基于开普勒算法优化卷积神经网络的燃料电池故障诊断技术

施永; 黄宁; 谢缔; 汪亮亮; 姚继刚

doi:10.19912/j.0254-0096.tynxb.2024-1777

PDF(2708 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (3) : 556-563. DOI: 10.19912/j.0254-0096.tynxb.2024-1777

基于开普勒算法优化卷积神经网络的燃料电池故障诊断技术

施永¹, 黄宁¹, 谢缔², 汪亮亮², 姚继刚²

作者信息 +

FUEL CELL FAULT DIAGNOSIS TECHNIQUE BASED ON CONVOLUTIONAL NEURAL NETWORK OPTIMIZED BY KEPLER OPTIMIZATION ALGORITHM

Shi Yong¹, Huang Ning¹, Xie Di², Wang Liangliang², Yao Jigang²

Author information +

文章历史 +

摘要

提出一种基于等效电路和基于开普勒算法优化的卷积神经网络（KOA-CNN）框架的诊断技术,通过使用电化学阻抗谱（EIS）获得质子交换膜燃料电池（PEMFC）阻抗谱信息,并使用等效电路进行参数辨识,使用拟合得到的电路参数作为诊断算法的训练数据,利用卷积神经网络对故障特征进行提取,利用开普勒优化算法收敛速度快、全局搜索能力强、参数少的特点去优化卷积神经网络的超参数,得到一个最佳的卷积神经网络参数,可显著提高燃料电池故障诊断的精度。经验证,该方法在水淹、膜干、氧气饥饿的故障诊断中准确率达到99.75%。

Abstract

Fault diagnosis techniques play a crucial role in the normal operation of proton exchange membrane fuel cells. In this paper, we propose a diagnostic technique based on equivalent circuit and KOA-CNN framework, which obtains the PEMFC impedance spectrum information by using electrochemical impedance spectroscopy （EIS） and uses the equivalent circuit for parameter identification, and uses the fitted circuit parameters as the training data for the diagnostic algorithm, and extracts the fault features by using a convolutional neural network, which can significantly improve the accuracy of PEMFC fault diagnosis. The Kepler optimization algorithm convergence speed, strong global search ability, and few parameters to optimize the hyperparameters of the convolutional neural network, to get an optimal convolutional neural network parameters, which can significantly improve the accuracy of fuel cell fault diagnosis. It is verified that the accuracy of this method reaches 99.75% in the fault diagnosis of water flooding, membrane drying and oxygen starvation.

导出引用

施永, 黄宁, 谢缔, 汪亮亮, 姚继刚. 基于开普勒算法优化卷积神经网络的燃料电池故障诊断技术[J]. 太阳能学报. 2026, 47(3): 556-563 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1777

Shi Yong, Huang Ning, Xie Di, Wang Liangliang, Yao Jigang. FUEL CELL FAULT DIAGNOSIS TECHNIQUE BASED ON CONVOLUTIONAL NEURAL NETWORK OPTIMIZED BY KEPLER OPTIMIZATION ALGORITHM[J]. Acta Energiae Solaris Sinica. 2026, 47(3): 556-563 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1777

