A new machine learning algorithm 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.
Fuel cells use clean hydrogen fuel — which can be generated by wind and solar energy — to produce heat, electricity, and lithium-ion batteries like those found in smartphones, laptops, and electric cars. Their performance is closely related to their microstructure — how the pores (holes) inside their electrodes are shaped and arranged can affect how much power fuel cells can generate and how quickly batteries charge and discharge. Because the micrometer-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.
Researchers have applied machine learning techniques to explore these pores virtually and run 3D simulations to predict cell performance based on their microstructure. The researchers 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 obtained from nanoscale imaging-performed synchrotrons (a kind of particle accelerator the size of a football stadium). The technique helps researchers zoom in on batteries and cells to see which properties affect overall performance.
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. The team 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.
By constraining the algorithm to only produce results that are currently feasible to manufacture, the researchers hope to apply their technique to designing optimized electrodes for next-generation cells.