Análise e Diferenciação de espécies de madeiras comerciais utilizando espectroscopia óptica no infravermelho por transformada de Fourier e análise multivariada

Abstract

Wood is an abundant, renewable and biodegradable compound with many useful applications, consisting primarily of 50% cellulose, 20 to 30% lignin, 20 to 25% hemicellulose and 2 to 5% of other wood constituents that may include lipids. , phenolic compounds, terpenoids, fatty acids, resin acids and waxes. However, he observes that the identification of wood species is usually done based on human sensory analysis, observing its color, smell, texture, quantity and pore distribution as some of the factors that form the identity of each wood species. The analysis can be done with the naked eye or with the aid of a portable 10x magnification lens. The absence of a more robust analysis method for classification and traceability, regardless of training or human sensory analysis leads to erroneous classification of it, harming the quality control and inspection of commercialized wood, traditional methods such as Van Soest are applied in this way, but take about 3 or 4 days for analysis. In this aspect, researches aimed at the association of Machine Learning (AM) techniques, together with the Fourier Transform Infrared Spectroscopy (FTIR) technique to discriminate different types of materials, which solve the difficulties of traditional methods and present advantages for implementation, such as speed, cost, has been growing in recent years. Thus, this work seeks to associate the technique of FTIR and AM to solve the problems found in the incorrect identification of commercial wood, and improve time and cost compared to traditional methods. The infrared absorption spectrum of five wood species was used: Hymenolobium petraeum Ducke, Angelim-pedra (ANG); Gochnatia polymorpha, Cambara (CAM); Erisma uncinatum, Cedrinho (CED)Dipteryx odorata, Champagne (CHA); Goupia glabra Aubl, Northern Peroba (PER). The results showed that the FTIR technique together with multivariate analysis were able to differentiate the five wood species with 100% sensitivity and specificity. The method developed allows industries, laboratories, companies and/or control bodies to identify the nature of the product after it is extracted and semi-manufactured.