Fuel cells and lithium-ion batteries could charge faster or gain more power to run data centres following the development of a new machine learning algorithm.
The machine learning algorithm from a team at Imperial College London reportedly allows researchers to explore possible designs for the microstructure of fuel cells and lithium-ion batteries, before running 3D simulations that help researchers make changes to improve performance.
Improvements could include increasing the time between charges for electric vehicles and improving the power of hydrogen fuel cells running data centres.
A paper describing the work is published in npj Computational Materials.
The performance of fuel cells and lithium-ion batteries is closely related to their microstructure; the shape and arrangement pores inside their electrodes can affect how much power fuel cells can generate, and how quickly batteries charge and discharge. Because the micrometre-scale pores are so small, their specific shapes and sizes can be difficult to study at a high enough resolution to relate them to overall cell performance.
Now, researchers at Imperial have applied machine learning techniques to help them explore these pores virtually and run 3D simulations to predict cell performance based on their microstructure.
The researchers said they have used a novel machine learning technique called deep convolutional generative adversarial networks (DC-GANs). These algorithms can learn to generate 3D image data of the microstructure based on training data.
Lead author Andrea Gayon-Lombardo, of Imperial’s Department of Earth Science and Engineering, said: “Our technique is helping us zoom right in on batteries and cells to see which properties affect overall performance. Developing image-based machine learning techniques like this could unlock new ways of analysing images at this scale.”
When running 3D simulations to predict cell performance, researchers need a large enough volume of data to be considered statistically representative of the whole cell. It is currently difficult to obtain large volumes of microstructural image data at the required resolution.
However, the authors found they could train their code to generate either much larger datasets that have all the same properties, or deliberately generate structures that models suggest would result in better performing batteries.
In a statement, project supervisor Dr Sam Cooper, of Imperial’s Dyson School of Design Engineering, said: “Our team’s findings will help researchers from the energy community to design and manufacture optimised electrodes for improved cell performance. It’s an exciting time for both the energy storage and machine learning communities, so we’re delighted to be exploring the interface of these two disciplines.”