人工智能赋能超级电容器中多孔碳材料设计：数据、模型与机制协同驱动的研究进展

王江; 易宗琳; 郭杰晨; 张圣斌; 白乃瑞; 范亚锋; 苏方远

doi:10.19799/j.cnki.2095-4239.2026.0300

您当前的位置：

首页 >

文章列表页 >

人工智能赋能超级电容器中多孔碳材料设计：数据、模型与机制协同驱动的研究进展

超级电容器关键材料与器件专刊 | 更新时间：2026-05-28

- 人工智能赋能超级电容器中多孔碳材料设计：数据、模型与机制协同驱动的研究进展
- Artificial intelligence-enabled design of porous carbon materials for supercapacitors: Recent advances driven by data, models, and mechanisms
- 储能科学与技术 2026年15卷第5期页码：1925-1946
- 作者机构：
  
  1.中国科学院山西煤炭化学研究所，炭材料山西省重点实验室，山西太原 030001
  2.中国科学院大学，北京 100049
- 作者简介：
  
  王江（1996—），男，硕士研究生，研究方向为基于大语言模型的储能碳材料文本数据挖掘，E-mail：wangjiang24@mails.ucas.ac.cn；
  易宗琳，助理研究员，研究方向为电化学储能器件技术开发，E-mail：yizonglin@sxicc.ac.cn
  苏方远，研究员，研究方向为电化学储能器件技术开发，E-mail：sufangyuan@sxicc.ac.cn。
- 基金信息：
  
  山西省优秀博士生来晋工作人才项目(SYXBS202529);山西省基础研究青年项目(202503021212407);炭材料山西省重点实验室自主研发课题(SCJC-XCL-202503)
- DOI：10.19799/j.cnki.2095-4239.2026.0300
  中图分类号： TM 53
- 收稿：2026-04-08，
  
  修回：2026-04-23，
  
  录用：2026-04-24，
  
  纸质出版：2026-05-28
- 稿件说明：
移动端阅览
王江, 易宗琳, 郭杰晨, 等. 人工智能赋能超级电容器中多孔碳材料设计:数据、模型与机制协同驱动的研究进展[J]. 储能科学与技术, 2026, 15(5): 1925-1946.

WANG Jiang, YI Zonglin, GUO Jiechen, et al. Artificial intelligence-enabled design of porous carbon materials for supercapacitors: Recent advances driven by data, models, and mechanisms[J]. Energy Storage Science and Technology, 2026, 15(5): 1925-1946.
王江, 易宗琳, 郭杰晨, 等. 人工智能赋能超级电容器中多孔碳材料设计:数据、模型与机制协同驱动的研究进展[J]. 储能科学与技术, 2026, 15(5): 1925-1946. DOI： 10.19799/j.cnki.2095-4239.2026.0300.

WANG Jiang, YI Zonglin, GUO Jiechen, et al. Artificial intelligence-enabled design of porous carbon materials for supercapacitors: Recent advances driven by data, models, and mechanisms[J]. Energy Storage Science and Technology, 2026, 15(5): 1925-1946. DOI： 10.19799/j.cnki.2095-4239.2026.0300.

