Problem and perspective for battery researcher based on large language model

doi:10.19799/j.cnki.2095-4239.2023.0071

Abstract

Abstract:

The Natural Language Process (NLP) models such as ChatGPT and GPT-3 have been discussed recently in academia and the Nature Publishing Group allows the authors to use ChatGPT to assist academic research. This means machine learning especially NLP has been integrated into the academia and will change the research paradigm. It exists opportunity and challenge for the battery researchers especially in replacing monotonous repetitive work. What can the researchers do for batteries, how to construct and use it to assist battery researching and the problem existing in it have not been discussed in details. Based on it, we write this perspective to explain above questions especially the following: ① The problems existing in NLP models; ② What can the battery practitioners do to meet these opportunities and challenges; and ③ How to learn the basic knowledge and construct battery model. All discussions are based on our recent works and the use of models and we hope it will offer initial guidance for battery researchers.

Key words: battery, natural language process, automation

CLC Number:

O6-39

Siyuan WU, Xuelong WANG, Ruijuan XIAO, Hong LI. Problem and perspective for battery researcher based on large language model[J]. Energy Storage Science and Technology, 2023, 12(3): 992-997.

Figures/Tables 6

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

References 12

1	Galactica大型语言模型[EB/OL]. https://galactica.org/explore/.
2	ChatGPT语言模型[EB/OL]. https://openai.com/blog/chatgpt/.
3	Nature. Tools such as ChatGPT threaten transparent science; here are our ground rules for their use[J]. Nature, 2023, 613(7945): 612.
4	LI H. Practical evaluation of Li-ion batteries[J]. Joule, 2019, 3(4): 911-914.
5	FRITH J T, LACEY M J, ULISSI U. A non-academic perspective on the future of lithium-based batteries[J]. Nature Communications, 2023, 14(1): 1-17.
6	WARD L, BABINEC S, DUFEK E J, et al. Principles of the battery data genome[J]. Joule, 2022, 6(10): 2253-2271.
7	Scikit-learn指导手册[Z/OL]. https://scikit-learn.org/stable/user_guide.html.
8	Tensorflow指导手册[Z/OL]. https://tensorflow.google.cn/learn?hl=zh-cn.
9	Pytorch指导手册[Z/OL]. https://pytorch.org/tutorials/.
10	Kears指导手册[Z/OL]. https://keras.io/zh/.
11	中国科学院凝聚态物质科学数据中心文献动态[DB/OL]. http://condmatt.iphy.ac.cn/literature_trends/newest.
12	HUANG S, COLE J M. BatteryBERT: A pretrained language model for battery database enhancement[J]. Journal of Chemical Information and Modeling, 2022, 62(24): 6365-6377.

[1]	Yunjie LI, Guangyu ZHANG, Weiwen ZHU, Yuanyuan MIN, Chengfei RAO, Yanfei SUN, Qingqing XU. The dynamic simulation of pressure relief characteristics of the power battery vent based on choking flow [J]. Energy Storage Science and Technology, 2023, 12(3): 960-967.
[2]	Ting TING, Qihang LIN, Changyang LIU, Liuzhen BIAN, Chao SUN, QI Ji, Jihua PENG, Shengli AN. Research progress in modification of manganese dioxide as cathode materials for aqueous zinc-ion batteries [J]. Energy Storage Science and Technology, 2023, 12(3): 754-767.
[3]	Zihao LIU, Xuesong ZHANG, Da LIN, Liqing SUN, Zhengyang LI, Rui XIONG. Joint energy and power state estimation method for energy storage battery based on extended Kalman filter [J]. Energy Storage Science and Technology, 2023, 12(3): 913-922.
[4]	Yiming YAO, Weiling LUAN, Ying CHEN, Min SUN. Recent progress in aging degradation of lithium-ion battery materials via in-situ optical microscopy [J]. Energy Storage Science and Technology, 2023, 12(3): 777-791.
[5]	Xin ZHENG, Hao YU, Xiaoyu GUO, Ying ZHOU, Yuanjie ZUO, Yujia LIU. Design optimization of integrated energy system using liquid flow battery and heating and cooling storage energy system [J]. Energy Storage Science and Technology, 2023, 12(3): 870-877.
[6]	Kuijie LI, Ping LOU, Minyuan GUAN, Jinlong MO, Weixin ZHANG, Yuancheng CAO, Shijie CHENG. A review of multi-dimensional signal evolution and coupling mechanism of lithium-ion battery thermal runaway [J]. Energy Storage Science and Technology, 2023, 12(3): 899-912.
[7]	Mai FENG, Nan CHEN, Renjie CHEN. Research progress of low-temperature electrolyte for lithium-ion battery [J]. Energy Storage Science and Technology, 2023, 12(3): 792-807.
[8]	Zhixiang CHENG, Wei CAO, Bo HU, Yunfang CHENG, Xin LI, Lihua JIANG, Kaiqiang JIN, Qingsong WANG. Thermal runaway and explosion propagation characteristics of large lithium iron phosphate battery for energy storage station [J]. Energy Storage Science and Technology, 2023, 12(3): 923-933.
[9]	Xue YUAN, Hongji LI, Wenhui BAI, Zhengxi LI, Libin YANG, Kai WANG, Zhe CHEN. Application of biomass-derived carbon-based anode materials in sodium ion battery [J]. Energy Storage Science and Technology, 2023, 12(3): 721-742.
[10]	Xinhao ZHAO, Liang XU. Improved firefly optimization algorithm to optimize back propagation neural network for state of health estimation of power lithium ion batteries [J]. Energy Storage Science and Technology, 2023, 12(3): 934-940.
[11]	Xiaoxue PU, Shaobo YANG, Aixue TUO, Lisha MOU, Qi NA. Simulation analysis on sensitivity of discharge capacity on design parameters of a battery [J]. Energy Storage Science and Technology, 2023, 12(3): 951-959.
[12]	Fan YANG, Jiarui HE, Ming LU, Lingxia LU, Miao YU. SOC estimation of lithium-ion batteries based on BP-UKF algorithm [J]. Energy Storage Science and Technology, 2023, 12(2): 552-559.
[13]	Guihong GAO, Shenshen LI, Fuyuan LIU, Xiangkun WU, Yanxia LIU. Study on the influence of particle composition on the performance of lithium slurry batteries [J]. Energy Storage Science and Technology, 2023, 12(2): 329-338.
[14]	Xueqing SHEN, Wei CHEN. Thermal management performance of batteries with embedded tree-like fins for phase transition layers [J]. Energy Storage Science and Technology, 2023, 12(2): 459-467.
[15]	Lulu LI, Zhengshun TAO, Tinglong PAN, Weilin YANG, Guanyang HU. Research on fractional modeling and SOC estimation strategy for lithium batteries [J]. Energy Storage Science and Technology, 2023, 12(2): 544-551.