Estimation of Speciation Data for Hydrocarbons using Data Science Kaust

Format:

Book

Conference/Event

Author/Creator:

Yalamanchi, Kiran, author.

Contributor:

Chen, Bingjie

Sarankapani, Rooppesh

Sarathy, Mani

Conference Name:

15th International Conference on Engines & Vehicles (2021-09-12 : Capri, Italy)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2021

Summary:

Strict regulations on air pollution motivates clean combustion research for fossil fuels. To numerically mimic real gasoline fuel reactivity, surrogates are proposed to facilitate advanced engine design and predict emissions by chemical kinetic modelling. However, chemical kinetic models could not well predict non-regular emissions, e.g. aldehydes, ketones and unsaturated hydrocarbons, which are important air pollutants. In this work, we propose a machine learning method to achieve better predictions. A dataset of neat fuels and their mixtures, constituting of 10 neat fuels, 6 primary reference fuels (PRF) and 6 FGX surrogates tested in jet stirred reactor, is used as training dataset for ML models. Experimental data were collected in the same setup to maintain data uniformity and consistency under following conditions: residence time at 1.0 second, fuel concentration at 0.25%, equivalence ratio at 1.0, and temperature range from 750 to 1100K. Measured species profiles of methane, ethylene, propylene, hydrogen, carbon monoxide and carbon dioxide are used for machine learning model development. The model considers both chemical effects and physical conditions. Chemical effects are described as different functional groups, ex. primary, secondary, tertiary, and quaternary carbons in molecular structures, and physical conditions as temperature. Machine learning models exhibits good prediction accuracy. This finding shows the great potential of machine learning application on combustion chemistry. By expanding the experimental database, machine learning models can be further applied to many other hydrocarbons in future works

Notes:

Vendor supplied data

Publisher Number:

2021-24-0081

Access Restriction:

Restricted for use by site license