Proton Exchange Membrane Fuel Cell Fault Prediction Method Based on Deep Learning

doi:10.12141/j.issn.1000-565X.240320

Abstract

Abstract:

Proton exchange membrane fuel cells (PEMFCs) have attracted significant attention in the fields of transportation, marine engineering, and aerospace due to their advantages of pollution-free operation, high efficiency, and low noise. However, reliability issues hinder their large-scale commercialization. To further enhance fuel cell reliability, this paper proposed a fault prediction method based on deep learning. First, for operational monitoring data including voltage, current, humidity, and temperature, feature parameters for fault diagnosis were selected based on fuel cell failure mechanisms. This approach reduces data dimensionality, suppresses redundant information, and improves the computational efficiency of the prediction model. Additionally, pre-processing techniques such as normalization and sliding time windows were employed to eliminate the effects of differing dimensions among monitoring parameters. Then, a fuel cell state prediction model based on the long short-term memory (LSTM) network was constructed. Its inputs were preprocessed multidimensional feature sequences, and its output predicts the fuel cell state for the next T time steps. Finally, the predicted state data was fed into a convolutional neural network (CNN)-based fault identification model to achieve fuel cell fault state prediction. The proposed method was validated using experimental fault data from fuel cell tests, and the results show that the model can predict failures in advance. By virtue of effective data preprocessing, future state prediction via LSTM, and fault recognition through CNN, this deep learning-based approach enables early prediction of operational anomalies in proton exchange membrane fuel cells.

Key words: fuel cell, deep learning, fault prediction, long short-term memory network, convolutional neural network

CLC Number:

TK01

ZUO Bin, DONG Tianhang, ZHANG Zehui, WANG Huajun, HUO Weiwei, GONG Wenfeng, CHENG Junsheng. Proton Exchange Membrane Fuel Cell Fault Prediction Method Based on Deep Learning[J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(7): 21-30.

