A Machine Learning Model For Optimizing Vanadium Flow Battery Systems

By Battery Power Online Staff

October 7, 2020 | Chinese researchers have published a machine learning (ML) methodology to optimize and predict the efficiencies and costs of vanadium flow battery (VFB) systems with extreme accuracy, based on a database of over 100 stacks with varying power rates. Their work was published in Energy & Environmental Science (DOI: 10.1039/D0EE02543G) in September.

The cost of a VFB system mainly depends on the VFB stack, electrolyte, and control system. Developing a VFB stack from lab to industrial scale can take years of experiments due to complex factors, from key materials to battery architecture.

Researchers from the Dalian Institute of Chemical Physics (DICP) of the Chinese Academy of Sciences proposed a strategy that takes operating current density as the main feature, and the material and structure of the stack as auxiliary features. The model can predict the voltage efficiency, energy efficiency, and electrolyte utilization ratio of the VFB stack, as well as the power and energy cost of the VFB system with high accuracy.

The results indicated that the cost of VFB systems (S-cost) at Energy/Power (E/P) =4 h can reach around 223 $·kWh-1, when the operating current density reaches 200 mA·cm-2, while voltage efficiency (VE) and utilization ratio of electrolyte (UE) are maintained above 90% and 80%, respectively. The model also suggested routes to developing high-power density VFB stacks under conditions of higher voltage efficiency and higher electrolyte utilization ratio.

This work highlights the potential of ML methodology to guide stack design and optimization of flow batteries to further accelerate their commercialization.