The colour analysis is performed on the whole surface of the froth images considering different colour reference systems (RGB, HSV, HSI); the morphological measurements are obtained after the application of selected enhancement and segmentation techniques, necessary to consider the bubbles as separate domains. The multiple correlation analysis performed between froth mineral concentrations (Cu, MgO, Zn and Pb content) and the extracted colour and structure parameters are good in most situations.

Surface Investigation of Photo-Degraded Wood by Colour Monitoring, Infrared Spectroscopy, and Hyperspectral Imaging

The aim of this investigation is to study the changes occurring on the surface of poplar wood exposed to artificial irradiation in a Solar Box. Colour changes were monitored with a reflectance spectrophotometer. Surface chemical modifications were evaluated by measuring the infrared spectra. Hyperspectral imaging was also applied to study the surface wood changes in the visible-near infrared and the short wave infrared wavelength ranges. The data obtained from the different techniques were compared to find the possible correlations in order to evaluate the applicability of the Hyperspectral imaging to investigate wood modifications in a non-invasive modality. The study of colour changes showed an important variation due to photo-irradiation which is the greatest change occurring within the first 24 hours. Infrared spectroscopy revealed that lignin degrades mainly in the first 48 hours. Concerning Hyperspectral imaging, the spectral features in the visible-near infrared range are mainly linked to the spectral shape, whereas in the short wave infrared cellulose and lignin affect shape and reflectance levels. The proposed approach showed that a correlation can be established between colour variation and wood degradation in the visible-near infrared range; furthermore in the short wave infrared region surface chemical changes can be assessed.

Hyperspectral imaging for process and quality control in recycling plants of polyolefin flakes

Hyperspectral imaging in the near infrared range (1000–1700 nm) was evaluated to identify different polyolefin flakes for quality assessment of recycled products. According to market requirements, the output of the recycling process of polyolefins must be high purity secondary polypropylene and polyethylene granulates. Hyperspectral images were acquired for selected plastic flakes coming from household waste, classified according to their typology. Spectra were analysed using principal component analysis to reduce the high dimensionality of data and for selecting effective wavelengths. Partial least square discriminant analysis was applied for classification of the two polyolefin typologies. Prediction results showed that it is possible to recognise the different plastic flakes with sensitivity and specificity ranging from 0.90 to 0.99. The developed procedures based on hyperspectral imaging can be utilised for quality control of the two pure polypropylene and polyethylene flow streams obtained by the innovative recycling process based on magnetic density separation.

An innovative recycling process to obtain pure polyethylene and polypropylene from household waste.

An innovative recycling process, based on magnetic density separation (MDS) and hyperspectral imaging (HSI), to obtain high quality polypropylene and polyethylene as secondary raw materials, is presented. More in details, MDS was applied to two different polyolefin mixtures coming from household waste. The quality of the two separated PP and PE streams, in terms of purity, was evaluated by a classification procedure based on HSI working in the near infrared range (1000-1700 nm). The classification model was built using known PE and PP samples as training set. The results obtained by HSI were compared with those obtained by classical density analysis carried in laboratory on the same polymers. The results obtained by MDS and the quality assessment of the plastic products by HSI showed that the combined action of these two technologies is a valid solution that can be implemented at industrial level.

Prediction of complex sulfide flotation performances by a combined 3D fractal and colour analysis of the froths

Abstract It has long been accepted that froth appearance is a good qualitative indicator of the performance of the flotation process. This paper investigates the possibility of the froth surface 3D reconstruction that can provide significant information about the process efficiency. The froth 3D model was realised performing a preliminary watershed segmentation of the image, a further morphological and morphometrical analysis and finally building a series of “domes” founded on the equivalent ellipses of the identified bubbles. Height and curvature of the resulting ellipsoids were defined analysing light intensity distribution inside each identified domain (bubble). The technique developed generates an elevation model of the surface that is then analysed by a fractal method. The froth surface showed two fractal dimensions that can be used, along with froth colour parameters, to forecast mineral grades of the froths.

