Accelerating battery research with retrieval-augmented large language models: Present and future

doi:10.19799/j.cnki.2095-4239.2024.0604

Abstract

Abstract:

In recent years, the surge in research investment within the battery field has presented researchers with challenges of information overload and knowledge gaps. This study examines the Retrieval-Augmented Generation (RAG) architecture of large language models in the battery domain, offering a review of contemporary research and future prospects. We describe the working principles of the RAG architecture, affirm its reliability in specialized domains, and discuss its applications across three key areas as follows: battery material design, battery cell design and manufacturing, and battery management systems for e-mobility and electric grids. In the section on battery material design, the study highlights the hallucination-free generation capabilities of RAG in data extraction, research protocol design, and multimodal data querying. The section on battery cell design and manufacturing elucidates RAG's role in enhancing research-driven battery cell design and bridging the gap between industry and academia, thereby aiding industrial control processes. The discussion on battery management systems for e-mobility and electric grids underscores RAG's contribution to cross-domain knowledge integration and system-level operation and maintenance support. The study concludes by considering the application of multimodal RAG technology in battery research and anticipates further expansion of RAG applications in this field.

Key words: large language model, retrieval augmented generation, battery material, battery cell, battery management system

CLC Number:

O 6-39

Yi ZHONG, Yan LENG, Sihui CHEN, Peiyi LI, Zhi ZOU, Yang LIU, Jiayu WAN. Accelerating battery research with retrieval-augmented large language models: Present and future[J]. Energy Storage Science and Technology, 2024, 13(9): 3214-3225.

