基于ARIMA-BiGRU双数据驱动的燃料电池性能退化预测方法  

A Fuel Cell Performance Degradation Prediction Method Based on ARIMA-BiGRU Dual Data-driven Approach

作　　者：吴航宇 王玮[1] 朱文超 谢长君[1] 杨扬[1] WU Hangyu;WANG Wei;ZHU Wenchao;XIE Changjun;YANG Yang(Wuhan University of Technology,Wuhan 430000,Hubei Province,China)

机构地区：[1]武汉理工大学,湖北省武汉市430000

出　　处：《中国电机工程学报》2025年第7期2690-2698,I0020,共10页PROCEEDINGS OF THE CHINESE SOCIETY FOR ELECTRICAL ENGINEERING

基　　金：国家重点研发计划项目(2020YFB1506802);广东省重点领域研发计划项目(2020B0909040004);国家资助博士后研究人员计划项目(GZC20232011)。

摘　　要：质子交换膜燃料电池(proton exchange membrane fuel cell,PEMFC)是新能源技术的核心载体,准确估计其性能退化对实际应用至关重要。传统的数据驱动方法一般使用非线性算法预测PEMFC系统的性能退化,并通过优化算法结构和参数来提高预测精度,因此对组件多老化时间尺度和电压恢复现象的考虑不够充分。通过分析电压数据中的性能退化信息,提出一种基于双数据驱动的燃料电池电压预测方法;基于时频域分解算法(自适应噪声完全集合经验模态分解经验模态分解)将原始电压数据分解重组为多个老化时间尺度序列;然后,分别使用不同的数据驱动方法预测序列中的整体下降趋势和局部恢复现象。在PEMFC动态数据集上的实验结果表明,所提方法的预测效果较单独方法提高37.2%~43.0%。The proton exchange membrane fuel cell(PEMFC),as a core component of new energy technologies,requires accurate performance degradation estimation for practical applications.While conventional data-driven approaches predominantly utilize nonlinear algorithms to forecast PEMFC system performance degradation and refine predictive accuracy through algorithmic architecture optimization,they frequently overlook critical challenges such as the multi-time-scale aging behaviors of individual components and the complex voltage recovery dynamics inherent in fuel cell operation.This study proposes a dual data-driven approach for fuel cell voltage prediction by extracting performance degradation signatures from voltage data.The methodology first decomposes and reconstructs raw voltage data into multiple aging time-scale sequences using a time-frequency domain decomposition algorithm(Complete Ensemble Empirical Mode Decomposition with Adaptive Noise,CEEMDAN).Subsequently,distinct data-driven methods are implemented to separately predict the global degradation trend and local recovery features within the decomposed sequences.Experimental validation on dynamic PEMFC datasets demonstrates that the proposed method achieves 37.2%-43.0%prediction accuracy improvement compared with standalone approaches.

关 键 词：质子交换膜燃料电池 性能退化预测 融合预测 双向机制 

分 类 号：TM911.4[电气工程—电力电子与电力传动]