大语言模型在储能研究中的应用

doi:10.19799/j.cnki.2095-4239.2024.0176

摘要/Abstract

摘要：

在碳达峰、碳中和的大背景下，储能科学作为一门信息密集、多学科交叉的研究领域，迫切需要新研究方法以应对其日益复杂的难题与挑战。随着人工智能技术的快速发展，大语言模型在文本处理、信息收集与整合、图片与视频生成等领域取得了巨大的成功，其应用也在逐渐延伸至自然科学研究领域，并在提升科研效率等方面展现出了巨大的潜力，有望助力储能科学应对未来挑战。本文首先以ChatGPT为例，回顾了人工智能和大语言模型领域的重大进展，从社会生活和科学研究两方面分析了这些进展所产生的影响，整理了国内重点的大语言模型；然后结合储能领域的具体案例介绍大语言模型的基本概念及原理，并从信息处理、信息生成和系统集成三个方面详细探讨大语言模型在储能研究中的应用，凸显这一全新研究方法的实际效果与发展前景；最后结合具体时代背景，指出大语言模型与储能交叉研究的挑战与未来发展方向，并对这一新领域做出总结和展望。

关键词: 大语言模型, 人工智能, 储能技术, 二次电池

Abstract:

In the pursuit of carbon neutrality, energy storage technology plays an increasingly crucial role in modern society. Addressing future challenges requires innovative methods in energy storage research, given its interdisciplinary and information-intensive nature. With the rapid development of artificial intelligence technology, large language models (LLMs) have achieved significant success in various domains, including text processing, information collection and integration, and picture and video generation. Moreover, the application of LLMs has extended to natural science research, demonstrating promising potential for improving research efficiency. Thus, LLMs are expected to assist in addressing future challenges in energy storage science and technology. This paper first focuses on ChatGPT and reviews AI advancements and LLMs, analyzing their impact on civil use and scientific research, particularly focusing on domestic LLMs. Subsequently, it discusses the basic concepts and fundamentals of LLMs and their application in energy storage, covering information processing, information generation, and system integration. Detailed examples are provided to illustrate the effectiveness of these new methods. Finally, this study outlines the remaining challenges and future development directions of the interdisciplinary nature of LLMs and energy storage.

Key words: large language model, artificial intelligence, energy storage technology, secondary battery

中图分类号:

TP 18

袁誉杭, 高宇辰, 张俊东, 高岩斌, 王超珑, 陈翔, 张强. 大语言模型在储能研究中的应用[J]. 储能科学与技术, 2024, 13(9): 2907-2919.

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.