Figures/Tables 4

References 68

3	RADFORD A, KIM J W, HALLACY C, et al. Learning transferable visual models from natural language supervision[EB/OL]. 2021: 2103.00020.[2024-06-30]. https://arxiv.org/abs/2103.00020v1
4	OpenAI. Hello GPT-4o[EB/OL]. [2024-06-30]. https://openai.com/index/hello-gpt-4o/
5	OpenAI. SORA[EB/OL]. [2024-06-30]. https://openai.com/sora
6	BUEHLER M J. Generative retrieval-augmented ontologic graph and multiagent strategies for interpretive large language model-based materials design[J]. ACS Engineering Au, 2024, 4(2): 241-277. DOI: 10.1021/acsengineeringau.3c00058.
7	BRAN A M, COX S, SCHILTER O, et al. Augmenting large language models with chemistry tools[J]. Nature Machine Intelligence, 2024, 6(5): 525-535. DOI: 10.1038/s42256-024-00832-8.
8	BOIKO D A, MACKNIGHT R, KLINE B, et al. Autonomous chemical research with large language models[J]. Nature, 2023, 624(7992): 570-578. DOI: 10.1038/s41586-023-06792-0.
9	KANG Y, KIM J. ChatMOF: An artificial intelligence system for predicting and generating metal-organic frameworks using large language models[J]. Nature Communications, 2024, 15(1): 4705. DOI: 10.1038/s41467-024-48998-4.
10	ZHENG Z L, ZHANG O F, BORGS C, et al. ChatGPT chemistry assistant for text mining and the prediction of MOF synthesis[J]. Journal of the American Chemical Society, 2023, 145(32): 18048-18062. DOI: 10.1021/jacs.3c05819.
11	JI Z W, LEE N, FRIESKE R, et al. Survey of hallucination in natural language generation[EB/OL]. 2022: 2202.03629.[2024-06-30]. https://arxiv.org/abs/2202.03629v7
12	吴思远, 王雪龙, 肖睿娟, 等. 基于大型语言模型的工具对电池研究的机遇与挑战[J]. 储能科学与技术, 2023, 12(3): 992-997. DOI: 10.19799/j.cnki.2095-4239.2023.0071.
	WU S Y, WANG X L, XIAO R J, et al. Problem and perspective for battery researcher based on large language model[J]. Energy Storage Science and Technology, 2023, 12(3): 992-997. DOI: 10.19799/j.cnki.2095-4239.2023.0071.
13	KIRKPATRICK J, PASCANU R, RABINOWITZ N, et al. Overcoming catastrophic forgetting in neural networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2017, 114(13): 3521-3526. DOI: 10.1073/pnas.1611835114.
14	TINN R, CHENG H, GU Y, et al. Fine-tuning large neural language models for biomedical natural language processing[J]. Patterns, 2023, 4(4): 100729. DOI: 10.1016/j.patter.2023.100729.
15	MOSBACH M, ANDRIUSHCHENKO M, KLAKOW D. On the stability of fine-tuning BERT: Misconceptions, explanations, and strong baselines[EB/OL]. 2020: 2006.04884.[2024-06-30]. https://arxiv.org/abs/2006.04884v3
16	KIM Y, OH J, KIM S, et al. How to fine-tune models with few samples: Update, data augmentation, and test-time augmentation[EB/OL]. 2022: 2205.07874.[2024-06-30].https://arxiv.org/abs/2205.07874v3
17	CHEN J W, LIN H Y, HAN X P, et al. Benchmarking large language models in retrieval-augmented generation[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(16): 17754-17762. DOI: 10.1609/aaai.v38i16.29728.
18	GAO Y F, XIONG Y, GAO X Y, et al. Retrieval-augmented generation for large language models: A survey[EB/OL]. 2023: 2312.10997.[2024-06-30]. https://arxiv.org/abs/2312.10997v5
19	EIBICH M, NAGPAL S, FRED-OJALA A. ARAGOG: Advanced RAG output grading[EB/OL]. 2024: 2404.01037.[2024-06-30]. https://arxiv.org/abs/2404.01037v1
20	PAN S R, LUO L H, WANG Y F, et al. Unifying large language models and knowledge graphs: A roadmap[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3580-3599. DOI: 10.1109/TKDE.2024.3352100.
21	ZHANG J, SUTING W, ZHAOXIANG W, et al. Solid electrolyte interphase (SEI) on graphite anode correlated with thermal runaway of lithium-ion batteries[J]. Energy Storage Science and Technology, 2023, 12(7): 2105-2118.
