Alkane data puts Intellegens’ lubricants in R&D driving seat
A recent study by researchers from the Department of Physics at the University of Cambridge has demonstrated that Intellegens’ Alchemite technology will help the lubricant industry massively accelerate and cut development costs.
“This news is a big step for Intellegens,” says market manager Andrea Olguin. “We just obtained important validation for the lubricant industry by applying Alchemite to the identification of alkanes for the most optimal lubricant base oils.
“By computationally deriving lubricants, our technology has the potential to accelerate R&D massively and cut-down development costs in this industry. We are quickly validating our product in several important areas including advanced materials, drug discovery and have now successfully validated the product in the chemicals industry.”
The study – led by Dr Conduit, a Research Fellow at the University of Cambridge and co-founder of Intellegens – and Pavao Santak (University of Cambridge) is titled ‘Predicting physical properties of alkanes with neural networks’ and is published in Fluid Phase Equilibria.
The authors implemented artificial neural networks that exploit property to property correlations to predict physical properties of alkanes.
The deep learning algorithm (Alchemite) inputs the molecular structure of alkanes to predict the boiling point, heat capacity, and vapour pressure as a function of temperature.
By combining sparse, fragmented and/or experimental data with molecular dynamics simulations to predict physical properties of alkanes, the algorithm can identify and speed up the identification of alkanes to be used for lubricant base oils with superior physical properties.
The results reproduced by this algorithm are significantly more accurate and consistent than those reproduced by other methods.
Lubricants are an essential component in industry and are widely used. They protect surfaces from wear, reduce friction, transfer heat, and ensure the smooth functioning of mechanical devices. Given that lubricants are mixtures of predominantly alkanes, it is unclear whether contemporary lubricant formulations are the most optimal.
Dr Conduit said: “We developed the deep learning tool Alchemite that is not only capable of predicting physical properties of alkanes, but has shown to accurately estimate intractable properties like density and shear viscosity. Alchemite could enable industries specialized in material formulations to substantially optimise their processes and yield better and faster results.”
Predicting the physical properties of alkanes and understanding the relationship between lubricant performance and alkane structure will facilitate the development of computationally-derived optimal base oils.
Applying Alchemite to existing lubricant technology – and potentially to develop entirely new lubricants – will lead to improvements in lubricants for car engines, hydraulic fluids in heavy machinery, team and gas turbine oils, and gearbox fluids.
Intellegens was spun out of the University of Cambridge in 2017.
More by this authorMike Scialom