图/表 8

图1

表1

图2

图3

图4

图5

图6

图7

参考文献 58

1	SILVER D, HUANG A, MADDISON C J, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529(7587): 484-489.
2	SILVER D, SCHRITTWIESER J, SIMONYAN K, et al. Mastering the game of Go without human knowledge[J]. Nature, 2017, 550(7676): 354-359.
3	JUMPER J, EVANS R, PRITZEL A, et al. Highly accurate protein structure prediction with AlphaFold[J]. Nature, 2021, 596(7873): 583-589.
4	SENIOR A W, EVANS R, JUMPER J, et al. Improved protein structure prediction using potentials from deep learning[J]. Nature, 2020, 577(7792): 706-710.
5	BROWN T B, MANN B, RYDER N, et al. Language models are few-shot learners[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. December 6-12, 2020, Vancouver, BC, Canada. ACM, 2020: 1877-1901.
6	ELOUNDOU T, MANNING S, MISHKIN P, et al. GPTs are GPTs: An early look at the labor market impact potential of large language models[EB/OL]. 2023: arXiv: 2303.10130.[2023-12-05]. http://arxiv.org/abs/2303.10130
7	ZHAO W X, ZHOU K, LI J Y, et al. A survey of large language models[EB/OL]. 2023: arXiv: 2303.18223.[2023-12-05]. http://arxiv.org/abs/2303.18223
8	WU T Y, HE S Z, LIU J P, et al. A brief overview of ChatGPT: The history, status quo and potential future development[J]. IEEE/CAA Journal of Automatica Sinica, 2023, 10(5): 1122-1136.
9	ZHANG D, LIU X, ZHANG X Y, et al. DPA-2: Towards a universal large atomic model for molecular and material simulation[EB/OL]. 2023: arXiv: 2312.15492.[2023-12-05]. http://arxiv.org/abs/2312.15492
10	LIAO C, YU Y M, MEI Y, et al. From words to molecules: A survey of large language models in chemistry[EB/OL]. 2024: arXiv: 2402.01439. http://arxiv.org/abs/2402.01439
11	WHITE A D. The future of chemistry is language[J]. Nature Reviews Chemistry, 2023, 7(7): 457-458.
12	ALAWIDA M, MEJRI S, MEHMOOD A, et al. A comprehensive study of ChatGPT: Advancements, limitations, and ethical considerations in natural language processing and cybersecurity[J]. Information, 2023, 14(8): 462.
13	BISHOP C M. Neural networks and their applications[J]. Review of Scientific Instruments, 1994, 65(6): 1803-1832.
14	GONG S, WANG S, ZHU T S, et al. Multimodal machine learning for materials science: Composition-structure bimodal learning for experimentally measured properties[EB/OL]. 2023: arXiv: 2309.04478. [2023-12-05].http://arxiv.org/abs/2309.04478
15	LIU X Y, PENG H J, LI B Q, et al. Untangling degradation chemistries of lithium-sulfur batteries through interpretable hybrid machine learning[J]. Angewandte Chemie, 2022, 61(48): e202214037.
16	HAN C, GAO Y C, CHEN X, et al. A self-adaptive, data-driven method to predict the cycling life of lithium-ion batteries[J]. InfoMat, 2024: e12521.
17	STUART J. RUSSELL P N. Artificial intelligence: A modern approach, Third Edition [M]. Beijing: Tsinghua University Press, 2013.
18	GOODFELLOW I, BENGIO Y, COURVILLE A. Deep learning [M]. Beijing: Posts & Telecom Press, 2017.
19	CASTRO NASCIMENTO C M, PIMENTEL A S. Do large language models understand chemistry? A conversation with ChatGPT[J]. Journal of Chemical Information and Modeling, 2023, 63(6): 1649-1655.
20	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.
	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.
21	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.
22	LIU Y X, SHI K J, HE K S, et al. On learning to summarize with large language models as references[EB/OL]. 2023: arXiv: 2305.14239.[2023-12-05]. http://arxiv.org/abs/2305.14239
23	XIE T, WAN Y W, HUANG W, et al. Large language models as master key: Unlocking the secrets of materials science with GPT[EB/OL]. 2023: arXiv: 2304.02213.[2023-12-05]. http://arxiv.org/abs/2304.02213
24	LI J T, LIU Y Q, FAN W Q, et al. Empowering molecule discovery for molecule-caption translation with large language models: A ChatGPT perspective[EB/OL]. 2023: arXiv: 2306.06615.[2023-12-05]. http://arxiv.org/abs/2306.06615
25	KUZMAN T, MOZETIČ I, LJUBEŠIĆ N. Automatic genre identification for robust enrichment of massive text collections: Investigation of classification methods in the era of large language models[J]. Machine Learning and Knowledge Extraction, 2023, 5(3): 1149-1175.
26	ALSHAMI A, ELSAYED M, ALI E, et al. Harnessing the power of ChatGPT for automating systematic review process: Methodology, case study, limitations, and future directions[J]. Systems, 2023, 11(7): 351.
27	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.
28	TANG L Y, SUN Z Y, IDNAY B, et al. Evaluating large language models on medical evidence summarization[J]. NPJ Digital Medicine, 2023, 6(1): 158.
29	FARROKHNIA M, BANIHASHEM S K, NOROOZI O, et al. A SWOT analysis of ChatGPT: Implications for educational practice and research[J]. Innovations in Education and Teaching International, 2023: 1-15.
30	HARRER S. Attention is not all you need: The complicated case of ethically using large language models in healthcare and medicine[J]. EBioMedicine, 2023, 90: 104512.
31	BISWAS S, LOGAN N S, DAVIES L N, et al. Assessing the utility of ChatGPT as an artificial intelligence-based large language model for information to answer questions on myopia[J]. Ophthalmic & Physiological Optics, 2023, 43(6): 1562-1570.