22	WANG A P, KADAM S, LI H, et al. Review on modeling of the anode solid electrolyte interphase (SEI) for lithium-ion batteries[J]. NPJ Computational Materials, 2018, 4: 15. DOI: 10.1038/s41524-018-0064-0.
23	WANG X X, NI L, XIE Q X, et al. Highly electrocatalytic active amorphous Al₂O₃ in porous carbon assembled on carbon cloth as an independent multifunctional interlayer for advanced lithium-sulfur batteries[J]. Applied Surface Science, 2023, 618: 156689. DOI: 10.1016/j.apsusc.2023.156689.
24	LAI G M, JIAO J Y, FANG C, et al. The mechanism of Li deposition on the Cu substrates in the anode-free Li metal batteries[J]. Small, 2023, 19(3): e2205416. DOI: 10.1002/smll. 202205416.
25	WANG F, SUN Y, CHENG J. Switching of redox levels leads to high reductive stability in water-in-salt electrolytes[J]. Journal of the American Chemical Society, 2023, 145(7): 4056-4064. DOI: 10.1021/jacs.2c11793.
26	HAN X, GU L H, SUN Z F, et al. Manipulating charge-transfer kinetics and a flow-domain LiF-rich interphase to enable high-performance microsized silicon-silver-carbon composite anodes for solid-state batteries[J]. Energy & Environmental Science, 2023, 16(11): 5395-5408. DOI: 10.1039/D3EE01696J.
27	CHEN G J, YU L W, GAN Y H, et al. Reinforcing the stability of cobalt-free lithium-rich layered oxides via Li-poor Ni-rich surface transformation[J]. Journal of Materials Chemistry A, 2024. DOI: 10.1039/d4ta01403k.
28	LI J, ZHOU M S, WU H H, et al. Machine learning-assisted property prediction of solid-state electrolyte[J]. Advanced Energy Materials, 2024, 14(20): 2304480. DOI: 10.1002/aenm.202304480.
29	MERCHANT A, BATZNER S, SCHOENHOLZ S S, et al. Scaling deep learning for materials discovery[J]. Nature, 2023, 624(7990): 80-85. DOI: 10.1038/s41586-023-06735-9.
30	XU J, XIAO R J, LI H. ESM cloud toolkit: A copilot for energy storage material research[J]. Chinese Physics Letters, 2024, 41(5): 054701. DOI: 10.1088/0256-307x/41/5/054701.
31	THIK J, WANG S W, WANG C H, et al. Realizing the cooking recipe of materials synthesis through large language models[J]. Journal of Materials Chemistry A, 2023, 11(47): 25849-25853. DOI: 10.1039/D3TA05457H.
32	DEB J, SAIKIA L, DIHINGIA K D, et al. ChatGPT in the material design: Selected case studies to assess the potential of ChatGPT[J]. Journal of Chemical Information and Modeling, 2024, 64(3): 799-811. DOI: 10.1021/acs.jcim.3c01702.
33	LIU Y, LI C, LI C X, et al. Porous, robust, thermally stable, and flame retardant nanocellulose/polyimide separators for safe lithium-ion batteries[J]. Journal of Materials Chemistry A, 2023, 11(43): 23360-23369. DOI: 10.1039/d3ta05148j.
34	凌仕刚, 许洁茹, 李泓. 锂电池研究中的EIS实验测量和分析方法[J]. 储能科学与技术, 2018, 7(4): 732-749. DOI: 10.12028/j.issn.2095-4239.2018.0092.
	LING S G, XU J R, LI H. Experimental measurement and analysis methods of electrochemical impedance spectroscopy for lithium batteries[J]. Energy Storage Science and Technology, 2018, 7(4): 732-749. DOI: 10.12028/j.issn.2095-4239.2018.0092.
35	LIU X H, HUANG J Y. In situ TEM electrochemistry of anode materials in lithium ion batteries[J]. Energy & Environmental Science, 2011, 4(10): 3844-3860. DOI: 10.1039/C1EE01918J.
36	KITAHARA A R, HOLM E A. Microstructure cluster analysis with transfer learning and unsupervised learning[J]. Integrating Materials and Manufacturing Innovation, 2018, 7(3): 148-156. DOI: 10.1007/s40192-018-0116-9.
37	ZHANG Y, LIN X Y, ZHAI W B, et al. Machine learning on microstructure-property relationship of lithium-ion conducting oxide solid electrolytes[J]. Nano Letters, 2024, 24(17): 5292-5300. DOI: 10.1021/acs.nanolett.4c00902.