Figures/Tables 12

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Table 1

Fig.6

Fig.7

Table 2

Fig.8

Table 3

Fig.9

References 29

[1]	赵天宇，陈东，霍为炜，等．氢燃料电池汽车能量管理系统模糊控制仿真研究［J］．重庆理工大学学报（自然科学），2022，36（3）：36-40.
	ZHAO Tianyu， CHEN Dong， HUO Weiwei，et al ．Simulation of energy management system of hydrogen fuel cell vehicle based on fuzzy control［J］．Journal of Chongqing University of Technology （Natural Science），2022，36（3）：36-40．
[2]	井绪宝，刘丛浩，郭宇，等．应用LADRC的车用质子交换膜燃料电池温湿度控制优化研究［J］．重庆理工大学学报（自然科学），2023，37（5）：54-59.
	JING Xubao， LIU Conghao， GUO Yu，et al ．Research on optimization of temperature and humidity control of proton exchange membrane fuel cells for vehicles using LADRC［J］．Journal of Chongqing University of Technology （Natural Science），2023，37（5）：54-59．
[3]	安治国，张东阳，张振，等．阶梯型流道对质子交换膜燃料电池性能的影响［J］．重庆交通大学学报（自然科学版），2022，41（12）：134-140，150.
	AN Zhiguo， ZHANG Dongyang， ZHANG Zhen，et al ．Influence of stepped flow channel on the performance of proton exchange membrane fuel cell［J］．Journal of Chongqing Jiaotong University （Natural Science），2022，41（12）：134-140，150.
[4]	LI H W， QIAO B X， LIU J N，et al ．A data-driven framework for performance prediction and parameter optimization of a proton exchange membrane fuel cell［J］．Energy Conversion and Management，2022，271：116338/1-15.
[5]	ZHANG Y F， MA R， XIE R Y，et al ．A degradation prediction method for PEM fuel cell based on deep temporal feature extraction and transfer learning［J］．IEEE Transactions on Transportation Electrification，2024，10（1）：203-212.
[6]	MIN W， LIANGFEI X， XIAOFAN Y ．A coupled CFD model for an accurate and fast prediction of the unsteady operation process of a proton exchange membrane fuel cell［J］．Energy Conversion and Management，2022，272：116317/1-16.
[7]	ZIHAN T， CHU Z， JINLIN X，et al ．Evolutionary gate recurrent unit coupling convolutional neural network and improved manta ray foraging optimization algorithm for performance degradation prediction of PEMFC［J］．Applied Energy，2023，336：120821/1-14.
[8]	张宁，霍为炜，孙超，等．应用模糊规则的燃料电池水管理容错控制［J］．重庆理工大学学报（自然科学），2022，36（5）：78-83.
	ZHANG Ning， HUO Weiwei， SUN Chao，et al ．Fault tolerant control of fuel cell water management based on fuzzy rules［J］．Journal of Chongqing University of Technology （Natural Science），2022，36（5）：78-83．
[9]	孙铁生，陈山，孙红，等．质子交换膜燃料电池发动机热管理特性仿真分析［J］．重庆大学学报，2023，46（4）：27-36.
	SUN Tiesheng， CHEN Shan， SUN Hong，et al ．Simulation analysis on thermal management characteristics of proton-exchange-membrane fuel-cell engine［J］．Journal of Chongqing University，2023，46（4）：27-36.
[10]	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 Xuexia， JIANG Yu， SUN Tengfei，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．
[11]	DU R， WEI X， WANG X，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.
[12]	LIU Z， SUN Y， MAO L，et al ．Efficient fault diagnosis of proton exchange membrane fuel cell using external magnetic field measurement［J］．Energy Conversion and Management，2022，266：115809/1-13.
[13]	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 Jiawang， ZHAO Qianqian， FENG Nenglian ．Fault diagnosis of proton exchange membrane fuel cell based on nonlinear dynamic model［J］．CIESC Journal，2022，73（9）：3983-3993.
[14]	XIAO F， CHEN T， ZHANG J，et al ．Water management fault diagnosis for proton-exchange membrane fuel cells based on deep learning methods［J］．International Journal of Hydrogen Energy，2023，48（72）：28163-28173.
[15]	刘昕宇，韩莹，陈维荣，等．基于改进SSA-DBN的质子交换膜燃料电池水故障智能分类方法［J］．电力自动化设备，2024，44（4）：18-24.
	LIU Xinyu， HAN Ying， CHEN Weirong，et al ．Intelligent classification method of water faults for proton exchange membrane fuel cell based on improved SSA-DBN［J］．Electric Power Automation Equipment，2024，44（4）：18-24.
[16]	RUBIO M A， SANCHEZ D G， GAZDZICKI P，et al ．Failure mode diagnosis in proton exchange membrane fuel cells using local electrochemical noise［J］．Journal of Power Sources，2022，541：231582/1-10.
[17]	ZUO B， ZHONG Z H， CHENG J S，et al ．Data-driven flooding fault diagnosis method for proton-exchange membrane fuel cells using deep learning technologies［J］．Energy Conversion and Management，2022，251：115004/1-9.
[18]	谢雨岑．基于深度学习的燃料电池性能衰退预测研究［D］．成都：电子科技大学，2021.
[19]	符灏．质子交换膜燃料电池系统的动态建模与优化控制［D］．南京：东南大学，2022.
[20]	HUANG W， JIAN Q， FENG S，et al ．A hybrid optimization strategy of electrical efficiency about cooling PEMFC combined with ultra-thin vapor chambers［J］．Energy Conversion and Management，2022，254：115301/1-15.
[21]	HUO W， LI W， ZHANG Z，et al ．Performance prediction of proton-exchange membrane fuel cell based on convolutional neural network and random forest feature selection［J］．Energy Conversion and Management，2021，243：114367/1-10.
[22]	DAI W， WANG H J， YUAN X Z，et al ．A review on water balance in the membrane electrode assembly of proton exchange membrane fuel cells［J］．International Journal of Hydrogen Energy，2009，34（23）：9461-9478.
[23]	KANDLIKAR S G， GAROFALO M L， LU Z ．Water management in a PEMFC：water transport mechanism and material degradation in gas diffusion layers［J］．Fuel Cells，2011，11（6）：814-823.
[24]	LIM B H， MAJLAN E H， DAUD W，et al ．Effects of flow field design on water management and reactant distribution in PEMFC：a review［J］．Ionics，2016，22：301-316.
[25]	KONG I M， JUNG A， KIM Y S，et al ．Numerical investigation on double gas diffusion backing layer functionalized on water removal in a proton exchange membrane fuel cell［J］．Energy，2017，120：478-487.
[26]	GU X， HOU Z， CAI J ．Data-based flooding fault diagnosis of proton exchange membrane fuel cell systems using LSTM networks［J］．Energy and AI，2021，4：100056/1-12.
[27]	LUO Z， CHANG Z， ZHANG Y，et al ．Electro-osmotic drag coefficient and proton conductivity in Nafion® membrane for PEMFC［J］．International Journal of Hydrogen Energy，2010，35（7）：3120-3124.
[28]	MAO L， JACKSON L， HUANG W，et al ．Polymer electrolyte membrane fuel cell fault diagnosis and sensor abnormality identification using sensor selection method［J］．Journal of Power Sources，2020，447：227394/1-10.
[29]	LIU M H， ZENG A L， CHEN M X，et al ．SCINET：time series modeling and forecasting with sample convolution and interaction［C］∥ Proceedings of the 36th International Conference on Neural Information Processing Systems.［S.l.］：NIPS，2022：5816-5828.

编号	参数		参数
1	电压	7	电堆温度
2	电流	8	阴极出口温度
3	阴极出口湿度	9	阳极出口温度
4	阳极出口湿度	10	阴极出口流量
5	阴极出口压力	11	阳极出口流量
6	阳极出口压力

模型	准确率/%	精确率/%	召回率/%
KNN	91.51	93.18	91.51
SVM	97.45	97.48	97.45
CNN	99.56	99.86	99.44

模型	层数	参数量
CNN	4	13 906
LSTM	4	473 729
SCI-Net	6	21 856