Skip to main content

Improving Fuel Cell Performance With AI

 

Improving Fuel Cell Performance With AI

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 micro-structure: 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 3D simulations to predict cell performance based on their micro-structure.

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 micro-structure 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.”

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 micro-structure 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.

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.”

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.

Comments

Popular posts from this blog

Fuel Cells Enable Green Ships

  Fuel Cells Enable Green Ships Ship pollutant emission standards have become stricter, and  fuel cells  have become the first choice for green ships. With the improvement of ship environmental protection requirements, the power system adopts clean energy. As a power system with high energy efficiency, zero pollution and low vibration noise, fuel cell system is the first choice for the development of ship power plants in the future. China’s ship power system is dominated by diesel engines. There are problems such as low energy conversion rate, high fuel demand, and serious environmental pollution. With the rising demand for environmental protection, at the end of 2019, 712 exhibited its own research and development at the Shanghai International Maritime Exhibition. The key performance indicators of the 500kW-class marine hydrogen fuel cell system have reached the international advanced level. my country has made major breakthroughs in the study of clean fuel cell ships. A...

Fuel Cell Manufacturing Using Ultrasonic Spray Technology

Fuel Cell Manufacturing Using Ultrasonic Spray Technology A variety of fuel cells utilize catalysts at both the anode (to oxidize fuel and convert it to protons/hydrogen cations and electrons) and the cathode (convert hydrogen cations and oxygen to water), often precious metal, nanocarbon, or other nanomaterial-based. Doped carbon nanotubes and core-shell metallic or composite nanoparticles are two examples of such. Such catalyst materials need first to be synthesized and then coated onto electrode and/or membrane surfaces for use in fuel cells. Solid oxide fuel cells (SOFCs) that do not utilize catalyst coatings are also of interest. Cheersonic high-temperature nozzles, nebulizers, and particle generators can be used for fuel cell catalyst nanomaterial synthesis via chemical vapor deposition and/or spray pyrolysis techniques. Moreover, Cheersonic can custom manufacture AACVD and spray pyrolysis systems for fuel cell catalyst synthesis, based on customer goals and requirements, whether...

Voltage reversal phenomenon is one of the main culprits of fuel cell failure!

Voltage reversal phenomenon is one of the main culprits of fuel cell failure! Operation errors, harsh working conditions and the anode gas shortage caused by the external environment are the main culprits for the voltage reversal. The voltage reversal is mainly accompanied by the water electrolysis reaction and the carbon corrosion reaction, and the attenuation of the battery cannot be reversed. Optimizing system control strategies and developing anti-reverse electrode materials are the main countermeasures. Cost, performance and durability are the three major obstacles to the commercialization of proton exchange membrane fuel cells. Among them, durability refers to the ability of a material or product to resist the long-term destructive effects of both itself and the objective environment. Generally, the working conditions that accelerate fuel cell degradation (affect durability) include start-stop, freezing/melting, idling (high potential), dry/wet cycle, and variable load. The parti...