人工智能赋能的超级电容器材料研发与器件管理——方法演进与前沿进展

赵衍博; 刘盼; 张雯; 张庆印; 张鹏; 时志强

doi:10.19799/j.cnki.2095-4239.2026.0243

您当前的位置：

首页 >

文章列表页 >

人工智能赋能的超级电容器材料研发与器件管理——方法演进与前沿进展

超级电容器关键材料与器件专刊 | 更新时间：2026-07-01

- 人工智能赋能的超级电容器材料研发与器件管理——方法演进与前沿进展
- AI-Empowered supercapacitor materials development and device management: Methodological evolution and frontier advances
- 储能科学与技术 2026年15卷第5期页码：1716-1731
- 作者机构：
  
  1.天津工业大学电子与信息工程学院，天津 300387
  2.容创未来（沧州）新能源有限公司，河北沧州 061000
  3.天津市先进纤维与储能技术重点实验室，天津 300387
  4.天津工业大学材料科学与工程学院，天津 300387
- 作者简介：
  
  赵衍博（1999—），男，博士研究生，从事人工智能与储能工程，E-mail：x6@outlook.lv；
  时志强，教授，研究电化学储能材料与器件，E-mail： shizhiqiang@tiangong.edu.cn。
- 基金信息：
  
  国家自然科学基金(22179094);河北省博士创新工作站(195)
- DOI：10.19799/j.cnki.2095-4239.2026.0243
  中图分类号： TM 53
- 收稿：2026-03-26，
  
  修回：2026-04-26，
  
  纸质出版：2026-05-28
- 稿件说明：
移动端阅览
赵衍博, 刘盼, 张雯, 等. 人工智能赋能的超级电容器材料研发与器件管理[J]. 储能科学与技术, 2026, 15(5): 1716-1731.

ZHAO Yanbo, LIU Pan, ZHANG Wen, et al. AI-Empowered supercapacitor materials development and device management: methodological evolution and frontier advances[J]. Energy Storage Science and Technology, 2026, 15(5): 1716-1731.
赵衍博, 刘盼, 张雯, 等. 人工智能赋能的超级电容器材料研发与器件管理[J]. 储能科学与技术, 2026, 15(5): 1716-1731. DOI： 10.19799/j.cnki.2095-4239.2026.0243.

ZHAO Yanbo, LIU Pan, ZHANG Wen, et al. AI-Empowered supercapacitor materials development and device management: methodological evolution and frontier advances[J]. Energy Storage Science and Technology, 2026, 15(5): 1716-1731. DOI： 10.19799/j.cnki.2095-4239.2026.0243.

摘要

超级电容器凭借其高功率密度、充放电速度快以及长循环寿命等显著优势，已成为现代储能技术的重要组成部分。然而其相对偏低的能量密度制约了其在新能源汽车与智能电网等长续航需求领域的进一步应用拓展。近年来，人工智能技术的快速发展为突破这一性能瓶颈提供了全新的研究路径。本文遵循“材料研发-器件管理”双阶段框架，系统综述了人工智能在超级电容器全生命周期中的研究进展。在材料研发阶段，回顾了开放式计算材料数据库及面向超级电容器的专用电化学数据库的发展现状，介绍了描述符的特征工程演进路径。重点综述了深度学习预测模型的技术演进，包括早期图神经网络、通用神经网络及大规模基础模型，阐述了从人工特征工程向端到端表示学习的范式转变及其对高通量虚拟筛选效率的显著提升。介绍了贝叶斯优化与主动学习驱动的合成工艺优化策略及“预测-合成-验证-反馈”闭环范式，阐述了基于扩散模型与自回归模型的生成式逆向设计方法，分析了其根据目标性能约束直接生成候选材料结构的应用潜力。在器件运维阶段，以锂电池领域的成熟方法论为参照，系统综述了健康状态评估与剩余使用寿命预测的技术演进，涵盖物理模型、传统机器学习、深度学习、状态空间模型、生成式预训练及物理信息神经网络，介绍了迁移学习与联邦学习在数据稀缺与隐私保护场景中的应用。展望未来，构建遵循原则的统一超级电容器数据库、发展适配孔网络拓扑特征的全局描述符、实现自主实验平台与闭环反馈系统的深度整合，将是推动人工智能从辅助分析工具向全链条核心研究基础设施转变的关键路径。

