汽车工程 ›› 2026, Vol. 48 ›› Issue (3): 690-699.doi: 10.19562/j.chinasae.qcgc.2026.03.018

• • 上一篇    

车载动态工况下燃料电池健康指标提取与寿命估计方法研究

杨云亮1,杜常清1,2,李威岐3,朱文超1(),吴航宇1,谢长君4   

  1. 1.武汉理工大学汽车工程学院,武汉 430070
    2.国家能源氢能及氨氢融合新能源技术重点实验室,佛山仙湖实验室,佛山 528200
    3.潍柴动力股份有限公司,潍坊 261061
    4.武汉理工大学国家卓越工程师学院,武汉 430070
  • 收稿日期:2025-05-14 修回日期:2025-06-26 出版日期:2026-03-25 发布日期:2026-03-19
  • 通讯作者: 朱文超 E-mail:zhuwenchao@whut.edu.cn
  • 基金资助:
    国家自然科学基金智能电网联合基金重点支持项目(U24B20103)和先进能源科学与技术广东省实验室佛山分中心(佛山仙湖实验室)开放基金(XHRD2024-11233100-01)资助。

Health Indicator Extraction Strategy and Life Estimation of Fuel Cells Under Dynamic Operating Condition

Yunliang Yang1,Changqing Du1,2,Weiqi Li3,Wenchao Zhu1(),Hangyu Wu1,Changjun Xie4   

  1. 1.School of Automotive Engineering,Wuhan University of Technology,Wuhan 430070
    2.National Energy Key Laboratory for New Hydrogen-Ammonia Energy Technologies,Foshan Xianhu Laboratory,Foshan 528200
    3.Weichai Power Co. ,Ltd. ,Weifang 261061
    4.National Graduate College for Engineers,Wuhan University of Technology,Wuhan 430070
  • Received:2025-05-14 Revised:2025-06-26 Online:2026-03-25 Published:2026-03-19
  • Contact: Wenchao Zhu E-mail:zhuwenchao@whut.edu.cn

摘要:

有效的健康指标(HI)和预测方法是评估质子交换膜燃料电池(PEMFC)剩余使用寿命(RUL)的关键,而在工况复杂的动态负载下直接获取HI是具有挑战性的。此外,传统的深度学习方法受限于一维数据结构的分析模式,难以准确预测PEMFC中包含多种变化模式的老化趋势。因此,本文提出了一种应对动态工况的预测框架,针对动态负载进行分级处理以得到具有老化趋势的伪动态数据,随后提出了一种经验模态分解、功率谱密度和能量分析相结合的方法(EPE),从分级负载中提取了反映动态工况老化趋势的HI。此外在预测方法上,采用了TimesNet网络将一维HI时间序列转换到二维空间并估计了RUL。结果表明,提取的HI可有效表征PEMFC的老化趋势。在RUL估计方面,TimesNet相比BiLSTM和CNN-BiLSTM的误差分别下降了61.8%和25%。

关键词: 质子交换膜燃料电池, 动态工况, 剩余使用寿命, 健康指标, 深度学习

Abstract:

Effective health indicators (HI) and predictive methods are crucial for assessing the remaining useful life (RUL) of proton exchange membrane fuel cell (PEMFC). However, directly obtaining HIs under complex dynamic load conditions poses significant challenges. Traditional deep learning methods, constrained by their one-dimensional data analysis framework, struggle to accurately predict the aging trends of PEMFCs, which encompass various modes of degradation. To address this, our study proposes a novel prediction framework tailored for dynamic operating conditions. This framework involves a hierarchical processing of dynamic loads to generate pseudo-dynamic data that encapsulates aging trends. Subsequently, a method that combines empirical mode decomposition (EMD), power spectral density (PSD), and energy analysis (EA) is proposed to extract HIs that reflect aging trends under dynamic conditions. Furthermore, in terms of prediction methods, the TimesNet network is utilized to transform one-dimensional HI time series into two-dimensional space and estimate RUL. The results demonstrate that the extracted HIs effectively capture the aging trends of PEMFCs. In terms of RUL estimation, TimesNet reduces the prediction error by 61.8% compared to bidirectional long-short term memory (BiLSTM) and by 25% compared to bidirectional long short-term memory with convolutional neural network (CNN-BiLSTM).

Key words: proton exchange membrane fuel cell, dynamic condition, remaining useful life, health indicator, deep learning