基于双层机器学习的非对称超级电容器跨表征EIS参数估计

赵一冰; 李艺多; 周瑜欢; 左之慧; 王瀚博; 王岩; 田玉美; 陆海彦; 刘长英

doi:10.19799/j.cnki.2095-4239.2026.0269

您当前的位置：

首页 >

文章列表页 >

基于双层机器学习的非对称超级电容器跨表征EIS参数估计

超级电容器关键材料与器件专刊 | 更新时间：2026-05-28

- 基于双层机器学习的非对称超级电容器跨表征EIS参数估计
- Estimation of cross-characterized EIS parameters of asymmetric supercapacitors based on double-layer machine learning
- 储能科学与技术 2026年15卷第5期页码：1694-1703
- 作者机构：
  
  1.吉林大学化学学院，吉林长春 130012
  2.吉林大学仪器科学与电气工程学院，吉林长春 130012
- 作者简介：
  
  赵一冰（2002—），男，硕士研究生，研究方向为锂离子电池建模与数据驱动寿命预测，E-mail：ybzhao24@mails.jlu.edu.cn；
  陆海彦，教授，研究方向为电化学储能技术、环境电化学及电化学工程，E-mail：luhy@jlu.edu.cn
  刘长英，教授，研究方向为车辆测控技术、视觉检测技术，E-mail：liuchangy@jlu.edu.cn。
- 基金信息：
  
  吉林省自然科学基金面上项目(20250102066JC);天津市飞机维修与民航地面特种设备技术工程中心资助项目(CAUCGCZX-202501)
- DOI：10.19799/j.cnki.2095-4239.2026.0269
  中图分类号： TM 53
- 收稿：2026-03-31，
  
  修回：2026-04-14，
  
  纸质出版：2026-05-28
- 稿件说明：
移动端阅览
赵一冰, 李艺多, 周瑜欢, 等. 基于双层机器学习的非对称超级电容器跨表征EIS参数估计[J]. 储能科学与技术, 2026, 15(5): 1694-1703.

ZHAO Yibing, LI Yiduo, ZHOU Yuhuan, et al. Estimation of cross-characterized EIS parameters of asymmetric supercapacitors based on double-layer machine learning[J]. Energy Storage Science and Technology, 2026, 15(5): 1694-1703.
赵一冰, 李艺多, 周瑜欢, 等. 基于双层机器学习的非对称超级电容器跨表征EIS参数估计[J]. 储能科学与技术, 2026, 15(5): 1694-1703. DOI： 10.19799/j.cnki.2095-4239.2026.0269.

ZHAO Yibing, LI Yiduo, ZHOU Yuhuan, et al. Estimation of cross-characterized EIS parameters of asymmetric supercapacitors based on double-layer machine learning[J]. Energy Storage Science and Technology, 2026, 15(5): 1694-1703. DOI： 10.19799/j.cnki.2095-4239.2026.0269.

摘要

电化学阻抗谱（EIS）是表征非对称超级电容器动力学特性的关键技术。然而，在表征高噪声的电极材料时，传统的非线性最小二乘法常因为难以获取准确的阻抗参数初值而导致拟合失准。为解决这一难题，本工作提出了一种基于跨表征融合与双层集成机器学习架构的EIS参数智能辨识方法。该方法深度提取循环伏安与恒流充放电曲线中的物理信息来构建特征矩阵，建立其与EIS关键参数（如内阻、恒相位元件等）之间的可解释映射关系，通过潜变量提取和时序归一化方法对全量特征进行降维和增强，构建XGBoost、随机森林、岭回归、ENR集成的双层机器学习架构进行训练，最终实现高精度的跨表征EIS参数估计。实验结果表明，所提方法的估计结果与直接基于EIS特征的估计结果高度一致，在钴锰基等材料体系中展现出跨材料体系的高度稳定性。本研究不仅为非对称超级电容器的EIS拟合提供可靠的初值估计策略，显著提升了拟合的收敛性与准确度，同时也为高噪声条件下的电化学阻抗参数辨识提供了新思路。

