Artificial Neural Network for Predicting Cetane Number of Biofuel Candidates Based on Molecular Structure
Tim Sennott, C. Gotianun, Rodney A. Serres, Masoud Ziabasharhagh, John Hunter Mack, Robert W. Dibble · 2013
The production of next-generation biofuels is being explored through a variety of chemical and biological approaches, all aiming at lowering costs and increasing yields while producing viable alternatives to gasoline or diesel fuel. Chemical synthesis can lead to a huge variety of different fuels and the guidelines from which molecules yield desirable properties as a fuel are largely based on intuition. One such property of interest is the cetane number (CN), a measure of the ignition quality of diesel fuel. The present work improves on existing models and extends them to more oxygenates (primarily ethers) to increase the model’s generalizability to the large variety of new potential biofuels currently of interest to researchers. This predictive model uses artificial neural networks (ANN’s) as a tool for quantitative structure property relationship (QSPR) analysis. Predicting the cetane number of a fuel is especially important because testing a fuel requires large volumes of pure sample (100mL for derived cetane number, >1L for cetane number), the production of which can be difficult, costly and time-consuming at the lab scale. To this end, a predictive model will allow chemists to eliminate unlikely targets and focus their attention on promising candidates.