Our Research and Development

Our interests are deeply rooted in studying the unknown and many of our team members have strong academic ties.
Please visit our ResearchGate profiles for a complete overview: David Zhe Gao / Filippo Federici Canova

Efficient Parameterization of Complex Molecule Surface Force Fields

Clustered Bayesian Neural Networks for Modeling Friction Processes

    Friction and wear are the source of every mechanical device failure, and lubricants are essential for the operation of the devices. These physical phenomena have a complex nature so that no model capable of accurately predicting the behavior of lubricants exists. We use a machine learning (ML) method that infers the relationship between chemical composition of lubricants and their performance from a database. The fluid friction relation is modeled by a Bayesian neural network (BNN) which is trained to reproduce the results for a training set of fluids.

    Journal of Chemical Theory and Computation 2017, 13, 3-8.