Abstract

Electrochemical impedance spectroscopy (EIS) is a crucial technique for characterizing the dynamic properties of asymmetric supercapacitors. However

for electrode materials with high noise levels

the traditional nonlinear least-squares method often fails to yield accurate fits owing to the difficulty in determining reliable initial impedance parameters. To address this challenge

this study proposes an intelligent EIS parameter identification method based on cross-characterization fusion and a two-layer machine learning architecture. This approach extracts physicochemical information from cyclic voltammetry and constant-current charge-discharge curves to construct a

feature matrix

establishing an interpretable mapping between these features and key EIS parameters (

e.g.

internal resistance and constant phase element parameters). After dimensionality reduction and feature enhancement through latent variable extraction and time-series normalization

a two-layer machine learning architecture integrating XGBoost

random forest

ridge regression

and elastic net regression is developed for training

enabling high-precision cross-characterization-based EIS parameter estimation. Experimental results demonstrate that the predicted parameters closely align with those derived directly from EIS

with high stability across different material systems

including cobalt-manganese-based electrodes. This study provides a reliable strategy for initializing EIS fitting in asymmetric supercapacitors

significantly improving convergence and accuracy

and offers a practical approach for identifying electrochemical impedance parameters under high-noise conditions.

关键词

Keywords

references

DUBAL D P, CHODANKAR N R, KIM D H, et al. Towards flexible solid-state supercapacitors for smart and wearable electronics[J]. Chemical Society Reviews, 2018, 47(6): 2065-2129.

KUMAR N, KIM S B, LEE S Y, et al. Recent advanced supercapacitor: A review of storage mechanisms, electrode materials, modification, and perspectives[J]. Nanomaterials, 2022, 12(20): 3708. DOI: 10.3390/nano12203708.

LUKATSKAYA M R, DUNN B, GOGOTSI Y. Multidimensional materials and device architectures for future hybrid energy storage[J]. Nature Communications, 2016, 7: 12647. DOI: 10.1038/ncomms12647.

WANG Y, WANG H B, XU Y H, et al. Engineering multiscale hollow core-shell nanostructures via in situ surface functionalization for advanced electrochemical energy storage applications[J ] . Inorganic Chemistry Frontiers, 2026, 13(1): 273-285.

WAN S, WANG H B, WANG Y, et al. Interfacial synergistic regulation of MXene-composited nickel-cobalt double hydroxide for high-performance supercapacitors[J]. Inorganic Chemistry Frontiers, 2025, 12(18): 5459-5467.

LAZANAS A C, PRODROMIDIS M I. Electrochemical impedance spectroscopy-A tutorial[J]. ACS Measurement Science Au, 2023, 3(3): 162-193. DOI: 10.1021/acsmeasuresciau.2c00070.

DAS S, BANERJEE A, NANDI U, et al. Critical review on the analysis of electrochemical impedance spectroscopy data[J]. Journal of Applied Physics, 2025, 138(12): 125002. DOI: 10.1063/5.0275205.

ZOU C F, ZHANG L, HU X S, et al. A review of fractional-order techniques applied to lithium-ion batteries, lead-acid batteries, and supercapacitors[J]. Journal of Power Sources, 2018, 390: 286-296. DOI: 10.1016/j.jpowsour.2018.04.033.

邓巧, 丘东元, 顾文超, 等. 超级电容器分数阶模型的分频段参数辨识方法[J]. 储能科学与技术, 2022, 11(10): 3371-3380. DOI: 10.19799/j.cnki.2095-4239.2022.0236.

DENG Q, QIU D Y, GU W C, et al. Parameter-identification method for fractional-order models of supercapacitors based on frequency-band division[J]. Energy Storage Science and Technology, 2022, 11(10): 3371-3380. DOI: 10.19799/j.cnki.2095-4239.2022.0236.

NUNES H, MARTINHO J, FERMEIRO J, et al. Impedance analysis and parameter estimation of lithium-ion batteries using the EIS technique[J]. IEEE Transactions on Industry Applications, 2024, 60(3): 5048-5060. DOI: 10.1109/TIA.2024.3365451.

LIU Y, YANG Z W, ZOU X X, et al. A general framework to govern machine learning oriented materials data quality[J]. Materials Science and Engineering: Reports, 2025, 166: 101050. DOI: 10.1016/j.mser.2025.101050.