摘要

超级电容器具有高功率密度、快速充放电、长循环寿命和良好安全性，在电网调频、能量回收和脉冲功率输出等场景中展现出重要应用价值。多孔碳材料凭借资源丰富、导电性较好、结构可调和电化学稳定性高，长期占据超级电容器电极材料研究的重要地位。然而，多孔碳材料存在前驱体复杂多样、制备参数耦合强、孔结构与表面化学协同调控困难、构效关系难以定量描述等问题，传统经验试错方式已难以满足高效设计需求。人工智能与材料信息学的发展为超级电容器研究提供了新的方法学支撑。本文围绕“数据-模型-机制-优化”研究思路，系统综述了人工智能在超级电容器中的研究进展：首先总结了孔结构、表面化学、缺陷和电解液溶剂化等关键因素对储能行为的影响；其次梳理了数据收集、特征工程、模型选择、可解释人工智能及其在性能预测中的应用；进一步归纳了人工智能在碳源筛选、合成参数优化、逆向设计以及多目标器件优化中的代表性成果；在此基础上，讨论了人工智能与机器学习势函数、第一性原理计算、分子动力学等多尺度模拟的融合进展。最后，针对当前领域中数据异构、评价标准不统一、模型泛化能力不足、解释性与机制验证脱节等问题，提出了构建最小信息集、建立分层评价基准、强化人工智能-模拟-表征闭环以及推动自动化实验平台发展的建议。本文旨在为人工智能驱动的多孔碳材料从相关性拟合走向机制牵引设计提供参考。

Abstract

Supercapacitors are an essential class of energy storage devices due to their high power density

fast charge-discharge cycles

long cycle life

and excellent safety performance. Porous carbon materials

owing to their abundant resources

good electrical conductivity

tunable structures

and high electrochemical stability

have long been considered as one of the most promising candidates for supercapacitor electrodes. However

the design of high-performance porous carbon materials for supercapacitors remains a significant challenge due to the complexity of precursor variability

the strong coupling of synthesis parameters

and difficulties in simultaneously optimizing pore structure and surface chemistry. Traditional trial-and-error approaches are no longer efficient enough to meet the demands of rapid and effective material design.This review provides a comprehensive overview of the recent progress in the design of porous carbon materials for supercapacitors

the review follows a "data-model-mechanism-optimization" framework

which emphasizes the synergistic integration of data-driven methods

machine learning models

and mechanistic understanding. The first section discusses the key factors that influence the energy storage performance of supercapacitors

including pore structure

surface chemistry

defects

and electrolyte solvation. It highlights how the specific roles of nitrogen-

oxygen-

and sulfur-doped sites

as well as defects

can be controlled to enhance both electric double-layer capacitance (EDLC) and pseudocapacitance

depending on their chemical states and the interaction with the electrolyte environment.The review then moves on to summarize the data-driven AI workflows that are transforming the design of porous carbon materials. It explores data collection techniques

feature engineering approaches

model selection processes

and the role of interpretable AI. Key applications in performance prediction

precursor screening

and the optimization of synthesis parameters are discussed

including how AI models can predict the optimal pore structures

dopant levels

and synthesis routes for enhanced electrochemical performance. Additionally

the integration of AI with multiscale simulations—such as machine learning-based atomic potentials

density functional theory (DFT)

and molecular dynamics (MD)—is examined

showing how these hybrid approaches provide deeper insights into the mechanisms governing ion transport and charge storage at the atomic scale.Furthermore

the review highlights representative achievements in AI-assisted inverse design and multi-objective optimization of supercapacitor devices. AI-driven methods have significantly advanced the understanding of multi-scale correlations between material properties

device parameters

and operational conditions. The ability to predict performance across different electrolytes and test conditions is a key milestone in advancing the generalizability of AI models.Finally

the review discusses the current challenges faced by the field

including data heterogeneity

inconsistent evaluation metrics

limited model generalization

and the disconnect between machine learning predictions and experimental validation. It proposes strategies to address these challenges

such as constructing minimal information sets

developing hierarchical evaluation benchmarks

strengthening the AI-simulation-characterization feedback loop

and promoting the development of automated experimental platforms.This review aims to guide future research in leveraging AI to transition the design of porous carbon materials for supercapacitors from empirical optimization to mechanism-driven discovery

ultimately leading to more efficient

reliable

and scalable energy storage solutions.

关键词

Keywords

references

PAN X X, LI W K, LAI X T, et al. Electrolyte design strategies for next-generation supercapacitors and metal-ion batteries[J]. Emergent Materials, 2025, 8(8): 6843-6917. DOI:10.1007/s42247-025-01284-5.

