A new machine learning algorithm allows researchers to explore possible designs for the microstructure of fuel cells and lithium-ion batteries, before running 3-D simulations that help researchers make changes to improve performance.Computational Materials.
Fuel cells use clean hydrogen fuel, which can be generated by wind and solar energy, to produce heat and electricity, and lithium-ion batteries, like those found in smartphones, laptops, and electric cars, are a popular type of energy storage. The performance of both 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.
However, 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.Now, Imperial researchers have applied machine learning techniques to help them explore these pores virtually and run 3-D 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 3-D image data of the microstructure based on training data obtained from nano-scale imaging performed synchrotrons (a kind of particle accelerator the size of a football stadium).
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 analyzing images at this scale."
In some countries, renewable energy is cheaper than fossil fuels. Renewable energy is a much cheaper alternative in some countries because of their ability to harness sources of energy that are prevalent to their location.
When running 3-D 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 collaboration, among researchers from ICIQ's Palomares and Vidal groups, the Physical Chemistry of Surfaces and Interfaces group at the Institut de Ciència de Materials de Barcelona (ICMAB-CSIC) and IMDEA Nanocienca, sheds light on the reasons behind the differences observed in perovskite solar cell performance by comparing four different HTMs that present close chemical and physical properties.
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.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 optimized 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."
In Iceland, 100% Of Their Energy Is Supplied By Geothermal And Hydropower Sources. Dubbed ‘The Land of Fire and Ice’, Iceland is essentially built around a string of volcanoes giving them access to geothermal energy that helps heat up 9 out of 10 homes. Due to this natural abundance of renewable energy, Iceland is the world’s largest green energy producer per capita – 9 times more than the rest of their EU neighbors in fact!
By constraining their algorithm to only produce results that are currently feasible to manufacture, the researchers hope to apply their technique to manufacturing to designing optimized electrodes for next generation cells.
More information: npj Computational Materials, DOI: 10.1038/s41524-020-0340-7Provided by Imperial College London
Credit: Junling Lu's research group In a study to publish in Nature on January 31, researchers at the University of Science and Technology of China (USTC) report advances in the development of hydrogen fuel cells that could increase its application in vehicles, especially in extreme temperatures like cold winters.
Citation: AI could help improve performance of lithium-ion batteries and fuel cells (2020, June 25) retrieved 5 July 2020 from https://techxplore.com/news/2020-06-ai-lithium-ion-batteries-fuel-cells.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
emit greenhouse gases.