LIU Y, YANG Z W, ZOU X X, et al. Data quantity governance for machine learning in materials science[J]. National Science Review, 2023, 10(7): nwad125. DOI: 10.1093/nsr/nwad125.

范亚锋, 易宗琳, 谢莉婧, 等. 基于一阶RC模型的高频超级电容器电容成分分析[J]. 储能科学与技术, 2025, 14(8): 2903-2912.

FAN Y F, YI Z L, XIE L J, et al. Capacitor composition analysis of high-frequency supercapacitors based on first-order RC model[J]. Energy Storage Science and Technology, 2025, 14(8): 2903-2912.

ZHANG Y L, LI X, LI Z H, et al. Evaluation of electrochemical performance of supercapacitors from equivalent circuits through cyclic voltammetry and galvanostatic charge/discharge[J]. Journal of Energy Storage, 2024, 86: 111122. DOI: 10.1016/j.est.2024.111122.

ZENG Z H, MEI B G, SONG G R, et al. Physical interpretation of the electrochemical impedance spectroscopy (EIS) characteristics for diffusion-controlled intercalation and surface-redox charge storage behaviors[J]. Journal of Energy Storage, 2024, 102: 114021. DOI: 10.1016/j.est.2024.114021.

DU X M, REN X L, XU C J, et al. Recent advances on the manganese cobalt oxides as electrode materials for supercapacitor applications: A comprehensive review[J]. Journal of Energy Storage, 2023, 68: 107672. DOI: 10.1016/j.est.2023.107672.

VIJAYA S, SHARMA P, ALJAFARI B, et al. A redox-additive electrolyte for cobalt-manganese-layered double hydroxides-based asymmetric supercapacitor[J]. International Journal of Energy Research, 2022, 46(15): 23871-23878. DOI: 10.1002/er.8684.

LU W T, ZHAO X. From single-atom to bi-atom and ordered multi-atom: Not just a number changing for electrocatalysis[J]. Chemical Research in Chinese Universities, 2025, 41(3): 432-446. DOI: 10.1007/s40242-025-4207-9.

LIU Y, WU L H, YANG Z W, et al. Descriptors divide-and-conquer enables multifaceted and interpretable materials structure-activity relationship analysis[J]. Advanced Functional Materials, 2025, 35(26): 2421621. DOI: 10.1002/adfm.202421621.

LIU Y, WU J M, YANG G, et al. Predicting the onset temperature ( T g ) of Ge x Se 1- x glass transition: A feature selection based two-stage support vector regression method[J ] . Science Bulletin, 2019, 64(16 ): 1195-1203. DOI: 10.1016/j.scib.2019.06.026.

LIU Y, WU J M, AVDEEV M, et al. Multi-layer feature selection incorporating weighted score-based expert knowledge toward modeling materials with targeted properties[J]. Advanced Theory and Simulations, 2020, 3(2): 1900215. DOI:10.1002/adts.201900215.

LIU Y, ZOU X X, MA S C, et al. Feature selection method reducing correlations among features by embedding domain knowledge[J]. Acta Materialia, 2022, 238: 118195. DOI: 10.1016/j.actamat.2022.118195.

施思齐, 涂章伟, 邹欣欣, 等. 数据驱动的机器学习在电化学储能材料研究中的应用[J]. 储能科学与技术, 2022, 11(3): 739-759.

SHI S Q, TU Z W, ZOU X X, et al. Applying data-driven machine learning to studying electrochemical energy storage materials[J]. Energy Storage Science and Technology, 2022, 11(3): 739-759.

LIU Y, GUO B R, ZOU X X, et al. Machine learning assisted materials design and discovery for rechargeable batteries[J]. Energy Storage Materials, 2020, 31: 434-450. DOI: 10.1016/j.ensm.2020.06.033.

SHIN K, CAO G Y, ZHOU X L, et al. Present and future of monovalent all-organic batteries[J]. Chemical Research in Chinese Universities, 2025, 41(3): 414-431. DOI: 10.1007/s40242-025-5036-6.