Abstract

Supercapacitors (SCs) play a crucial role in modern energy storage technologies

offering advantages

including high power density

fast charge/discharge rates

and a long cycle life. However

their relatively low energy density limits applications in fields requiring prolonged endurance

such as new energy vehicles and smart grids. Recently

the rapid development of artificial intelligence (AI) has opened new avenues for overcoming this performance limitation. Based on a dual-stage framework of "materials development-device management

" this review systematically surveys recent AI advancements across the full lifecycle of SCs. In the materials development phase

we assess the current landscape of open computational materials databases and specialized electrochemical databases for supercapacitors. We also discuss the evolutionary trajectory of feature engineering for descriptors. The evolution of deep learning prediction models is comprehensively surveyed

highlighting early graph neural networks

universal neural networks

and large-scale foundation models. We examine the paradigm shift from manual feature engineering to end-to-end representation learning and its significant enhancement of high-throughput virtual screening efficiency. We also introduce Bayesian optimization and active learning-driven synthesis optimization strategies

as well as the closed-loop paradigm of "prediction-synthesis-validation-feedback." In addition

we describe generative inverse design methods based on diffusion models and autoregressive models

analyzing their potential for the direct generation of candidate material structures under target property constraints. In the device operational stage

we draw insights from established methodologies in the lithium-ion battery field to systematically survey the evolution of state-of-health assessment and remaining useful life prediction. This encompasses physics-based models

traditional machine learning

deep learning

state-space models

generative pre-training

and physics-informed neural networks

as well as applications of transfer learning and federated learning in data-scarce and privacy-sensitive contexts. Looking ahead

we identify several key pathways for advancing AI from a supplementary analytical tool to a central research infrastructure across the entire value chain. These include constructing unified supercapacitor databases based on established principles

developing global descriptors tailored to pore network topology

and achieving deep integration of autonomous experimental platforms with closed-loop feedback systems.

关键词

Keywords

references

LIU Y Y, SHEARING P R, HE G J, et al. Supercapacitors: History, theory, emerging technologies, and applications[M]//Advances in Sustainable Energy. Cham: Springer International Publishing, 2021: 417-449. DOI:10.1007/978-3-030-74406-9_15.

AUGUSTYN V, SIMON P, DUNN B. Pseudocapacitive oxide materials for high-rate electrochemical energy storage[J]. Energy & Environmental Science, 2014, 7(5): 1597-1614.

VAHIDMOHAMMADI A, ROSEN J, GOGOTSI Y. The world of two-dimensional carbides and nitrides (MXenes)[J]. Science, 2021, 372(6547): eabf1581. DOI:10.1126/science.abf1581.

LI C, YUE Q Y, GAO Y, et al. Toward rational design of carbon-based electrodes for high-performance supercapacitors[J]. ACS Applied Materials & Interfaces, 2025, 17(17): 24675-24700.

KRESS T, LIU X Y, FORSE A C. Pore network tortuosity controls fast charging in supercapacitors[J]. Nature Materials, 2026, 25(3): 440-446. DOI:10.1038/s41563-025-02404-6.

NOH J, DOAN H A, JOB H, et al. An integrated high-throughput robotic platform and active learning approach for accelerated discovery of optimal electrolyte formulations[J]. Nature Communications, 2024, 15: 2757. DOI:10.1038/s41467-024-47070-5.

ZHAO C X, LU X Y, TU H Y, et al. Research on specific capacitance prediction of biomass carbon-based supercapacitors based on machine learning[J]. Journal of Energy Storage, 2024, 97: 112974. DOI:10.1016/j.est.2024.112974.

