Predicting Cetane Index, Flash Point, and Content Sulfur of Diesel–Biodiesel Blend Using an Artificial Neural Network Model

Artificial neural networks (ANNs) were used to predict, not simultaneously, flash point, cetane index, and sulfur content (S1800) of diesel blends (7% (v/v) biodiesel) using distillation curves (ASTM D86), specific gravity at 20 °C (ASTM D405), cetane index (ASTM D4737), flash point (ASTM D93), and sulfur content (ASTM D4294). The low error values obtained compared with other chemometric based models described in literature, and high correlation coefficients between reference and predicted values showed that ANNs were efficient in determining flash point, cetane index/cetane number, and sulfur content (S1800). The constructed model contains diesel samples of different compositions (50, 500, and 1800 mg kg–1), thus revealing the variety of fuel in the Brazilian market. Furthermore, the proposed method has advantages such as low cost and easy implementation, as it applies the results of the routine test to evaluate the quality control of diesel.