Machine Learning-Based Prediction of Selected Parameters of Commercial Biomass Pellets Using Line Scan Near Infrared-Hyperspectral Image

Biomass pellets are required as a source of energy because of their abundant and high energy. The rapid measurement of pellets is used to control the biomass quality during the production process. The objective of this work was to use near infrared (NIR) hyperspectral images for predicting the prope...

Full description

Saved in:
Bibliographic Details
Published inProcesses Vol. 9; no. 2; p. 316
Main Authors Pitak, Lakkana, Laloon, Kittipong, Wongpichet, Seree, Sirisomboon, Panmanas, Posom, Jetsada
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.02.2021
Subjects
Accuracy
Algorithms
Biodiesel fuels
Biofuels
Biomass
Biomass energy
Carbon dioxide
Cellulose
Efficiency
Gene mapping
Genetic algorithms
Hyperspectral imaging
Immunoglobulin A
Infrared imagery
Learning algorithms
Machine learning
Moisture content
Pellets
Raw materials
Renewable resources
Spectra
Spectrum analysis
Wavelengths
Online AccessGet full text

Cover

More Information
Summary:Biomass pellets are required as a source of energy because of their abundant and high energy. The rapid measurement of pellets is used to control the biomass quality during the production process. The objective of this work was to use near infrared (NIR) hyperspectral images for predicting the properties, i.e., fuel ratio (FR), volatile matter (VM), fixed carbon (FC), and ash content (A), of commercial biomass pellets. Models were developed using either full spectra or different spatial wavelengths, i.e., interval successive projections algorithm (iSPA) and interval genetic algorithm (iGA), wavelengths and different spectral preprocessing techniques. Their performances were then compared. The optimal model for predicting FR could be created with second derivative (D2) spectra with iSPA-100 wavelengths, while VM, FC, and A could be predicted using standard normal variate (SNV) spectra with iSPA-100 wavelengths. The models for predicting FR, VM, FC, and A provided R2 values of 0.75, 0.81, 0.82, and 0.87, respectively. Finally, the prediction of the biomass pellets’ properties under color distribution mapping was able to track pellet quality to control and monitor quality during the operation of the thermal conversion process and can be intuitively used for applications with screening.
ISSN:2227-9717
2227-9717
DOI:10.3390/pr9020316