An algorithm that may enhance hydrogen fuel cell performance

A team of researchers* from UNSW Australia developed an algorithm to improve the understanding of what is happening inside a Proton Exchange Membrane Fuel Cell (PEMFC). 

This new process, detailed in a paper published in Nature Communications, has been tested on hydrogen fuel cells to accurately model the interior in precise detail and potentially improve their efficiency. To be precise, it consists of an algorithm that produces high-resolution modelled images from lower-resolution micro X-ray computerised tomography (CT). 

As it is reminded in the press release “PEMFCs can become inefficient if the water cannot properly flow out of the fuel cell and subsequently ‘floods’ the system. Until now, it has been very hard for engineers to understand the precise ways in which water drains, or indeed pools, inside the fuel cells due to their very small size and very complex structures.” Consequently, there is a huge untapped performance improvement that could be made just by improving water management (an estimated 60% increase overall).

Thanks to the algorithm, known as DualEDSR, it will be possible to improve the field of view by around 100 times compared to the high-resolution image. For now, the researchers are able to provide a detailed 3D model of the inside of a PEMFC in order for manufacturers to improve the management of the water produced and make the fuel cells more efficient.

When tested, DualEDSR achieved a 97.3% accuracy when producing high-res modelling from low-res imagery. It also produced a high-resolution model in just 1 hour. It would have taken 1188 hours (the equivalent of 50 days non-stop) to obtain high-res images of the whole section of the fuel cell using a micro-CT scanner.

“From our model we can quickly and precisely see where the water tends to accumulate and therefore, we can help to solve those problems in future designs,” says Dr Meyer.

But that’s not all. The algorithm could also be applied to the medical field. For instance on human X-rays, “to give medical professionals a better understanding of tiny cellular structures inside the body, which could allow for better and faster diagnosis of a wide range of diseases such as tumour cells, earlier, when they are smaller.”

For curious people, here is a video simulating the water formation, accumulation and transport in the hydrogen fuel cell. 

*The research team behind this project features Professor Ryan Armstrong, Professor Peyman Mostaghimi, Dr Ying Da Wang, and Kunning Tang from the School of Mineral and Energy Resources Engineering and Prof Chuan Zhao and Dr Quentin Meyer from the School of Chemistry.  

Reference: Wang, Y.D., Meyer, Q., Tang, K. et al. Large-scale physically accurate modelling of real proton exchange membrane fuel cell with deep learning. Nat Commun 14, 745 (2023).

Article written by Logan King

If you liked it, share it

About the author

Logan King

Logan King

After an unusual career (3 years in the French army followed by a 3-year degree in Applied Foreign Languages), it was my passion for environmental issues that finally caught up with me and led me to join Seiya Consulting and H2 Today in June 2022. First as an end-of-study internship, then as Marketing & Communication Manager and translator at Hydrogen Today.

Our latest articles

interactive world map