GATEMAN S M, GHARBI O, GOMES DE MELO H, et al. On the use of a constant phase element (CPE) in electrochemistry[J]. Current Opinion in Electrochemistry, 2022, 36: 101133. DOI: 10.1016/j.coelec.2022.101133.

YUN C, HWANG S. Analysis of the charging current in cyclic voltammetry and supercapacitor's galvanostatic charging profile based on a constant-phase element[J]. ACS Omega, 2021, 6(1): 367-373.

SAWAI K, OHZUKU T. A method of impedance spectroscopy for predicting the dynamic behavior of electrochemical system and its application to a high-area carbon electrode[J]. Journal of the Electrochemical Society, 1997, 144(3): 988-995. DOI: 10. 1149/1. 1837518.

GAROUANI M, BARHRHOUJ A, TESTE O. XStacking: An effective and inherently explainable framework for stacked ensemble learning[J]. Information Fusion, 2025, 124: 103358. DOI: 10.1016/j.inffus.2025.103358.

WANG Q K, LU H F. A novel stacking ensemble learner for predicting residual strength of corroded pipelines[J]. npj Materials Degradation, 2024, 8: 87. DOI: 10.1038/s41529-024-00508-z.

XU Q, WU M, KHOO E, et al. A hybrid ensemble deep learning approach for early prediction of battery remaining useful life[J]. IEEE/CAA Journal of Automatica Sinica, 2023, 10(1): 177-187. DOI: 10.1109/JAS.2023.123024.

CHAMLAL H, BENZMANE A, OUADERHMAN T. Elastic net-based high dimensional data selection for regression[J]. Expert Systems with Applications, 2024, 244: 122958. DOI: 10.1016/j.eswa.2023.122958.

LI H Y, LYU Z W, HAN M F. Robust and fast estimation of equivalent circuit model from noisy electrochemical impedance spectra[J]. Electrochimica Acta, 2022, 422: 140474. DOI: 10.1016/j.electacta.2022.140474.

ZHAO Z Y, ZOU Y, LIU P, et al. EIS equivalent circuit model prediction using interpretable machine learning and parameter identification using global optimization algorithms[J]. Electrochimica Acta, 2022, 418: 140350. DOI:10.1016/j.electacta.2022.140350.

MA L, TIAN J P, ZHANG T L, et al. Accurate and efficient remaining useful life prediction of batteries enabled by physics-informed machine learning[J]. Journal of Energy Chemistry, 2024, 91: 512-521. DOI: 10.1016/j.jechem.2023.12.043.

GAO T H, LU W. Machine learning toward advanced energy storage devices and systems[J]. iScience, 2021, 24(1): 101936. DOI: 10.1016/j.isci.2020.101936.

LIN C P, XU J, JIANG D L, et al. Multi-model ensemble learning for battery state-of-health estimation: Recent advances and perspectives[J]. Journal of Energy Chemistry, 2025, 100: 739-759. DOI: 10.1016/j.jechem.2024.09.021.

SYLVESTRIN G R, MACIEL J N, ANDO O H Jr. Comprehensive feature extraction for battery health prognostics: Identifying predictive indicators of state of health[J]. Journal of Power Sources, 2026, 668: 239389. DOI: 10.1016/j.jpowsour.2026.239389.

AMINU M, AHMAD N A. Complex chemical data classification and discrimination using locality preserving partial least squares discriminant analysis[J]. ACS Omega, 2020, 5(41): 26601-26610.

KAPPATOU C D, ODGERS J, GARCÍA-MUÑOZ S, et al. An optimization approach coupling preprocessing with model regression for enhanced chemometrics[J]. Industrial & Engineering Chemistry Research, 2023, 62(15): 6196-6213.

LIU Y, WU J M, WANG Z C, et al. Predicting creep rupture life of Ni-based single crystal superalloys using divide-and-conquer approach based machine learning[J]. Acta Materialia, 2020, 195: 454-467. DOI: 10.1016/j.actamat.2020.05.001.

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

机器学习强化的电化学阻抗谱技术及其在锂离子电池研究中的应用

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

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

高倍率型MXene基复合薄膜电极的氧化重构制备与界面调控

聚吡咯基齿形叉指全固态超级电容器的设计及性能优化