32	DWIVEDI Y K, KSHETRI N, HUGHES L, et al. Opinion Paper: "So what if ChatGPT wrote it?" Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy[J]. International Journal of Information Management, 2023, 71: 102642.
33	YU-HAN C, CHUN-CHING C. Investigating the impact of generative artificial intelligence on brainstorming: A preliminary study[C]//2023 International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan). PingTung, Taiwan, China. IEEE, 2023: 193-194.
34	SUMMERS-STAY D, VOSS C R, LUKIN S M. Brainstorm, then select: A generative language model improves its creativity score[C]. In: The AAAI-23 Workshop on Creative AI Across Modalities, F, 2023.
35	ALZAABI A, ALAMRI A, ALBALUSHI H, et al. ChatGPT applications in academic research: A review of benefits, concerns, and recommendations [J]. bioRxiv, 2023, 2023. 08.17.553688.
36	LUND B D, WANG T, MANNURU N R, et al. ChatGPT and a new academic reality: Artificial Intelligence-written research papers and the ethics of the large language models in scholarly publishing[J]. Journal of the Association for Information Science and Technology, 2023, 74(5): 570-581.
37	COTTON D R E, COTTON P A, SHIPWAY J R. Chatting and cheating: Ensuring academic integrity in the era of ChatGPT[J]. Innovations in Education and Teaching International, 2024, 61(2): 228-239.
38	CHEN M, TWOREK J, JUN H, et al. Evaluating large language models trained on code[EB/OL]. 2021: arXiv: 2107.03374.[2023-12-05]. http://arxiv.org/abs/2107.03374
39	FENG Y H, VANAM S, CHERUKUPALLY M, et al. Investigating code generation performance of ChatGPT with crowdsourcing social data[C]//2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC). Torino, Italy. IEEE, 2023: 876-885.
40	SARSA S, DENNY P, HELLAS A, et al. Automatic generation of programming exercises and code explanations using large language models[C]//Proceedings of the 2022 ACM Conference on International Computing Education Research-Volume 1. August 7-11, 2022, Lugano and Virtual Event, Switzerland. ACM, 2022: 27-43.
41	BURGER B, MAFFETTONE P M, GUSEV V V, et al. A mobile robotic chemist[J]. Nature, 2020, 583(7815): 237-241.
42	ZHU Q, ZHANG F, HUANG Y, et al. An all-round AI-Chemist with a scientific mind[J]. National Science Review, 2022, 9(10): nwac190.
43	SZYMANSKI N J, RENDY B, FEI Y X, et al. An autonomous laboratory for the accelerated synthesis of novel materials[J]. Nature, 2023, 624(7990): 86-91.
44	BOIKO D A, MACKNIGHT R, KLINE B, et al. Autonomous chemical research with large language models[J]. Nature, 2023, 624(7992): 570-578.
45	BRAN A M, COX S, SCHILTER O, et al. ChemCrow: Augmenting large-language models with chemistry tools[EB/OL]. 2023: arXiv: 2304.05376.[2023-12-05]. http://arxiv.org/abs/2304.05376
46	MERCHANT A, BATZNER S, SCHOENHOLZ S S, et al. Scaling deep learning for materials discovery[J]. Nature, 2023, 624(7990): 80-85.
47	RUAN J Q, LIANG G Q, ZHAO H, et al. Applying large language models to power systems: Potential security threats[J]. IEEE Transactions on Smart Grid, 2023, 15: 3333-3336.
48	BONADIA R S, TRINDADE F C L, FREITAS W, et al. On the potential of ChatGPT to generate distribution systems for load flow studies using OpenDSS[J]. IEEE Transactions on Power Systems, 2023, 38(6): 5965-5968.
49	ZENG R, QU L, GAO F, et al. Development status and prospects of the Energy Internet [J]. Scientia Sinica Informationis, 2017, 47(2): 149-170.
50	曹祎, 张莉, 郭静, 等. 基于大语言模型的低碳电力市场发展应用前景[J]. 智慧电力, 2024, 52(2): 8-16.
	CAO Y, ZHANG L, GUO J, et al. Prospects for development of low-carbon electricity markets based on large language models[J]. Smart Power, 2024, 52(2): 8-16.
51	康重庆, 刘静琨, 张宁. 未来电力系统储能的新形态: 云储能[J]. 电力系统自动化, 2017, 41(21): 2-8, 16.
	KANG C Q, LIU J K, ZHANG N. A new form of energy storage in future power system: Cloud energy storage[J]. Automation of Electric Power Systems, 2017, 41(21): 2-8, 16.
52	KIM S C, OYAKHIRE S T, ATHANITIS C, et al. Data-driven electrolyte design for lithium metal anodes[J]. Proceedings of the National Academy of Sciences of the United States of America, 2023, 120(10): e2214357120.
53	赖根明, 焦君宇, 蒋耀, 等. 机器学习原子势在锂金属负极中的应用[J]. 硅酸盐学报, 2023, 51(2): 469-475.
	LAI G M, JIAO J Y, JIANG Y, et al. Analysis of Li metal anode by machine learning potential[J]. Journal of the Chinese Ceramic Society, 2023, 51(2): 469-475.
54	罗啸山, 王振雨, 高朋越, 等. 机器学习加速理论晶体结构预测研究进展[J]. 硅酸盐学报, 2023, 51(2): 552-560.
	LUO X S, WANG Z Y, GAO P Y, et al. Review on machine learning accelerated crystal structure prediction[J]. Journal of the Chinese Ceramic Society, 2023, 51(2): 552-560.
55	YAO N, CHEN X, FU Z H, et al. Applying classical, Ab initio, and machine-learning molecular dynamics simulations to the liquid electrolyte for rechargeable batteries[J]. Chemical Reviews, 2022, 122(12): 10970-11021.
56	FU Z H, CHEN X, YAO N, et al. The chemical origin of temperature-dependent lithium-ion concerted diffusion in sulfide solid electrolyte Li₁₀GeP₂S₁₂[J]. Journal of Energy Chemistry, 2022, 70: 59-66.
57	GAO Y C, YAO N, CHEN X, et al. Data-driven insight into the reductive stability of ion-solvent complexes in lithium battery electrolytes[J]. Journal of the American Chemical Society, 2023, 145(43): 23764-23770.
58	HONG Z J. ChatGPT for computational materials science: A perspective[J]. Energy Material Advances, 2023, 4: 0026.

