基于ISAO-CNN-GRU的质子交换膜燃料电池寿命预测
2025-07-29熊健宇匡亚洲彭忆强





中图分类号:TM911.4 文献标志码:A DOI:10.20104/j.cnki.1674-6546.20240429
LifePrediction of Proton Exchange Membrane Fuel Cell Based onISAO-CNN-GRU
Xiong Jianyu1,Kuang Yazhoul,Peng Yiqiangl,2
(1.ScholofAutomobileand Transportation,Xihua University,Chengdu 610o39;2.Vehicle MeasurementControlandSafety KeyLaboratoryofSichuanProvince,Chengdu61Oo39;3.ProvincialEngineering Research CenterforNewEnergy Vehicle Intelligent Control and Simulation Test Technology of Sichuan, Chengdu 610039)
【Abstract]To predict the Remaining Useful Life(RUL)of Proton Exchange Membrane Fuel Cell (PEMFC)precisely,the paper proposes a method for predicting the RUL based onneural network optimized by Improved Snow Ablation Optimizer (ISAO).Firstlytheoriginaldataarepreprocessedbyusing Pautacriterionandwavelets,thenthePearson’scorrelation coeficients areused toselect parameters which have strong corelation with voltageas input variables.ISAOisused to optimize hyperparametersof Convolutional Neural Network-GatedRecurent Unit(CNN-GRU) model.Thenthe CNN-GRU model isusedtopredicttheoutputvoltageof the PEMFC.Testresults show that whenthetraining setratio is 30%,the mean absoluteerroris 1.6mV ,theroot mean square erroris 2.2mV ,therelativeerroris 0.41% ,and theR-squared of themethod is 99.20%,whicharethe bestresults theof six models.Compared with the Sparow Search Algorithm (SSA),Snow Ablation Optimizer (SAO)and Whale Optimization Algorithm(WOA),the ISAO hasfasteroptimization speed and beterresult,proving that the prediction model and the improved algorithm are effective.
Keywords:Proton Exchange Membrane Fuel Cell(PEMFC),Remaining Useful Life (RUL). SnowAblation Optimizer (SAO),Gauss-Cauchy mutation
【引用格式】熊健宇,匡亚洲,彭忆强.基于ISAO-CNN-GRU的质子交换膜燃料电池寿命预测[J].汽车工程师,2025(7): 36-43. XIONGJY,KUANGYZ,PENGYQ.LifePredictionof Proton Exchange MembraneFuel CellBasedon ISAOCNN-GRU[J]. Automotive Engineer, 2025(7): 36-43.
*基金项目:四川省科技厅重大科技项目(2019ZDZX0002);四川省区域创新合作项目(2020YFQ0037);四川省重点研发计划项目(2021YFG0071)。
1前言
2 基本原理
质子交换膜燃料电池(ProtonExchangeMembraneFuelCell,PEMFC)在许多领域得到了广泛应用。虽然其具有能量转换效率高、工作噪声小、无污染等多种优点,但目前仍面临维护成本高、性能衰减快、耐久性不足等问题2。精准预测PEMFC的剩余使用寿命(RemainingUsefulLife,RUL)是确保PEMFC得到及时维护,进而延长其使用寿命的关键因素。
目前,RUL的预测方法包括模型驱动法、数据驱动法和混合驱动法。模型驱动法通过构建数学模型表征燃料电池的退化特性,主要包括根据燃料电池退化的物理及化学原理构建的机理模型,以及通过挖掘电池内部各种参数的数学关系构建的经验模型[4-5,预测算法主要有卡尔曼滤波及其变体6-8、粒子滤波等。数据驱动法直接运用燃料电池老化过程中的数据即可实现准确预测。文献[10]提出了一种多灰色组合结合反向传播(BackPropagation,BP)神经网络的预测模型,运用氢燃料电池汽车的实时数据进行训练,预测结果与实际结果相近。文献[11]提出一种支持向量机(SupportVectorMachine,SVM)与经验模型结合的燃料电池寿命混合预测模型,预测误差相比SVM模型平均下降了 80% 。文献[12]在基于长短期记忆(Long Short-TermMemory,LSTM)网络的预测方法的基础上增加卷积神经网络(ConvolutionalNeuralNetworks,CNN),加快了训练和预测速度,相对误差仅为0.03% 。文献[13]提出基于门控循环单元(GatedRecurrentUnit,GRU)的燃料电池RUL预测方法,与BP和LSTM网络相比,预测精度得到大幅提升。……