MAHMOUDI-QASHQAY S, ZAMANI-MEYMIAN M R, MALEKI A, et al. Fabrication of an asymmetric supercapacitor using a novel electrode design and introduce a robust machine learning model for its performance evaluation[J]. Journal of Power Sources, 2024, 613: 234911. DOI:10.1016/j.jpowsour.2024.234911.

CHOUDHARY N, TOMAR A, BHARDWAJ S, et al. Advancements in biomass-derived cellulose composite electrodes for supercapacitors: A review[J]. Journal of Materials Chemistry A, 2025, 13(6): 4012-4042.

YUKSEL K, EROGLU D, YILDIRIM R. Key aspects of sustainable and high-performance K-ion batteries: A machine learning approach[J]. Journal of Power Sources, 2025, 657: 238215. DOI:10.1016/j.jpowsour.2025.238215.

SUN X T, UNIVERSITY C S, LI R L, et al. Function–structure–synthesis: Machine learning enabled closed-loop design of biomass-derived porous carbon materials[J]. ACS Sustainable Chemistry & Engineering, 2025, 13(21): 7698-7709. DOI:10.1021/acssuschemeng.4c08492.

LIU H W, CUI Z M, QIAO Z N, et al. Machine learning-assisted prediction, screen, and interpretation of porous carbon materials for high-performance supercapacitors[J]. Journal of Materials Informatics, 2024, 4(4): DOI:10.20517/jmi.2024.29.

LI H T, YAN Q C, LI J H, et al. Porous carbon materials: From traditional synthesis, machine learning-assisted design, to their applications in advanced energy storage and conversion[J]. Advanced Functional Materials, 2025, 35(33): 2504272. DOI:10.1002/adfm.202504272.

YI Z L, ZHOU Y, LIU H, et al. Predicting practical reduction potential of electrolyte solvents via computational hydrogen electrode and interpretable machine-learning models[J]. npj Computational Materials, 2025, 11: 135. DOI:10.1038/s41524-025-01582-w.

CHENWITTAYAKHACHON A, JITAPUNKUL K, NAKPALAD B, et al. Machine learning approach to understanding the 'synergistic' pseudocapacitive effects of heteroatom doped graphene[J]. 2D Materials, 2023, 10(2): 025003. DOI:10.1088/2053-1583/acaf8d.

LIU P, GE Y, LI H H, et al. New insights into the performance of biomass carbon-based supercapacitors based on interpretable machine learning approach[J]. Journal of Energy Storage, 2025, 118: 116300. DOI:10.1016/j.est.2025.116300.

HONDA T, MUROGA S, NAKAJIMA H, et al. Virtual experimentations by deep learning on tangible materials[J]. Communications Materials, 2021, 2: 88. DOI:10.1038/s43246-021-00195-2.

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.

RAHIMI M, ABBASPOUR-FARD M H, ROHANI A. A multi-data-driven procedure towards a comprehensive understanding of the activated carbon electrodes performance (using for supercapacitor) employing ANN technique[J]. Renewable Energy, 2021, 180: 980-992. DOI:10.1016/j.renene.2021.08.102.

MISHRA S, SRIVASTAVA R, MUHAMMAD A, et al. The impact of physicochemical features of carbon electrodes on the capacitive performance of supercapacitors: A machine learning approach[J]. Scientific Reports, 2023, 13: 6494. DOI:10.1038/s41598-023-33524-1.

LIU H W, CUI Z M, SUN Y, et al. Synergistic design and synthesis of O, N Co-doped hierarchical porous carbon for enhanced supercapacitor performance[J]. Energy Materials, 2025, 5(3): DOI:10.20517/energymater.2024.101.

ZHOU M S, VASSALLO A, WU J Z. Data-driven approach to understanding the In-operando performance of heteroatom-doped carbon electrodes[J]. ACS Applied Energy Materials, 2020, 3(6): 5993-6000.