38	KUSCHE C, RECLIK T, FREUND M, et al. Large-area, high-resolution characterisation and classification of damage mechanisms in dual-phase steel using deep learning[J]. PLoS One, 2019, 14(5): e0216493. DOI: 10.1371/journal.pone.0216493.
39	WANG Z H, ZHOU X Z, ZHANG W G, et al. Parameter sensitivity analysis and parameter identifiability analysis of electrochemical model under wide discharge rate[J]. Journal of Energy Storage, 2023, 68: 107788. DOI: 10.1016/j.est.2023.107788.
40	黄晟贤,徐会升,王起鹏,等.冲击荷载下圆柱型动力锂离子电池的响应特性研究[J/OL].储能科学与技术.[2024-05-05]. https://doi.org/10.19799/j.cnki.2095-4239.2024.0274.
	HUANG S, XU H, WANG Q, et al. Study on the Response characteristics of cylindrical power lithium-ion batteries under impact load[J/OL]. Energy Storage Science and Technology. [2024-05-05]. https://doi.org/10.19799/j.cnki.2095-4239.2024.0274.
41	WU X K, SONG K F, ZHANG X Y, et al. Safety issues in lithium ion batteries: Materials and cell design[J]. Frontiers in Energy Research, 2019, 7: 65. DOI: 10.3389/fenrg.2019.00065.
42	OAKLEY J. Intelligent cognitive assistants [EB/OL].[2024-06-30]. https://www.src.org/program/ica/
43	KERNAN FREIRE S, FOOSHERIAN M, WANG C F, et al. Harnessing large language models for cognitive assistants in factories[C]// Proceedings of the 5th International Conference on Conversational User Interfaces. ACM, 2023: 1-6. DOI: 10.1145/3571884.3604313.
44	CHEN H S, HOU L, WU S Z, et al. Augmented reality, deep learning and vision-language query system for construction worker safety[J]. Automation in Construction, 2024, 157: 105158. DOI: 10.1016/j.autcon.2023.105158.
1	VASWANI A, SHAZEER N, PARMER N, et al. Attention is all you need[J]. arXiv preprint arXiv:, 2017.
2	ZHAO S, CHEN S H, ZHOU J Y, et al. Potential to transform words to Watts with large language models in battery research[J]. Cell Reports Physical Science, 2024, 5(3): 101844. DOI: 10.1016/j.xcrp.2024.101844.
45	PERES R S, JIA X D, LEE J, et al. Industrial artificial intelligence in industry 4.0 - Systematic review, challenges and outlook[J]. IEEE Access, 2874, 8: 220121-220139. DOI: 10.1109/ACCESS. 2020.3042874.
46	GUO N L, CHEN S H, TAO J, et al. Semi-supervised learning for explainable few-shot battery lifetime prediction[J]. Joule, 2024, 8(6): 1820-1836. DOI: 10.1016/j.joule.2024.02.020.
47	TRIVEDI C, BHATTACHARYA P, PRASAD V K, et al. Explainable AI for industry 5.0: Vision, architecture, and potential directions[J]. IEEE Open Journal of Industry Applications, 2024, 5: 177-208. DOI: 10.1109/OJIA.2024.3399057.
48	ZHOU B, LI X Y, LIU T Y, et al. CausalKGPT: Industrial structure causal knowledge-enhanced large language model for cause analysis of quality problems in aerospace product manufacturing[J]. Advanced Engineering Informatics, 2024, 59: 102333. DOI: 10.1016/j.aei.2023.102333.
49	LIN T Z, CHEN S H, HARRIS S J, et al. Investigating explainable transfer learning for battery lifetime prediction under state transitions[J]. eScience, 2024: 100280. DOI: 10.1016/j.esci. 2024.100280.
50	朱伟杰, 史尤杰, 雷博. 锂离子电池储能系统BMS的功能安全分析与设计[J]. 储能科学与技术, 2020, 9(1): 271-278. DOI: 10.19799/j.cnki.2095-4239.2019.0177.
	ZHU W J, SHI Y J, LEI B. Functional safety analysis and design of BMS for lithium-ion battery energy storage system[J]. Energy Storage Science and Technology, 2020, 9(1): 271-278. DOI: 10.19799/j.cnki.2095-4239.2019.0177.
51	SHEN M, GAO Q. A review on battery management system from the modeling efforts to its multiapplication and integration[J]. International Journal of Energy Research, 2019, 43(10): 5042-5075.
