Profile of the biodiesel B100 commercialized in the region of Londrina: application of artificial neural networks of the type self organizing maps

Abstract

The 97 samples were grouped according to the year of analysis. For each year, letters from A to D were attributed, between 2010 and 2013; A (33) B (25) C (24) and D (15). The parameters of compliance previously analyzed are those established by the National Agency of Petroleum, Natural Gas and Biofuels (ANP), through resolution ANP 07/2008. The parameters analyzed were density, flash point, peroxide and acid value. The observed values were presented to Artificial Neural Network (ANN) Self Organizing MAP (SOM) in order to classify, by physical-chemical properties, each sample from year of production. The ANN was trained on different days and randomly divided samples into two groups, training and test set. It was found that SOM network differentiated samples by the year and the compliance parameters, allowing to identify that the density and the flash point were the most significant compliance parameters, so good for the distinction and classification of these samples.

Keywords

• Artificial Neural Networks
• Self Organizing Maps
• Compliance parameters
• Biofuel
• Biodiesel