Search Results

Distillation properties of gasoline are regulated to ensure the safe and efficient operation of SI-engines. Blending various gasoline components affects the distillation values in a non-linear fashion, making the prediction of these properties challenging. Furthermore, the rise of renewable components necessitates the development of new property prediction methods. In this work, a variety of Machine Learning models were created to predict the distillation points of gasoline blends based on the blending recipe. As input data, real industrial data from a refinery was used together with data from blends created for R&D purposes. The predicted properties were the evaporated volume at the 70 and 100 °C distillation points (E70 and E100). Altogether four different machine learning models were trained, cross-validated and tested using seven different pre-processing methods. It was found that Support Vector Regression (SVR) was the most effective at predicting the distillation points.

Gasoline blending is known to be complicated, because individual gasoline fractions with different octane numbers, Research Octane Number (RON) or Motor Octane Number (MON) do not always blend linearly. Instead, they may blend non-linearly, in a synergistic or antagonistic manner. Even though RON and MON are regulated properties, linear and non-linear octane blending is not a broadly understood topic. The target in the developing process of a modern SI engine is to have 100% combustion efficiency which would lead to the reduction of hydrocarbon and carbon monoxide emissions. Therefore, the properties of gasoline, especially RON and MON, need to be optimized to ensure proper ignition in the engine and prevent harmful autoignition reactions. There are hundreds of hydrocarbons in gasoline which have different octane numbers (ON). The explanations for these variations are the structural differences in hydrocarbon molecules that influence on their reactivity.