比较项目	GPT-1	GPT-2	GPT-3	GPT-4
发布时间	2018年6月	2019年2月	2020年5月	2023年3月
参数数量	1.17亿	15亿	1750亿	—
解码层层数	12层	48层	96层	128层
隐藏层层数	768层	1600层	12888层	20480层
上下文窗口	512个令牌	1024个令牌	2049个令牌	8192个令牌
预训练数据大小	约5 GB	约40 GB	约45 TB	未公开
数据来源	BooksCorpus, Wikipedia	WebText	Common Crawl, etc.	未公开
文本总结能力	不支持	不支持	支持	加强
学习目标	无监督学习	多任务学习	上下文学习	多模态学习

[1]	黄家辉, 邝祝芳. 人工智能与储能技术融合的前沿发展[J]. 储能科学与技术, 2024, 13(9): 3161-3181.
[2]	焦君宇, 张全權, 陈宁波, 王冀钰, 芦秋迪, 丁浩浩, 彭鹏, 宋孝河, 张帆, 郑家新. 电池大数据智能分析平台的研发与应用[J]. 储能科学与技术, 2024, 13(9): 3198-3213.
[3]	许晶, 王宇琦, 符晓, 杨其凡, 连景臣, 王力奇, 肖睿娟. 基于大数据的电池新材料设计[J]. 储能科学与技术, 2024, 13(9): 2920-2932.
[4]	钟逸, 冷彦, 陈思慧, 李培义, 邹智, 刘洋, 万佳雨. 基于大语言模型RAG架构的电池加速研究：现状与展望[J]. 储能科学与技术, 2024, 13(9): 3214-3225.
[5]	刘子玉, 姜泽坤, 邱伟, 徐泉, 牛迎春, 徐春明, 周天航. 人工智能在长时液流电池储能中的应用：性能优化和大模型[J]. 储能科学与技术, 2024, 13(9): 2871-2883.
[6]	朱文韬, 周杨, 徐艺敏, 施涛. 电池储能技术在新能源发电系统中的应用与优化[J]. 储能科学与技术, 2024, 13(8): 2737-2739.
[7]	张楚, 陈栋才, 陈湘萍, 蔡永翔. 多应用场景下储能最优配置经济性效益分析[J]. 储能科学与技术, 2024, 13(6): 2078-2088.
[8]	孙健, 陶建龙, 胡芸蓉, 蔡潇龙, 杨勇平. 基于热泵型储电技术国内外研究综述[J]. 储能科学与技术, 2024, 13(6): 1963-1976.
[9]	杨建航, 冯文婷, 韩俊伟, 魏欣茹, 马晨宇, 毛常明, 智林杰, 孔德斌. 锂/钠-氯二次电池的最新进展——从材料构建到性能评估[J]. 储能科学与技术, 2024, 13(6): 1824-1834.
[10]	周理, 刘琰. 合金材料在储能技术中的应用与发展[J]. 储能科学与技术, 2024, 13(6): 1874-1876.
[11]	孙振新, 张秩鸣, 马俯波, 蒋丛进, 杜昊易, 陈换军, 张玉魁. 基于熵理论的能量调节性能研究[J]. 储能科学与技术, 2024, 13(5): 1584-1591.
[12]	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.
[13]	李天晨, 尹建政, 张大伟, 刘小恒. 基于水电站储能技术的可再生能源并网策略研究[J]. 储能科学与技术, 2024, 13(2): 677-679.
[14]	闫苏, 钟芳芳, 刘俊伟, 丁美, 贾传坤. 高能量密度液流电池关键材料与先进表征[J]. 储能科学与技术, 2024, 13(1): 143-156.
[15]	陈淑媛, 程晨, 夏啸, 鞠焕鑫, 张亮. 高比能二次电池正极材料的X射线谱学研究进展[J]. 储能科学与技术, 2024, 13(1): 113-129.