A team at King Abdullah University of Science and Technology (KAUST) has developed a data-driven artificial intelligence (AI) framework to design liquid fuels exhibiting tailor-made properties for combustion engine applications to improve efficiency and lower carbon emissions. An open-access paper on their work is published in the Nature journal Communications Chemistry.
The fuel design approach is a constrained optimization task integrating two parts: (i) a deep learning (DL) model to predict the properties of pure components and mixtures and (ii) search algorithms to efficiently navigate in the chemical space. Our approach presents the mixture-hidden vector as a linear combination of each single component’s vectors in each blend and incorporates it into the network architecture (the mixing operator (MO)). We demonstrate that the DL model exhibits similar accuracy as competing computational techniques in predicting the properties for pure components, while the search tool can generate multiple candidate fuel mixtures. The integrated framework was evaluated to showcase the design of high-octane and low-sooting tendency fuel that is subject to gasoline specification constraints. This AI fuel design methodology enables rapidly developing fuel formulations to optimize engine efficiency and lower emissions.—Kuzhagaliyeva et al.
An inverse mixture-design approach based on machine learning can teach computers to create mixtures from a set of target properties. Developed by KAUST, this could help find high-performance transport fuels that burn efficiently while releasing little carbon dioxide (CO2) into the atmosphere.
There are several methods developed for fuel screening, but they are usually validated only on smaller blends, or require additional preprocessing, which makes these configurations unsuitable for inverse fuel design.
The key bottleneck is screening complex mixtures containing hundreds of components to predict synergistic and antagonistic effects of species on the resultant mixture properties.—first author Nursulu Kuzhagaliyeva
Kuzhagaliyeva, Mani Sarathy and coworkers constructed a deep learning model comprising multiple smaller networks dedicated to specific tasks to screen fuels efficiently. The problem was a good fit for deep learning that allows capturing nonlinear interactions between species, Kuzhagaliyeva said.
In the inverse-design approach, the researchers first defined combustion-related properties, such as fuel ignition quality and sooting propensity, and then determined potential fuels according to these properties.
Publicly available experimental data are scarce. Therefore, the researchers built an extensive database using experimental measurements from the literature to train the model. The database consisted of different types of pure compounds, surrogate fuel blends and complex mixtures, such as gasoline.
There was no model adaptable to inverse fuel design, so the researchers had to embed vector representations in the model, Kuzhagaliyeva said. Inspired by text processing techniques that relate words to phrases using hidden vectors, they introduced a mixing operator that directly connects hidden representations of pure compounds and mixtures through linear combinations. They also added search algorithms to detect fuel mixtures that match the predefined properties within a chemical space.
The model accurately predicted the fuel ignition quality and sooting propensity of various molecules and mixtures. It also identified several fuel blends fitting the predefined criteria.
The team is now enhancing model accuracy by extending the property database to other criteria, such as volatility, viscosity and pollutant formation. The tool is being advanced to formulate gasoline e-fuels and synthetic aviation fuels. They are also developing a cloud-based platform to enable others to use the tool.
Kuzhagaliyeva, N., Horváth, S., Williams, J., Nicolle, A. & Sarathy, S.M. (2022) “Artificial intelligence-driven design of fuel mixtures.” Communications Chemistry 5, 111doi: 10.1038/s42004-022-00722-3