中图分类号： TM911.4

参考文献

[1] 施永, 黄宁, 谢缔, 等. 基于自注意力机制和CNN融合的燃料电池故障诊断技术[J]. 太阳能学报, 2025, 46(5): 53-61.
SHI Y, HUANG N, XIE D, et al.Fuel cell fault diagnosis technique based on self-Attention mechanism and CNN fusion[J]. Acta energiae solaris sinica, 2025, 46(5): 53-61.
[2] 张雪霞, 蒋宇, 孙腾飞, 等. 质子交换膜燃料电池水淹和膜干故障诊断研究综述[J]. 西南交通大学学报, 2020, 55(4): 828-838, 864.
ZHANG X X, JIANG Y, SUN T F, et al.Review on fault diagnosis for flooding and drying in proton exchange membrane fuel cells[J]. Journal of Southwest Jiaotong University, 2020, 55(4): 828-838, 864.
[3] 雍加望, 赵倩倩, 冯能莲. 基于非线性动态模型的质子交换膜燃料电池故障诊断[J]. 化工学报, 2022, 73(9): 3983-3993.
YONG J W, ZHAO Q Q, FENG N L.Fault diagnosis of proton exchange membrane fuel cell based on nonlinear dynamic model[J]. CIESC journal, 2022, 73(9): 3983-3993.
[4] 周苏, 任宏伟, 裴冯来. 基于诊断用COMSOL模型的PEMFC故障诊断方法研究[J]. 化学工业与工程, 2015, 32(4): 56-62.
ZHOU S, REN H W, PEI F L.Faults diagnosis method study of PEMFC based on a diagnostic COMSOL model[J]. Chemical industry and engineering, 2015, 32(4): 56-62.
[5] RUBIO M A, URQUIA A, DORMIDO S.Diagnosis of performance degradation phenomena in PEM fuel cells[J]. International journal of hydrogen energy, 2010, 35(7): 2586-2590.
[6] ROTONDO D, FERNANDEZ-CANTI R M, TORNIL-SIN S, et al. Robust fault diagnosis of proton exchange membrane fuel cells using a Takagi-Sugeno interval observer approach[J]. International journal of hydrogen energy, 2016, 41(4): 2875-2886.
[7] AKITOMO F, SASABE T, YOSHIDA T, et al.Investigation of effects of high temperature and pressure on a polymer electrolyte fuel cell with polarization analysis and X-ray imaging of liquid water[J]. Journal of power sources, 2019, 431: 205-209.
[8] 孙誉宁, 毛磊, 黄伟国, 等. 基于磁场的质子交换膜燃料电池故障诊断方法[J]. 机械工程学报, 2022, 58(22): 106-114.
SUN Y N, MAO L, HUANG W G, et al.Fault diagnosis of proton exchange membrane fuel cell using magnetic field data[J]. Journal of mechanical engineering, 2022, 58(22): 106-114.
[9] 刘嘉蔚, 李奇, 陈维荣, 等. 基于在线序列超限学习机和主成分分析的蒸汽冷却型燃料电池系统快速故障诊断方法[J]. 电工技术学报, 2019, 34(18): 3949-3960.
LIU J W, LI Q, CHEN W R, et al.Fast fault diagnosis method of evaporatively cooled fuel cell system based on online sequential extreme learning machine and principal component analysis[J]. Transactions of China Electrotechnical Society, 2019, 34(18): 3949-3960.
[10] 刘相万, 杨扬, 朱文超, 等. 基于二阶RQ-RLC模型的质子交换膜燃料电池水管理故障诊断[J]. 中国电机工程学报, 2022, 42(21): 7893-7905.
LIU X W, YANG Y, ZHU W C, et al.Second-order RQ-RLC model-based fault diagnosis for water management in proton exchange membrane fuel cells[J]. Proceedings of the CSEE, 2022, 42(21): 7893-7905.
[11] 张领先, 刘斌, 邓琳, 等. 基于改进TSO优化Xception的PEMFC故障诊断[J]. 化工学报, 2024, 75(3): 945-955.
ZHANG L X, LIU B, DENG L, et al.PEMFC fault diagnosis based on improved TSO optimized Xception[J]. CIESC journal, 2024, 75(3): 945-955.
[12] 黄赵军, 苏建徽, 解宝, 等. 基于模糊C均值聚类和概率神经网络的PEMFC故障诊断方法研究[J]. 太阳能学报, 2024, 45(1): 475-483.
HUANG Z J, SU J H, XIE B, et al.Research on pemfc fault diagnosis method based on fuzzy C means clustering and probabilistic neural network[J]. Acta energiae solaris sinica, 2024, 45(1): 475-483.
[13] DU R B, WEI X Z, WANG X Y, et al.A fault diagnosis model for proton exchange membrane fuel cell based on impedance identification with differential evolution algorithm[J]. International journal of hydrogen energy, 2021, 46(78): 38795-38808.
[14] LIU Z Y, SUN Y N, TANG X W, et al.Enabling unsupervised fault diagnosis of proton exchange membrane fuel cell stack:knowledge transfer from single-cell to stack[J]. Applied energy, 2024, 360: 122814.
[15] WANG Z H, GAO Y, YU J, et al.Data-driven fault diagnosis of PEMFC water management with segmented cell and deep learning technologies[J]. International journal of hydrogen energy, 2024, 67: 715-727.
[16] 贺飞, 张雪霞, 陈维荣. 基于P-L双重特征提取的PEMFC系统故障诊断方法[J]. 太阳能学报, 2024, 45(1): 492-499.
HE F, ZHANG X X, CHEN W R.Fault diagnosis method of PEMFC system based on P-L dual feature extraction[J]. Acta energiae solaris sinica, 2024, 45(1): 492-499.
[17] 赵波, 刘相万, 章雷其, 等. 基于GoogLeNet与迁移学习的质子交换膜燃料电池集成系统故障诊断[J]. 中国电机工程学报, 2024, 44(13): 5147-5158.
ZHAO B, LIU X W, ZHANG L Q, et al.Fault diagnosis of proton exchange membrane fuel cell integrated system based on GoogLeNet and transfer learning[J]. Proceedings of the CSEE, 2024, 44(13): 5147-5158.
[18] 杨怡菲, 高岩. 基于线性判别分析的电力负荷预测[J]. 电子设计工程, 2023, 31(11): 102-106.
YANG Y F, GAO Y.Power load forecasting based on linear discriminant analysis[J]. Electronic design engineering, 2023, 31(11): 102-106.
[19] ABDEL-BASSET M, MOHAMED R, ABDEL AZEEM S A, et al. Kepler optimization algorithm: a new metaheuristic algorithm inspired by Kepler’s laws of planetary motion[J]. Knowledge-based systems, 2023, 268: 110454.