Machine Learning-Assisted Design of Electrode Microstructures and Flow Fields for Redox Flow Batteries by Dr.Shuaibin Wan
Speaker: Dr.Shuaibin Wan
Topic: Machine Learning-Assisted Design of Electrode Microstructures and Flow Fields for Redox Flow Batteries
Time & Date: 10:00 -11:00,Tuesday,February 28, 2023 (Beijing time)
Zoom Meeting:
https://cuhk
Zoom Meeting ID:956 0464 3160
Password：123456
Abstract:
Redox flow batteries (RFBs) offer a reliable solution for long-term and grid-scale storage of renewable energy. However, the lack of effective approaches to designing electrodes and flow fields limits the performance of RFBs. In this talk, I will demonstrate the potential of machine learning in designing electrode microstructures and flow fields for RFBs. First, we develop a generative adversarial network (GAN) to reconstruct the three-dimensional microstructure of RFB electrodes. The high quality of the images generated by GAN is shown through a statistical comparison between the real and generated datasets in terms of structural parameters (porosity, specific surface area, tortuosity) and two-point correlation function. Next, we develop a coupled machine learning and genetic algorithm approach to identifying the optimal structural parameters of RFB electrodes. The optimized electrodes perform up to 80% larger specific surface area and up to 50% higher hydraulic permeability than commercial electrodes. Finally, we develop a data-driven approach to designing flow fields, encompassing library generation, multi-physics simulation, and machine learning. The battery with newly designed flow fields yields about a 22% increase in limiting current density and up to 11% improvement in energy efficiency, compared to a conventional serpentine flow field.
Biography:
Shuaibin Wan obtained his B.Eng. degree in Material Science and Engineering from Harbin Institute of Technology in 2018 and received his Ph.D. degree in Mechanical Engineering from the Hong Kong University of Science and Technology in 2022. His research interests include machine learning and numerical simulation, with a focus on their applications in the design of energy storage systems.