52	RAHIMI-EICHI H, OJHA U, BARONTI F, et al. Battery management system: An overview of its application in the smart grid and electric vehicles[J]. IEEE Industrial Electronics Magazine, 2013, 7(2): 4-16. DOI: 10.1109/MIE.2013.2250351.
53	LIU Y, CHEN S H, LI P Y, et al. Status, challenges, and promises of data-driven battery lifetime prediction under cyber-physical system context[J]. IET Cyber-Physical Systems: Theory & Applications, 2024. DOI: 10.1049/cps2.12086.
54	LU T, ZHAI X A, CHEN S H, et al. Robust battery lifetime prediction with noisy measurements via total-least-squares regression[J]. Integration, 2024, 96: 102136. DOI: 10.1016/j.vlsi. 2023.102136.
55	LAWDER M T, SUTHAR B, NORTHROP P W C, et al. Battery energy storage system (BESS) and battery management system (BMS) for grid-scale applications[J]. Proceedings of the IEEE, 2014, 102(6): 1014-1030. DOI: 10.1109/JPROC.2014.2317451.
56	MISHRA S, SWAIN S C, SAMANTARAY R K. A Review on battery management system and its application in electric vehicle[C]// 2021 International Conference on Advances in Computing and Communications (ICACC). IEEE, 2021: 1-6. DOI: 10.1109/ICACC-202152719.2021.9708114.
57	WANG J, FENG X N, YU Y Z, et al. Rapid temperature-responsive thermal regulator for safety management of battery modules[J]. Nature Energy, 2024, 9: 939-946. DOI: 10.1038/s41560-024-01535-5.
58	CHEN X J, JIA S B, XIANG Y. A review: Knowledge reasoning over knowledge graph[J]. Expert Systems with Applications, 2020, 141: 112948. DOI: 10.1016/j.eswa.2019.112948.
59	XIONG R, LI L L, TIAN J P. Towards a smarter battery management system: A critical review on battery state of health monitoring methods[J]. Journal of Power Sources, 2018, 405: 18-29. DOI: 10.1016/j.jpowsour.2018.10.019.
60	ZHAO X Z, SUN B X, ZHANG W G, et al. Error theory study on EKF-based SOC and effective error estimation strategy for Li-ion batteries[J]. Applied Energy, 2024, 353: 121992. DOI: 10.1016/j.apenergy.2023.121992.
61	XIONG R, SUN Y, WANG C X, et al. A data-driven method for extracting aging features to accurately predict the battery health[J]. Energy Storage Materials, 2023, 57: 460-470. DOI: 10.1016/j.ensm.2023.02.034.
62	WANG W T, YANG K Y, ZHANG L S, et al. An end-cloud collaboration approach for online state-of-health estimation of lithium-ion batteries based on multi-feature and transformer[J]. Journal of Power Sources, 2024, 608: 234669. DOI: 10.1016/j.jpowsour.2024.234669.
63	吴思远, 李泓. 发展基于"语义检测" 的低参数量、多模态预训练电池通用人工智能模型[J]. 储能科学与技术, 2024, 13(4): 1216-1224. DOI: 10.19799/j.cnki.2095-4239.2024.0092.
	WU S Y, LI H. Developing a general pretrained multimodal battery model with small parameters based on semantic detection[J]. Energy Storage Science and Technology, 2024, 13(4): 1216-1224. DOI: 10.19799/j.cnki.2095-4239.2024.0092.
64	WU S Q, FEI H, QU L G, et al. NExT-GPT: Any-to-any multimodal LLM[EB/OL]. 2023: 2309.05519. https://arxiv.org/abs/2309. 05519v3
65	JABLONKA K M, AI Q X, AL-FEGHALI A, et al. 14 examples of how LLMs can transform materials science and chemistry: A reflection on a large language model hackathon[J]. Digital Discovery, 2023, 2(5): 1233-1250. DOI: 10.1039/d3dd00113j.
66	BRUCKHAUS T. RAG does not work for enterprises[EB/OL]. 2024: 2406.04369.[2024-06-30]. https://arxiv.org/abs/2406.04369v1
67	LIU Y, HUANG L Z, LI S C, et al. RECALL: A benchmark for LLMs robustness against external counterfactual knowledge[EB/OL]. 2023: 2311.08147.[2024-06-30]. https://arxiv.org/abs/2311.08147v1
68	ANDERSON M, AMIT G, GOLDSTEEN A. Is my data in your retrieval database? membership inference attacks against retrieval augmented generation[EB/OL]. 2024: 2405.20446.[2024-06-30]. https://arxiv.org/abs/2405.20446v2