GUO J C, CHAI Y F, HONG C C, et al. Prediction of the low-temperature properties of electrolyte solvents for lithium-ion batteriesviamachine learning[J]. Nanoscale, 2026, 18(5): 2613-2624. DOI:10.1039/d5nr03942h.

DONG Y W, LIU Y T, MAO F F, et al. Energy storage in supercapacitor researches: Interdisciplinary applications from molecular simulations to machine learning[J]. Applied Energy, 2025, 393: 126074. DOI:10.1016/j.apenergy.2025.126074.

MCCUSKER L B, LIEBAU F, ENGELHARDT G. Nomenclature of structural and compositional characteristics of ordered microporous and mesoporous materials with inorganic hosts (IUPAC recommendations 2001)[J]. Microporous and Mesoporous Materials, 2003, 58(1): 3-13. DOI:10.1016/S1387-1811(02)00545-0.

CUI Z M, LIU H W, AN X K, et al. Synergistic regulation of carbonyl oxygen active sites and micropores in lignite-derived porous carbon for high-performance supercapacitors[J]. Journal of Electroanalytical Chemistry, 2025, 997: 119488. DOI:10.1016/j.jelechem.2025.119488.

GHOSH S, SIBI A, THOMAS T. Machine learning and explainable artificial intelligence reveal physical insights into biomass-derived carbon for high-performance supercapacitors[J]. Journal of Power Sources, 2026, 665: 239040. DOI:10.1016/j.jpowsour.2025.239040.

TAWFIK W Z, SHABAN M, RAVEENDRAN A, et al. Insights into the specific capacitance of CNT-based supercapacitor electrodes using artificial intelligence[J]. RSC Advances, 2025, 15(5): 3155-3167.

DUBEY R, GURUVIAH V. A data-driven approach for evaluation of electrolyte informatics on electrochemical performance of carbon-based electrode materials[J]. Ionics, 2022, 28(5): 2169-2183. DOI:10.1007/s11581-022-04480-z.

ZHANG Y F, TIAN J, LI G Y, et al. Design principles for gradient porous carbon on aqueous zinc-ion hybrid capacitors: A combined molecular dynamic and machine learning study[J]. ACS Applied Materials & Interfaces, 2025, 17(2): 3448-3456. DOI:10.1021/acsami.4c19397.

SHRIVAS S, DUBEY A. Prediction of specific capacitance of activated carbon electrode for energy storage device by machine learning based approach[J]. Journal of Energy Storage, 2025, 121: 116632. DOI:10.1016/j.est.2025.116632.

OLADIPO A A. N, S co–doped biocarbon for supercapacitor application: Effect of electrolytes concentration and modelling with artificial neural network[J]. Materials Chemistry and Physics, 2021, 260: 124129. DOI:10.1016/j.matchemphys.2020.124129.

ABDI J, PIRHOUSHYARAN T, HADAVIMOGHADDAM F, et al. Modeling of capacitance for carbon-based supercapacitors using Super Learner algorithm[J]. Journal of Energy Storage, 2023, 66: 107376. DOI:10.1016/j.est.2023.107376.

ZHANG Y F, TIAN J, HUANG H, et al. New insights into the role of nitrogen doping in microporous carbon on the capacitive charge storage mechanism: From ab initio to machine learning accelerated molecular dynamics[J]. Carbon, 2024, 229: 119498. DOI:10.1016/j.carbon.2024.119498.

RAJ V, NAIR M R, SOAID N I, et al. Benchmarking classical machine learning and neural networks for supercapacitor electrodes optimization[J]. Diamond and Related Materials, 2026, 161: 113085. DOI:10.1016/j.diamond.2025.113085.

REDDY B S, NARAYANA P L, MAURYA A K, et al. Modeling capacitance of carbon-based supercapacitors by artificial neural networks[J]. Journal of Energy Storage, 2023, 72: 108537. DOI:10.1016/j.est.2023.108537.

