Estimation Of The Lower Heating Value Of Solid Recovered Fuel Based On Swir Hyper-Spectral Images And Machine Learning

In this work, we apply Machine Learning techniques to Hyper-Spectral Images acquired by a Short Wave Infra-Red (SWIR) Camera, to classify the materials composing the Solid Recovered Fuel (SRF). This classification, enabled by data pre-processing techniques, is used to estimate the Lower Heat Value (LHV) of SRF samples, building on models of the literature. The accurate and timely estimates of SRF LHVs yield significant benefits to SRF consumers.

[1]  J. Havukainen,et al.  Impact of utilizing solid recovered fuel on the global warming potential of cement production and waste management system: A life cycle assessment approach , 2020, Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA.

[2]  Leland McInnes,et al.  UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction , 2018, ArXiv.

[3]  M. Moroni,et al.  PET and PVC Separation with Hyperspectral Imagery , 2015, Sensors.

[4]  Silvia Serranti,et al.  Quality control by HyperSpectral Imaging (HSI) in solid waste recycling: logics, algorithms and procedures , 2014, Electronic Imaging.

[5]  Silvia Serranti,et al.  Characterization of post-consumer polyolefin wastes by hyperspectral imaging for quality control in recycling processes. , 2011, Waste management.

[6]  Y. Chang,et al.  Multiple regression models for the lower heating value of municipal solid waste in Taiwan. , 2007, Journal of environmental management.

[7]  Ghanshyam Das Agrawal,et al.  Multiple regression analysis for the estimation of energy content of municipal solid waste , 2007 .

[8]  Richard E. Lyon,et al.  Heats of combustion of high temperature polymers , 2000 .

[9]  J. Mosby,et al.  Machine learning based modelling for lower heating value prediction of municipal solid waste , 2021 .

[10]  S. Pieber,et al.  Advanced Waste-Splitting by Sensor Based Sorting on the Example of the MT-Plant Oberlaa CONFERENCE , 2015 .