AI startup aims to design-on-demand batteries and more

Image: Polaron

22 January 2024 | Muriel Cozier

‘This “process-structure-performance” conundrum is the “Holy Trinity” of the advanced materials world.’

A spinout company from Imperial College London’s Dyson School of Design Engineering is aiming to help manufacturers improve the performance of advanced materials used in products such as batteries and wind turbines.

The company, Polaron, is developing generative machine learning algorithms which it says will enable materials producers to accelerate their design by modelling the complex relationships between processing parameters, the microstructures of the materials produced, and the performance of the resulting materials.

The company has strong connections to the Faraday Institution’s Multiscale Modelling project, which was established to equip industry and academia with new software modelling tools to predict and improve battery lifetime and performance, by connecting the understanding of battery materials at the atomic level, up to the assembled battery pack.

Big Data III and AI event banner
Interested in how AI and big data are shaping science based industries? Sign up here to find out live from key figures in industry.

In December 2023, The Faraday Battery Challenge awarded £12 million in funding to the Advanced Materials Battery Industrialisation Centre, which will provide capability for scale up of synthesis and processing of current and next-generation battery materials.

‘This “process-structure-performance” conundrum is the “Holy Trinity” of the advanced materials world,’ said Dr Sam Cooper, one of the company’s founders. ‘In the case of battery electrodes, hundreds of parameters need to be carefully tuned, including the ratio of materials in the mix, the coating thickness, and the drying temperature to name but a few.’

Dr Cooper added: ‘These parameters interact with each other in complex ways and therefore cannot be optimised in isolation. Each combination results in a distinct micro structural arrangement of particles, and therefore different performance characteristics of a product, such as an electric car’s range and charging time.’

Polaron says that there is a strong market need for off-the-shelf generative AI design tools that can accelerate the design process based on customer data. ‘These complex manufacturing processes are currently beyond the capability of today’s best computer simulations,’ said Dr Steve Kench, Polaron’s Chief Technology Officer and co-founder.

Polaron added that its models are designed to be run on manufacturers own hardware or cloud platform, allowing them to keep their training data and results private.

A new spinout from @ImperialDyson will use AI to help manufacturers produce higher performing materials for products such as batteries and wind turbines.

Congratulations to the @PolaronAI team! 👏 #InventedAtImperialhttps://t.co/tBeK5T3vqs

Issac Squires, Chief Executive Officer and one of the founders, said that demand for solutions such as theirs is being driven by a skills shortage. ‘Generative AI has been identified by manufacturers as the top emerging AI technology for integrating their workflows, but a tech skills shortage means there is a need for off-the-shelf solutions.’

Polaron is currently raising funding and is talking to major manufacturers to begin applying the techniques to large-scale problems.

Show me news from
All themes
from
All categories
by
All years
search by