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 Z H, GADOW S I, FAYZULLAEV K, et al. Feature engineering enhanced machine learning prediction of pore properties in lignin-derived nanoporous carbon for high-performance supercapacitor applications[J]. ACS Applied Nano Materials, 2025, 8(38): 18392-18400.

CHEN Y Y, WANG H, WANG C L, et al. Machine learning-guided prediction of energy storage performance of carbon cathode materials for zinc-ion hybrid capacitors[J]. Journal of Colloid and Interface Science, 2025, 699: 138139. DOI:10.1016/j.jcis.2025.138139.

DWIVEDI R P, DUBEY R, MAHAPATRA D K, et al. Ensemble approach assisted specific capacitance prediction for heteroatom-doped high-performance supercapacitors[J]. International Journal of Energy Research, 2025, 2025(1): 5975979. DOI:10.1155/er/5975979.

KUSHWAHA R, SINGH M K, KRISHNAN S, et al. Machine learning enabled property prediction of carbon-based electrodes for supercapacitors[J]. Journal of Materials Science, 2023, 58(39): 15448-15458. DOI:10.1007/s10853-023-08981-8.

SAAD A G, EMAD-ELDEEN A, TAWFIK W Z, et al. Data-driven machine learning approach for predicting the capacitance of graphene-based supercapacitor electrodes[J]. Journal of Energy Storage, 2022, 55: 105411. DOI:10.1016/j.est.2022.105411.

AHMED S I, RADHAKRISHNAN S, NAIR B B, et al. Efficient hyperparameter-tuned machine learning approach for estimation of supercapacitor performance attributes[J]. Journal of Physics Communications, 2021, 5(11): 115011. DOI:10.1088/2399-6528/ac3574.

TAWFIK W Z, MOHAMMAD S N, RAHOUMA K H, et al. Machine learning models for capacitance prediction of porous carbon-based supercapacitor electrodes[J]. Physica Scripta, 2024, 99(2): 026001. DOI:10.1088/1402-4896/ad190c.

SUN Y X, SUN P H, JIA J X, et al. Machine learning in clarifying complex relationships: Biochar preparation procedures and capacitance characteristics[J]. Chemical Engineering Journal, 2024, 485: 149975. DOI:10.1016/j.cej.2024.149975.

KANNAN V, SOMASUNDARAM K, FISHER A, et al. Monte Carlo-based sensitivity analysis of an electrochemical capacitor[J]. International Journal of Energy Research, 2021, 45(11): 16947-16962. DOI:10.1002/er.6919.

PAN R T, GU M Y, WU J Z. Data-driven optimization of carbon electrodes for aqueous supercapacitors[J]. Journal of Chemical & Engineering Data, 2024, 69(12): 4320-4334.

RACCUGLIA P, ELBERT K C, ADLER P D F, et al. Machine-learning-assisted materials discovery using failed experiments[J]. Nature, 2016, 533(7601): 73-76. DOI:10.1038/nature17439.

YUAN X Z, SUVARNA M, LIM J Y, et al. Active learning-based guided synthesis of engineered biochar for CO 2 capture[J ] . Environmental Science & Technology, 2024, 58(15): 6628-6636. DOI:10.1021/acs.est.3c10922.

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.

HUSSAIN I, AL MAHMUD A, AMNA R, et al. Interface and surface engineering: The nexus of MXenes, MOFs, and AI in hybrid material design for energy storage/conversion[J]. Materials Today, 2025, 89: 344-373. DOI:10.1016/j.mattod.2025.07.026.

IRFAN M, SHAHI A, BARI M A, et al. Emerging composite electrode architectures based on transition metal oxides for high-performance Li-ion capacitors[J]. RSC Advances, 2026, 16(6): 4801-4840.