SAWANT V, DESHMUKH R, AWATI C. Machine learning techniques for prediction of capacitance and remaining useful life of supercapacitors: A comprehensive review[J]. Journal of Energy Chemistry, 2023, 77: 438-451. DOI:10.1016/j.jechem.2022.11.012.

WANG Z X, WU T Z, ZENG L, et al. Machine learning relationships between nanoporous structures and electrochemical performance in MOF supercapacitors[J]. Advanced Materials, 2025, 37(15): 2500943. DOI:10.1002/adma.202500943.

JAIN A, ONG S P, HAUTIER G, et al. Commentary: The Materials Project: A materials genome approach to accelerating materials innovation[J]. APL Materials, 2013, 1: 011002. DOI:10.1063/1.4812323.

CURTAROLO S, SETYAWAN W, HART G L W, et al. AFLOW: An automatic framework for high-throughput materials discovery[J]. Computational Materials Science, 2012, 58: 218-226. DOI:10.1016/j.commatsci.2012.02.005.

SAAL J E, KIRKLIN S, AYKOL M, et al. Materials design and discovery with high-throughput density functional theory: The open quantum materials database (OQMD)[J]. JOM, 2013, 65(11): 1501-1509. DOI:10.1007/s11837-013-0755-4.

CHOUDHARY K, GARRITY K F, REID A C E, et al. The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design[J]. npj Computational Materials, 2020, 6: 173. DOI:10.1038/s41524-020-00440-1.

JAIN A, HAUTIER G, ONG S P, et al. Formation enthalpies by mixing GGA and GGA+U calculations[J]. Physical Review B, 2011, 84(4): 045115. DOI:10.1103/physrevb.84.045115.

WILKINSON M D, DUMONTIER M, AALBERSBERG I J, et al. The FAIR Guiding Principles for scientific data management and stewardship[J]. Scientific Data, 2016, 3: 160018. DOI:10.1038/sdata.2016.18.

ANDERSEN C W, ARMIENTO R, BLOKHIN E, et al. OPTIMADE, an API for exchanging materials data[J]. Scientific Data, 2021, 8: 217. DOI:10.1038/s41597-021-00974-z.

ROSEN A S, IYER S M, RAY D, et al. Machine learning the quantum-chemical properties of metal-organic frameworks for accelerated materials discovery[J]. Matter, 2021, 4(5): 1578-1597. DOI:10.1016/j.matt.2021.02.015.

MERLET C, PÉAN C, ROTENBERG B, et al. Simulating supercapacitors: Can we model electrodes as constant charge surfaces?[J]. The Journal of Physical Chemistry Letters, 2013, 4(2): 264-268.

WARD L, DUNN A, FAGHANINIA A, et al. Matminer: An open source toolkit for materials data mining[J]. Computational Materials Science, 2018, 152: 60-69. DOI:10.1016/j.commatsci. 2018.05.018.

BARTÓK A P, KONDOR R, CSÁNYI G. On representing chemical environments[J]. Physical Review B, 2013, 87(18): 184115. DOI:10.1103/physrevb.87.184115.

TAWFIK W Z, MOHAMMAD S N, RAHOUMA K H, et al. An artificial neural network model for capacitance prediction of porous carbon-based supercapacitor electrodes[J]. Journal of Energy Storage, 2023, 73: 108830. DOI:10.1016/j.est.2023.108830.

XIE T, GROSSMAN J C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties[J]. Physical Review Letters, 2018, 120(14): 145301. DOI:10.1103/physrevlett.120.145301.

GAO Y C, CHEN X, YUAN Y H, et al. Accelerating battery innovation: AI-powered molecular discovery[J]. Chemical Society Reviews, 2025, 54(21): 9630-9684.

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. DOI:10.1021/jacs.3c08346.

HUANG H, HU Y T, HOU Y J, et al. Delocalized electrolyte design enables 600 Wh kg -1 lithium metal pouch cells[J ] . Nature, 2025, 644(8077): 660-667. DOI:10.1038/s41586-025-09382-4.

