via The World Economic Forum
Machine learning could fast-track the formulation of tailor-made mixtures, including “greener” fuels.
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.
Greenhouse gas emissions are major contributors to rising global temperatures. A large proportion of CO2 emissions comes from the combustion of hydrocarbon fuels, such as gasoline, that power most automotive engines. A promising solution to these environmental issues is to engineer transport fuels that offer enhanced efficiency and lower carbon emissions.
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,” says first author Nursulu Kuzhagaliyeva, a Ph.D. student in Mani Sarathy’s research group.
Kuzhagaliyeva, Sarathy and coworkers constructed a deep learning model — comprising multiple smaller networks dedicated to specific tasks — to screen fuels efficiently. “This problem was a good fit for deep learning that allows capturing nonlinear interactions between species,” Kuzhagaliyeva says. 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 says. 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. “We are also developing a cloud-based platform to enable others to use the tool,” Kuzhagaliyeva says.
Original Article: AI screens to make transport fuels green
More from: King Abdullah University of Science and Technology
The Latest Updates from Bing News
Go deeper with Bing News on:
Greener transportation fuels
- Green Drinks Kankakee to meet Tuesday
The presenter for the evening will be Marlee Giacometti, Midwest program specialist on the Perennial Bioenergy Crop Diversification Project at American Farmland Trust. She will give a talk on the ...
- Canada’s best green hydrogen play is based in reality
Green hydrogen has potential as both a transportation fuel and for use in the chemical industry. While the truth is that converting our transportation systems to running on renewable hydrogen fuel is ...
- CNX Resources, KeyState Energy considering sustainable aviation fuel hub at Pittsburgh International Airport
CNX Resources Corp., KeyState Energy and Pittsburgh International Airport are working together on a $1.5 billion project that, if completed, could make sustainable aviation fuel at PIT from coal-mine ...
- Exclusive: Pittsburgh International Airport wants top role in sustainable aviation fuel
A clean-energy transition is coming to the aviation industry, and Allegheny County Airport Authority CEO Christina Cassotis wants Pittsburgh International Airport and the region on the ground floor.
- Booster Fuels: Renewable Diesel: A Convenient Way To Control Pollution | BOOSTER
This green fuel reduces our need for oil and cuts harmful ... Renewable Diesel in Transportation The transport sector benefits significantly from renewable diesel. It uses public and private ...
Go deeper with Bing News on:
High-performance transport fuels
- Honda unveils hydrogen fuel cell truck concept at ACT Expo 2024
Honda has announced the debut of its Class 8 Hydrogen Fuel Cell Truck Concept at the Advanced Clean Transportation (ACT) Expo, which will be held on May 20, 2024. This truck concept represents the ...
- Hyzon Unveils Hydrogen Fuel Cell Refuse Truck
Hydrogen fuel cell technology developer Hyzon and New Way Trucks ... "As a growing market leader with a long history in building high-performance refuse collection equipment, New Way is in a unique ...
- Shell launches new gas to improve performance, efficiency because EV transition won’t ‘happen overnight’
Tested in Ferrari Formula 1 cars, the new formulation is designed to remove more gunk from car engines and keep fuel injectors cleaner ...
- Neste progress with renewable fuels expansions
Neste will use its proprietary next generation biomass-to-liquids technology to increase overall production of renewable products to 5.5 million tpy by yearend 2024.
- Experts weigh in on the prospects and challenges of Hydrogen fuel cell trucks
Daimler Truck announced in Berlin its substantial investment in hydrogen technology. The CEO, Martin Daum, showcased the Mercedes-Benz ...