LI D P, LIANG A J, ZHOU M W, et al. Energy utilization of agricultural waste: Machine learning prediction and pyrolysis transformation[J]. Waste Management, 2024, 175: 235-244. DOI:10.1016/j.wasman.2024.01.003.

KATI N, UÇAR F. Investigation of prediction approaches for the design and performance analysis of supercapacitors with biomass-based activated carbon electrodes[J]. Journal of Energy Storage, 2025, 133: 118029. DOI:10.1016/j.est.2025.118029.

JAYABAL R. Waste derived graphene metal oxide composites for advanced supercapacitors: A review on modern energy storage[J]. Journal of Energy Storage, 2025, 136: 118031. DOI:10.1016/j.est.2025.118031.

LIU X R, YANG H P, XUE P X, et al. Machine learning modeling of the capacitive performance of N-doped porous biochar electrodes with experimental verification[J]. Renewable Energy, 2024, 231: 120969. DOI:10.1016/j.renene.2024.120969.

ZHAO X L, WANG X Q, GAO P, et al. Eco-friendly synthesis coupled with predictive analytics: Developing hierarchical lignin-derived ordered mesoporous carbon for advanced supercapacitors[J]. Green Energy & Environment, 2025, 10(6): 1256-1269. DOI:10.1016/j.gee.2024.11.006.

SUN Z X, WANG R. Emerging nanomaterials for energy storage: A critical review of metrics, hotspots, and future directions[J]. Renewable and Sustainable Energy Reviews, 2025, 224: 116093. DOI:10.1016/j.rser.2025.116093.

RAHIMI M, SALAUDEEN S A. Synthesis-feature-coupled machine learning approaches to predict the capacitance of biomass-derived carbon electrodes in supercapacitors[J]. Materials Chemistry and Physics, 2026, 348: 131525. DOI:10.1016/j.matchemphys.2025.131525.

QU L B, WANG P Y, MOTEVALLI B, et al. New engineering science insights into the electrode materials pairing of electrochemical energy storage devices[J]. Advanced Materials, 2024, 36(35): 2404232. DOI:10.1002/adma.202404232.

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.

LIU M X, TANG Q, LENG E W, et al. Multi-staged machine learning-driven investigation of biomass-derived hard carbon anodes for sodium-ion batteries: Connecting precursor, structure, and performance[J]. Chemical Engineering Journal, 2026, 528: 172350. DOI:10.1016/j.cej.2025.172350.

LIU Y Y, ZHANG H, CAO R, et al. Interpretable machine learning for optimizing the specific capacitance of biomass-derived supercapacitors[J]. Fuel, 2026, 417: 138681. DOI:10.1016/j.fuel.2026.138681.

YANG X P, YUAN C, HE S R, et al. Machine learning prediction of specific capacitance in biomass derived carbon materials: Effects of activation and biochar characteristics[J]. Fuel, 2023, 331: 125718. DOI:10.1016/j.fuel.2022.125718.

SOLANGI N H, NEIBER R R, SHARMA B P, et al. Tuning charge storage in bimetallic CoV-LDH for high-performance supercapacitor: A synergistic experimental and machine learning approach[J]. Small, 2026, 22(17): e07764. DOI:10.1002/smll.202507764.

WICKRAMAARACHCHI K, MINAKSHI M, ASSA ARAVINDH S, et al. Repurposing N-doped grape Marc for the fabrication of supercapacitors with theoretical and machine learning models[J]. Nanomaterials, 2022, 12(11): DOI:10.3390/nano12111847.

KOMARSOFLA M K, KHOSRAVINIA K, KIANI A. Integrated machine learning framework combining electrical cycling and material features for supercapacitor health forecasting[J]. Batteries, 2025, 11(7): DOI:10.3390/batteries11070264.

GHOSH S, SIBI A, PRIYANGA G S, et al. Temperature-dependent performance prediction for cerium oxynitride solid-state symmetric supercapacitor using machine learning[J]. Journal of Energy Storage, 2025, 113: 115562. DOI:10.1016/j.est.2025.115562.