[1]	Zhenwei ZHU, Jiawei MIAO, Xiayu ZHU, Xiaoxu WANG, Jingyi QIU, Hao ZHANG. Research progress in lithium-ion battery remaining useful life prediction based on machine learning [J]. Energy Storage Science and Technology, 2024, 13(9): 3134-3149.
[2]	Ziyu LIU, Zekun JIANG, Wei QIU, Quan XU, Yingchun NIU, Chunming XU, Tianhang ZHOU. Application of artificial intelligence in long-duration redox flow batteries storage systems [J]. Energy Storage Science and Technology, 2024, 13(9): 2871-2883.
[3]	Yuhang YUAN, Yuchen GAO, Jundong ZHANG, Yanbin GAO, Chaolong WANG, Xiang CHEN, Qiang ZHANG. The application of large language models in energy storage research [J]. Energy Storage Science and Technology, 2024, 13(9): 2907-2919.
[4]	Xintian XU, Bixiao ZHANG, Xinlong ZHU, Kaijie YANG. Refined thermal design optimization of energy storage battery system based on battery box openings [J]. Energy Storage Science and Technology, 2024, 13(2): 515-525.
[5]	Qi ZHANG, Xiaodong LI, Wenwen WANG, Xiao LIU. Rational design of multifunctional cellulose based materials for their application in emerging energy storage [J]. Energy Storage Science and Technology, 2023, 12(5): 1427-1443.
[6]	Chunhui LIU, Hongbin REN. Research on active equalization of power batteries based on state of charge [J]. Energy Storage Science and Technology, 2022, 11(2): 667-672.
[7]	Bin FAN, Chenglong JIANG, Chunjing LIN, Yupeng LI, Bayi YU, Jinjie ZHANG, Liang ZHANG, Mengyang GAO, Wei WANG, Kun XIE, Hong CHANG. Experimental study on the cycle life of electric vehicle battery systems [J]. Energy Storage Science and Technology, 2021, 10(2): 671-678.
[8]	Xincheng LIANG, Mian ZHANG, Guojun HUANG. Review on lithium-ion battery modeling methods based on BMS [J]. Energy Storage Science and Technology, 2020, 9(6): 1933-1939.
[9]	ZHU Weijie, SHI Youjie, LEI Bo. Functional safety analysis and design of BMS for lithium-ion battery energy storage system [J]. Energy Storage Science and Technology, 2020, 9(1): 271-278.
[10]	LUO Yong, ZHAO Xiaoshuai, QI Pengwei, LIU Zengyue, DENG Tao, LI Peiran. Second-order RC modeling and parameter identification of electric vehicle power battery [J]. Energy Storage Science and Technology, 2019, 8(4): 738-744.
[11]	CHEN Shixuan, JIN Peng. Application of LTC6803 in energy storage management system of Ni-MH battery#br# [J]. Energy Storage Science and Technology, 2017, 6(S1): 31-.
[12]	LUO Hongbin, DENG Linwang, FENG Tianyu, LV Chun. The relationship between internal resistance and discharge rate of LiFePO4 batteries [J]. Energy Storage Science and Technology, 2017, 6(4): 799-805.
[13]	ZHANG Jian1, GUO Weiwen1,2, ZOU Haishu3, SHAO Guangjie2, LOU Yuwan1, XIA Baojia1 . 100 kW/200 kW·h energy storage system of MH-Ni batteries [J]. Energy Storage Science and Technology, 2016, 5(4): 596-601.
[14]	XU Shouping, HOU Chaoyong, YANG Shuili. A Li-ion battery management system for large-capacity energy storage [J]. Energy Storage Science and Technology, 2016, 5(1): 69-77.
[15]	PEI Lina, HUANG Zhe, DONG Dexin. A hierarchical management system for energy storage batteries [J]. Energy Storage Science and Technology, 2014, 3(4): 416-422.