E-Mobility Engineering’s Post

Making powertrains faster with the aid of AI Monumo has used two forms of artificial intelligence (AI) to speed the development of powertrain systems for e-mobility, writes Nick Flaherty. Time pressures often limit collaboration between sub-system teams in the early stages of design, which means genuine system-level optimisation is limited, said Simon Shepherd, head of hardware development at Monumo. Its Anser AI engine allows exploration of design parameters to provide greater coverage. It can run hundreds of thousands of simulations in a single day, and generate detailed design concepts within days, once the key requirements and design criteria are defined. In the concept phase of powertrain development, many decisions are made that lock significant engineering resources into a design. Reversing or refining it then becomes risky and costly. For instance, choosing axle gear ratios influences torque and speed demands on an electric motor – key factors in power density and overall system performance. Evaluating these factors in detail is often too time-consuming for designers. The number of design iterations is typically limited by the time required to run complex, multi-physics simulations, often involving various software and specialists and OEMs have tight deadlines. So, existing templates are often adapted, hindering the ability to fully optimise designs for new uses. Simulation data produced by the Anser AI engine can feed machine-learning (ML) algorithms, which Monumo calls engineering models, and these can predict the performance of a wide range of powertrain design possibilities. Once trained on a specific operational or parametric domain, these models could soon be queried by engineers using algorithms similar to search engines, where simple input design rules yield refined implementations. “This will fundamentally change how powertrain designs are conceived,” said Shepherd. “The Anser engine will be able to propose alternative parametric design solutions, based on performance requirements, with simulations backing each proposed concept. Because of the depth embedded in the training data, each query can generate highly refined designs in a few days. “In future, we estimate that up to 80% of design time can be removed from the A-phase concept design stage.” Click here to access more news articles & deeper technical investigations into e-mobility ▶ https://lnkd.in/exVm22ce #emobility #powertrain #electricvehicles #automotive #ai #electrification

  • No alternative text description for this image
Christophe Gallon

Product development / Application Engineering

3w

Of course interesting but need to deeply control and understand, no rush.

Like
Reply

To view or add a comment, sign in

Explore topics