MIYATA H, MANABE K, SUGAHARA Y, et al. Machine-learning-guided multiscale design of nitrogen-doped carbon for enhanced supercapacitor performance[J]. ACS Applied Materials & Interfaces, 2025, 17(36): 50967-50976.

YUAN F, ZHOU J, YAMAUCHI Y, et al. Supercapacitor dynamics: Mechanisms, architectures, and advanced in-situ characterizations for next-generation energy storage[J]. Coordination Chemistry Reviews, 2026, 549: 217268. DOI:10.1016/j.ccr.2025.217268.

ZHU S, LI J J, MA L Y, et al. Artificial neural network enabled capacitance prediction for carbon-based supercapacitors[J]. Materials Letters, 2018, 233: 294-297. DOI:10.1016/j.matlet.2018.09.028.

REHMAN H U, KHAN H, ABBASI Z, et al. DLS-based optimization of ZnS-CoS nanoparticles with enhanced energy and power density for supercapacitor applications and its validation by AI models[J]. Materials Advances, 2025, 6(21): 7847-7865.

SIAL Q A, SAFDER U, IQBAL S, et al. Advancement in supercapacitors for IoT applications by using machine learning: Current trends and future technology[J]. Sustainability, 2024, 16(4): DOI:10.3390/su16041516.

GU R, WEI L, XU N, et al. Machine learning enhanced self-charging power sources[J]. Advanced Functional Materials, 2025, 35(40): 2505719. DOI:10.1002/adfm.202505719.

DOUCET T, MOGNIOTTE J F, AMIOT R, et al. Multiphysics measurement method for supercapacitors state of health determination[J]. Micromachines, 2025, 16(11): DOI:10.3390/mi16111295.

ZHU S, LI J, MA L, et al. Machine learning enabled capacitance prediction for carbon-based supercapacitors [J]. Materials Letters, 2018, 233: 294-297. https://doi.org/10.1016/j.matlet.2018.09.028.

LI Q, ZHENG H, LI C P, et al. Boosting supercapacitor efficiency with δ-MnO 2 nanoflakes on electrochemically exfoliated graphene nanosheets[J ] . Chinese Journal of Chemical Engineering, 2026, 89: 249-258. DOI:10.1016/j.cjche.2025.08.022.

AHMAD S, ALI KHAN M, EID G, et al. Machine learning-assisted synthesis of N-S functionalized NiO/CoO nanocomposite for enhanced supercapacitor performance[J]. Electrochimica Acta, 2026, 546: 147782. DOI:10.1016/j.electacta.2025.147782.

RAMACHANDRAN T, ZHENG L X, BUTT H, et al. Energy nexus: MXene-MOF-chalcogenide hybrids triboelectric nanogenerators (TENGs) for self-powered supercapacitor storage with machine learning insights[J]. Materials Today Advances, 2026, 29: 100675. DOI:10.1016/j.mtadv.2025.100675.

SABET M. Machine learning-optimized hybrid graphene/polymer electrodes for high-performance and scalable supercapacitors[J]. Journal of Materials Science, 2025, 60(38): 17738-17756. DOI:10.1007/s10853-025-11468-3.

MOMBESHORA E T, MUCHUWENI E, HASHEMI H. Applications of graphene derivatives in all-solid-state supercapacitors[J]. ChemistrySelect, 2024, 9(44): e202404345. DOI:10.1002/slct.202404345.

DESHSORN K, CHAVALEKVIRAT P, DEEPAISARN S, et al. Historical data mining deep dive into machine learning-aided 2D materials research in electrochemical applications[J]. ACS Materials Au, 2026, 6(1): 28-56.

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.

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

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

超级电容器自放电的研究进展

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

锂离子电容器预锂化技术：现状、局限与展望

多孔碳超级电容器储能机理研究进展