CHEN C, YE W K, ZUO Y X, et al. Graph networks as a universal machine learning framework for molecules and crystals[J]. Chemistry of Materials, 2019, 31(9): 3564-3572. DOI:10.1021/acs.chemmater.9b01294.

CHEN C, ONG S P. A universal graph deep learning interatomic potential for the periodic table[J]. Nature Computational Science, 2022, 2(11): 718-728. DOI:10.1038/s43588-022-00349-3.

DENG B W, ZHONG P C, JUN K, et al. CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling[J]. Nature Machine Intelligence, 2023, 5(9): 1031-1041. DOI:10.1038/s42256-023-00716-3.

BATZNER S, MUSAELIAN A, SUN L X, et al. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials[J]. Nature Communications, 2022, 13: 2453. DOI:10.1038/s41467-022-29939-5.

BATATIA I, CSANYI G, KOVACS D P, et al. MACE: Higher order equivariant message passing neural networks for fast and accurate force fields[C]//Advances in Neural Information Processing Systems 35. November 28-December 9, 2022. New Orleans, Louisiana, USA. Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2022: 11423-11436.. DOI:10.52202/068431-0830.

LIAO Y L, WOOD B, DAS A, et al. EquiformerV2: Improved equivariant transformer for scaling to higher-degree representations[EB/OL]. 2023: arXiv: 2306.12059. https://arxiv.org/abs/2306.12059

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.

YANG H, HU C X, ZHOU Y C, et al. MatterSim: A deep learning atomistic model across elements, temperatures and pressures[EB/OL]. 2024: arXiv: 2405.04967. https://arxiv.org/abs/2405.04967

SZYMANSKI N J, BARTEL C J. Computationally guided synthesis of battery materials[J]. ACS Energy Letters, 2024, 9(6): 2902-2911. DOI:10.1021/acsenergylett.4c00821.

GUPTA V, CHOUDHARY K, DECOST B, et al. Structure-aware graph neural network based deep transfer learning framework for enhanced predictive analytics on diverse materials datasets[J]. NPJ Computational Materials, 2024, 10: 1. DOI:10.1038/s41524-023-01185-3.

SZYMANSKI N J, RENDY B, FEI Y X, et al. An autonomous laboratory for the accelerated synthesis of inorganic materials[J]. Nature, 2023, 624(7990): 86-91. DOI:10.1038/s41586-023-06 734-w.

WANG T, PAN R T, MARTINS M L, et al. Machine-learning-assisted material discovery of oxygen-rich highly porous carbon active materials for aqueous supercapacitors[J]. Nature Communications, 2023, 14: 4607. DOI:10.1038/s41467-023-40282-1.

CHEN S, WU G B, JIANG H B, et al. External Li supply reshapes Li deficiency and lifetime limit of batteries[J]. Nature, 2025, 638(8051): 676-683. DOI:10.1038/s41586-024-08465-y.

ZHENG Z L, CHEN S, WU G B, et al. Boron-centered organic salts enabling Na-ion supply and interfacial protection for Na-ion batteries[J]. Angewandte Chemie International Edition, 2025, 64(48): e202517997. DOI:10.1002/anie.202517997.

KANG Z Y, WANG S F, WU G B, et al. Nitrogen-centered organic salts enable stable lithium-ion supply for high-energy-density batteries[J]. Journal of the American Chemical Society, 2025, 147(34): 30591-30598. DOI:10.1021/jacs.5c09300.

MANOHARAN A, CHONG J J, CHOONG Z J, et al. Optimizing lithium-ion battery manufacturing with digitalization and AI-driven frameworks[J]. The International Journal of Advanced Manufacturing Technology, 2026, 142(1): 1-37. DOI:10.1007/s00170-025-17129-8.

LU X Y, ZHAO C X, TU H Y, et al. Research on prediction of energy density and power density of biomass carbon-based supercapacitors based on machine learning[J]. Sustainable Materials and Technologies, 2025, 44: e01309. DOI:10.1016/j.susmat.2025.e01309.

