The study is addressed to define HyperSpectral Imaging (HSI) based platform to develop innovative recognition logics finalized to perform a full quality control of fed/recovered plastic particles streams resulting from Magnetic Density Separation (MDS) process. The integrated hardware and software (HD&SW) architectures have been defined in order to be implemented inside industrial recycling plants, with particular reference to polyolefins recovery. An HSI platform, working in the near infrared region (1000-1700 nm), has been set-up at laboratory scale. Logics have thus been designed an implemented on the basis of a systematic study carried out on different possible feeds belonging respectively to Automotive Shredder Residue (ASR) and Building and Construction Waste (B&CW). Algorithms and recognition procedures have been set up considering that, being the material usually transported on a conveyor belt, a fast particles recognition has to be performed to maximize the quantity of particle investigated per unit of time. In this perspective the reliability of the proposed architecture was verified trough an in depth analysis of the robustness of the acquired data.
Design of an Hyperspectral Imaging Based Platform for Quality Control in the MDS-based Recycling Process of Polyolefins / Bonifazi, Giuseppe; Dall'Ava, A; Serranti, Silvia. - ELETTRONICO. - (2011), pp. 1522-1537. (Intervento presentato al convegno The 26th Int. Conf. on Solid Waste Technology and Management tenutosi a Philadelphia nel 27-30 March 2011).
Design of an Hyperspectral Imaging Based Platform for Quality Control in the MDS-based Recycling Process of Polyolefins
BONIFAZI, Giuseppe;SERRANTI, Silvia
2011
Abstract
The study is addressed to define HyperSpectral Imaging (HSI) based platform to develop innovative recognition logics finalized to perform a full quality control of fed/recovered plastic particles streams resulting from Magnetic Density Separation (MDS) process. The integrated hardware and software (HD&SW) architectures have been defined in order to be implemented inside industrial recycling plants, with particular reference to polyolefins recovery. An HSI platform, working in the near infrared region (1000-1700 nm), has been set-up at laboratory scale. Logics have thus been designed an implemented on the basis of a systematic study carried out on different possible feeds belonging respectively to Automotive Shredder Residue (ASR) and Building and Construction Waste (B&CW). Algorithms and recognition procedures have been set up considering that, being the material usually transported on a conveyor belt, a fast particles recognition has to be performed to maximize the quantity of particle investigated per unit of time. In this perspective the reliability of the proposed architecture was verified trough an in depth analysis of the robustness of the acquired data.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
