Today’s engine performance is largely determined by the physical properties and chemical composition of fuels. With an increase in the production of heavier and sour crudes that require more processing, as well as a rise in unconventional fuel blendstocks, the relationships between the physical and chemical properties of fuels are evolving. To ensure a smooth transition to the next generation of fuel blends it is essential to understand the quantitative and qualitative compositional property relationships of fuels. This can be accomplished with support from advanced analytical techniques such as Comprehensive Two Dimensional Gas Chromatography (GCxGC), Gas Chromatography with Field Ionization Mass Spectrometry (GC-FIMS), Nuclear Magnetic Resonance (NMR), Fourier Transfer Infrared (FTIR) and Raman Spectroscopy.<br/>CanmetENERGY Devon has been actively furthering knowledge of transportation fuel chemistry and its effects on internal combustion engines by using advanced analytical techniques in combination with artificial intelligence. This presentation will demonstrate the application of machine learning approaches such as Principal Component Analysis (PCA), Neural Networks (NN), Partial Least Squares (PLS), and Support Vector Machines (SVM) to develop relationships between diesel fuel chemistry and engine performance. The concept of ‘in silico’ blends to design a Virtual Combinatorial Fuel Library (VCF) is introduced. The VCFL represents and reconstructs the chemical space of available blend possibilities. After projection of the VCFL through existing models we create the property space which can be utilized in fuel-to-property prediction and participate in optimization and designing of new ‘greener’ fuels.

Impact of detailed fuel chemical composition on engine-related properties

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.