SINGH S, OBERLE M, SCHEL D, et al. Digital twin in the battery industry[M]//Digital Twins, Simulation, and the Metaverse. Cham: Springer Nature Switzerland, 2024: 363-393. DOI:10.1007/978-3-031-69107-2_15.

ZENI C, PINSLER R, ZÜGNER D, et al. A generative model for inorganic materials design[J]. Nature, 2025, 639(8055): 624-632. DOI:10.1038/s41586-025-08628-5.

CAO Z D, LUO X S, LV J, et al. Space group informed transformer for crystalline materials generation[J]. Science Bulletin, 2025, 70(21): 3522-3533. DOI:10.1016/j.scib.2025.09.035.

ANTUNES L M, BUTLER K T, GRAU-CRESPO R. Crystal structure generation with autoregressive large language modeling[J]. Nature Communications, 2024, 15: 10570. DOI:10.1038/s41467-024-54639-7.

YANG S, CHO K, MERCHANT A, et al. Scalable diffusion for materials generation[C/OL]//The Twelfth International Conference on Learning Representations, ICLR 2024. Vienna, Austria: OpenReview, 2024.

VETTER J, NOVÁK P, WAGNER M R, et al. Ageing mechanisms in lithium-ion batteries[J]. Journal of Power Sources, 2005, 147(1/2): 269-281. DOI:10.1016/j.jpowsour.2005.01.006.

REN J H, LIN X R, LIU J Y, et al. Engineering early prediction of supercapacitors' cycle life using neural networks[J]. Materials Today Energy, 2020, 18: 100537. DOI:10.1016/j.mtener.2020. 100537.

BARRÉ A, DEGUILHEM B, GROLLEAU S, et al. A review on lithium-ion battery ageing mechanisms and estimations for automotive applications[J]. Journal of Power Sources, 2013, 241: 680-689. DOI:10.1016/j.jpowsour.2013.05.040.

PLETT G L. Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs Part 1. Background[J]. Journal of Power Sources, 2004, 134(2): 252-261. DOI:10.1016/j.jpowsour.2004.02.031.

UNO M, TANAKA K. Accelerated charge-discharge cycling test and cycle life prediction model for supercapacitors in alternative battery applications[J]. IEEE Transactions on Industrial Electronics, 2012, 59(12): 4704-4712. DOI:10.1109/TIE. 2011. 2182018.

EL MEJDOUBI A, CHAOUI H, SABOR J, et al. Remaining useful life prognosis of supercapacitors under temperature and voltage aging conditions[J]. IEEE Transactions on Industrial Electronics, 2018, 65(5): 4357-4367. DOI:10.1109/TIE.2017.2767550.

KÖTZ R, RUCH P W, CERICOLA D. Aging and failure mode of electrochemical double layer capacitors during accelerated constant load tests[J]. Journal of Power Sources, 2010, 195(3): 923-928. DOI:10.1016/j.jpowsour.2009.08.045.

GILLANI S W, SHAHID K, GULZAR M M, et al. Remaining useful life prediction of super-capacitors in electric vehicles using neural networks[J]. Arabian Journal for Science and Engineering, 2024, 49(5): 7327-7340. DOI:10.1007/s13369-024-08766-4.

QI G H, MA N, WANG K. Predicting the remaining useful life of supercapacitors under different operating conditions[J]. Energies, 2024, 17(11): DOI:10.3390/en17112585.

ANANTHA P N K, PRATIHASTA A K, TANWAR N, et al. Interpretable hybrid CDTCN-GRU model for supercapacitor life prediction[J]. IEEE Sensors Journal, 2025, 25(14): 26970-26978. DOI:10.1109/JSEN.2025.3573331.

SINGH A, SINGH S, KAMBOJ R K, et al. Explainable OptiCNN-SLSTM hybrid model for enhanced lithium-ion battery state of health prediction[J]. Scientific Reports, 2025, 15: 44364. DOI:10.1038/s41598-025-28091-6.

