The development of vehicle components is a lengthy and therefore very costly process. Researchers at Graz University of Technology (TU Graz) have developed a method that can shorten the development phase of the powertrain of battery electric vehicles by several months. A team led by Martin Hofstetter from the Institute of Automotive Engineering is combining simulation models of components with evolutionary optimisation algorithms. This AI system automatically optimises the entire powertrain – from the power electronics to the electric machine through to the transmission – in line with the manufacturer’s technical requirements, taking into account targets such as production costs, efficiency and package space requirements in the vehicle. The OPED (Optimisation of Electric Drives) software solution was developed at TU Graz and is the result of almost ten years of research. It is already being used successfully by a renowned Austrian automotive supplier.

AI agents trained in simulations that differ from the environments where they are deployed sometimes perform better than agents trained and deployed in the same environment, MIT research shows.

Many materials store information about what has happened to them in a sort of material memory, like wrinkles on a once crumpled piece of paper. Now, a team led by Penn State physicists has uncovered how, under specific conditions, some materials seemingly violate underlying mathematics to store memories about the sequence of previous deformations.