Prediction of pellet quality through machine learning techniques and near-infrared spectroscopy. (September 2020)

• Record Type: Journal Article
• Authors: Mancini, Manuela; Mircoli, Alex; Potena, Domenico; Diamantini, Claudia; Duca, Daniele; Toscano, Giuseppe
• Is Part Of: Computers & industrial engineering. Volume 147(2020)
• Publication Date: 2020-09
• Subjects: Pellet quality -- Near-infrared spectroscopy -- Machine learning -- Supply chain management -- Ash content -- Biofuel analysis -- Biomass analysis; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2020.106566
• Languages: English
• ISSNs: 0360-8352

Abstract

Highlights: Near-infrared spectroscopy coupled with machine learning to classify pellet quality. Quick and cheap methodology that is a valid alternative to laboratory analysis. The methodology is suitable in different contexts along the entire supply chain. Abstract: In recent years, pellet has received increasing attention among other biofuels due to its low storage costs and high combustion efficiency. The traceability of pellet quality along the entire supply chain is a critical issue, since fraudulent behaviours, such as the replacement with lower quality pellet, may both cause an economic damage and harm consumers' health. Traditionally, pellet quality is evaluated through laboratory analysis, which is costly and time-consuming. To overcome these limitations, in this work we define a methodology for quick and low-cost evaluation of pellet quality, which may be used along the entire supply chain. The proposed technique is based on the classification of pellet spectra through machine learning techniques. Spectra are obtained by means of a near-infrared (NIR) spectrophotometer, which is a relatively cheap instrument of small dimensions (even portable) that is suitable for on-site analysis at any phase of the supply chain. We propose two different approaches, namely an automatic classification of pellet, which does not require laboratory analysis, and a semi-automatic approach, that increases the overall accuracy but requires laboratory analysis for uncertainly classified samples. We validate the methodology by performing several experiments on real-world data, by training different machine learning algorithms and evaluating the impact of several transformations introduced to reduce the scattering effect, which is a well-known issue related to NIR data.