MOHANTY P K, JENA P, PRASAD PADHY N. Federated learning with a temporal-degradation-aware transformer for robust joint SOC and SOH estimation in electric vehicle batteries[J]. IEEE Transactions on Transportation Electrification, 2026, 12(2): 3663-3678. DOI:10.1109/TTE.2025.3646926.

FAN Q Y, HE G X, RUAN D W, et al. Multi-expert fusion for state-of-health estimation of lithium-ion batteries[J]. Scientific Reports, 2025, 15: 42058. DOI:10.1038/s41598-025-26163-1.

ZHANG H, LI Y Q, ZHENG S, et al. Battery lifetime prediction across diverse ageing conditions with inter-cell deep learning[J]. Nature Machine Intelligence, 2025, 7(2): 270-277. DOI:10.1038/s42256-024-00972-x.

OLALDE-VERANO J I, KIRCH S, PÉREZ-MOLINA C, et al. SambaMixer: State of health prediction of Li-ion batteries using mamba state space models[J]. IEEE Access, 2025, 13: 2313-2327. DOI:10.1109/ACCESS.2024.3524321.

WANG F Y, BAO M H, RU Q. An enhanced prognostication of lithium-ion batteries degradation trajectory and remaining useful life based on Mamba-MoE model[J]. Ionics, 2025, 31(10): 10615-10630. DOI:10.1007/s11581-025-06607-4.

HU J C, FU P Y, WEI Z B, et al. Early prediction of lithium-ion battery degradation with a generative pre-trained transformer[J]. Nature Communications, 2026, 17: 126. DOI:10.1038/s41467-025-66819-0.

SALEM N M, MOHAMED A. Physics-informed hybrid reinforcement learning for estimating lithium-ion battery state of health[J]. Scientific Reports, 2025, 15: 43819. DOI:10.1038/s41598-025-30602-4.

QAADAN S, ALSHARE A, ALAZRAI R, et al. Causal physics-infused hybrid learning (CPIHL) framework for next-gen battery health forecasting[J]. IEEE Access, 2025, 13: 61728-61739. DOI:10.1109/ACCESS.2025.3556314.

CHE Y H, ZHENG Y S, RHYU J, et al. Mechanistically guided residual learning for battery state monitoring throughout life[J]. Nature Communications, 2026, 17: 855. DOI:10.1038/s41467-025-67565-z.

CAO R, ZHANG Z J, SHI R W, et al. Model-constrained deep learning for online fault diagnosis in Li-ion batteries over stochastic conditions[J]. Nature Communications, 2025, 16: 1651. DOI:10.1038/s41467-025-56832-8.

LIU H A, LI C, HU X S, et al. Multi-modal framework for battery state of health evaluation using open-source electric vehicle data[J]. Nature Communications, 2025, 16: 1137. DOI:10.1038/s41467-025-56485-7.

LIU Y P, AHMED M, FENG J T, et al. A federated transfer learning framework for lithium-ion battery state of health estimation based on fast-charging segments[J]. IEEE Transactions on Transportation Electrification, 2025, 11(6): 12887-12897. DOI:10.1109/TTE.2025.3594553.

ZHU R, PENG W W, YE Z S, et al. Collaborative prognostics of lithium-ion batteries using federated learning with dynamic weighting and attention mechanism[J]. IEEE Transactions on Industrial Electronics, 2025, 72(1): 980-991. DOI:10.1109/TIE.2024.3387115.

WANG M Y, WU Y F, CAO Y C, et al. Real-time artificial intelligence for solid-state lithium metal batteries[J]. Nature Communications, 2025, 16: 11160. DOI:10.1038/s41467-025-66079-y.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

储能科学与工程本科生人才培养实践——以重庆大学为例

分布式水力发电与超级电容器联合调频控制策略

氮化钼电极材料的电子结构调控与电容储能性能研究

数据驱动的直写式3D打印：超级电容器厚电极的微观结构调控与动力学优化

我国压缩空气储能电站适建性分区研究