EXTENDED ABSTRACT: In the era of AI for Science, the Battery Design Automation (BDA) intelligent R&D platform has brought revolutionary changes to the ffeld of battery research and development by integrating advanced artiffcial intelligence technologies. The BDA platform covers ffve key aspects of battery R&D: 'Read', 'Design', 'Make', 'Test', and 'Analysis'. It utilizes advanced algorithms such as machine learning, multi-scale modeling, and pre-training models, and combines them with software engineering to develop user-friendly tools to accelerate the entire battery R&D cycle from theoretical design to experimental validation. Through automated experimental design, synthesis and preparation, characterization testing, and performance optimization, the BDA platform not only enhances R&D efffciency but also improves the accuracy and reliability of battery design, promoting the development of battery technology towards higher energy density, longer cycle life, and lower costs.
Keywords: AI for Science;battery;Intelligent Research and Development;machine learning; Battery Design Automation; Multi-scale
REFERENCES:
[1] Deng Bin, Hua Haiming, Zhang Yuzi, WANG Xiaoxu*ZHANG Linfeng. Deep potential method and its application to electrochemical energy storage materials [J]. Energy Storage Science and Technology, 2024, 13(9): 2884-2906.
[2] Xie Yingying, Deng Bin, Zhang Yuzi, WANG Xiaoxu*, ZHANG Linfeng. Intelligent R&D of Battery Design Automation (BDA) in the Era of AI for Science [J]. Energy Storage Science and Technology, 2024, 13(9): 2884-290
Wang Xiaoxu, Vice President of Intelligent R&D at DP Technology and General Manager of the Energy Materials Business Unit; Senior Researcher at the AISI; PhD. The main research direction at the company is to use AI and multi-scale computing in the new research paradigm of AI for Science to rationally design and develop new energy materials and devices (batteries, catalytic chemistry, photovoltaics, etc.). He is also the leader of Piloteye, a research and practice platform for battery BDA (Battery Design Automation), and has published over 40 SCI papers in prestigious journals such as JACS, AM, AEM, JMCA, and CEJ. He has participated in and led more than ten key national projects funded by the Ministry of Science and Technology and the Ministry of Industry and Information Technology. He is currently a member of the Committee on Chemical Engineering Big Data and Intelligent Design of the China Chemical Society; a postgraduate industry mentor at Nankai University. He was previously employed by the Beijing Computing Center, where he was responsible for designing new material calculation platforms, conducting high-throughput screening of new materials, and optimizing machine learning. He has received numerous industry awards, including the Leading Science and Technology Achievement Award at the Digital China Expo for the ffrst-authored research results, the Invention and Entrepreneurship Award at the National Invention Exhibition, and the Innovation Award in Big Data and Intelligent Computing Technology.