Recycling-oriented characterization of polyolefin packaging waste.

Packaging waste is one of the main sources of secondary polyolefins. It is essential to characterize polyolefins derived from this waste stream in such way, that not only mechanical sorting methods can effectively separate, but also that on-line sensor systems can quantitatively assess their distribution. The characterization methodology is hierarchical, relating all properties of waste particles in any phase of the processing ultimately to the input End-Of-Life products. The present paper documents a pre-concentrate obtained by hand picking of mixed Romanian household waste. Investigations have been addressed to identify the composition of this polyolefin waste stream, to study the polyolefin density distribution, to distinguish the polymer manufacturing methods (i.e. injection molding and blow molding) by flake physical properties and finally to perform all the required characterization and identification by hyperspectral imaging. On the basis of these analyses, polyolefins from packaging wastes can be recycled by density separation and their rheological properties and wall thickness indicate the molding procedures. Hyperspectral imaging based procedures have been also applied to set up quality control actions for recycled products.

Micro-scale energy valorization of grape marcs in winery production plants.

The Biochemical Methane Potential (BMP) of winery organic waste, with reference to two Italian red and white grapes (i.e. Nero Buono and Greco) by-products was investigated. The study was carried out to verify the possibility to reduce the production impact in a green-waste-management-chain-perspective. The possibility to efficiently utilize wine-related-by-products for energy production at a micro-scale (i.e. small-medium scale winery production plant) was also verified. Results showed as a good correlation can be established between the percentage of COD removal and the biogas production, as the winery can produce, from its waste methanization, about 7800 kW h year(-1) electrical and 8900 kW h year(-1) thermal. A critical evaluation was performed about the possibility to utilize the proposed approach to realize an optimal biomass waste management and an energetic valorization in a local-energy-production-perspective.

Upgrading of PVC rich wastes by magnetic density separation and hyperspectral imaging quality control

Polyvinylchloride (PVC) is one of the most produced polymers in Europe, with a share of 11% in terms of mass (8 milliontons) of total polymer consumption, but in 2010 only 5% of the total PVC production came from recycled materials, where other polymer recycling achieves a level of 15% on average. In order to find an innovative process to extract PVC from window frames waste, a combination of two innovative technologies was tested: magnetic density separation (MDS) and hyperspectral imaging (HSI). By its nature, MDS is a flexible high precision density separation technology that is applicable to any mixture of polymers and contaminants with non-overlapping densities. As PVC has a very distinctive high density, this technology was tested to obtain high-grade PVC pre-concentrates from window frame waste. HSI was used to perform a quality control of the products obtained by MDS showing that PVC was clearly discriminated from unwanted rubber particles of different colors. The results showed that the combined application of MDS and HSI techniques allowed to separate and to check the purity of PVC from window frame waste.

Hyperspectral imaging based procedures applied to bottom ash characterization

Bottom ash from Municipal Solid Waste Incinerators (MSWIs) is mainly land filled or used as material for the foundation of road in European countries. Bottom ash is usually first crushed to below 40 mm and separated magnetically to recover the steel scrap. The remaining material contains predominantly sand, sinters and pieces of stone, glass and ceramics, which could be used as building material if strict technical and environmental requirements are respected. The main problem is the presence of residual organic matter in the ash and the large surface area presented by the fine fraction that creates leaching values, for elements such as copper, that are above the accepted levels for standard building materials. Main aim of the study was to evaluate the possibility offered by hyperspectral imaging to identify organic matter inside the residues in order to develop control/selection strategies to be implemented inside the bottom ash recycling plant. Reflectance spectra of selected bottom ash samples have been acquired in the VIS-NIR field (400- 1000 nm). Results showed as the organic content of the different samples influences the spectral signatures, in particular an inverse correlation between reflectance level and organic matter content was found.