PEMFC fault diagnosis based on improved TSO optimized Xception

doi:10.11949/0438-1157.20231247

Abstract

Abstract:

This paper proposes a fault diagnosis method for proton exchange membrane fuel cells (PEMFC) based on Xception network optimized by an improved transient search optimization (TSO) algorithm. First, the fault data are normalized and dimensionally reduced by linear discriminant analysis, which reduces the computational complexity while preserving the main features. Secondly, the TSO algorithm is enhanced by introducing Tent chaotic mapping and reverse learning strategy, which improves its global search ability. The hyperparameters of the Xception neural network are optimized by the TSO algorithm in the training phase. Finally, the fully trained Xception network is used to classify and identify PEMFC faults, and compared with the classic classification model. On the experimental water management fault data and the simulated multi-class fault data, the Xception network achieves the highest classification accuracy, which is 100% and 98.08%, respectively. This indicates that the Xception network has a strong ability to extract data features and the proposed method can serve as a general diagnosis method for PEMFC faults.

Key words: proton exchange membrane fuel cell, fault diagnosis, Tent chaotic mapping, reverse learning, transient search optimization, Xception neural network

摘要：

针对质子交换膜燃料电池（PEMFC）的故障诊断问题，提出了一种利用改进的瞬态搜索优化（TSO）算法优化Xception网络的故障通用诊断方法。首先，对故障数据进行线性判别分析降维和归一化处理，在保留主要特征的前提下降低计算复杂度；其次，引入Tent混沌映射和反向学习策略增强TSO算法的全局搜索能力，在训练阶段对Xception神经网络的超参数进行优化；最后，使用充分训练的Xception网络对PEMFC故障进行分类识别，并与经典的分类模型进行对比。在基于实验测量的水管理故障数据和仿真产生的多类故障数据上，Xception均取得了最高的分类准确率，分别为100%和98.08%，这表明Xception对数据特征的提取能力较强，且所提方法能作为一种PEMFC故障的通用诊断方法。

关键词: 质子交换膜燃料电池, 故障诊断, Tent混沌映射, 反向学习, 瞬态搜索优化, Xception神经网络

CLC Number:

TQ 028.8

Lingxian ZHANG, Bin LIU, Lin DENG, Yuhang REN. PEMFC fault diagnosis based on improved TSO optimized Xception[J]. CIESC Journal, 2024, 75(3): 945-955.

张领先, 刘斌, 邓琳, 任宇航. 基于改进TSO优化Xception的PEMFC故障诊断[J]. 化工学报, 2024, 75(3): 945-955.

Figures/Tables 19

References 30

1	马睿, 党翰斌, 张钰奇, 等. 质子交换膜燃料电池系统故障机理分析及诊断方法研究综述[J]. 中国电机工程学报, 2024, 44(1): 407-427.
	Ma R, Dang H B, Zhang Y Q, et al. A review on failure mechanism analysis and diagnosis for proton exchange membrane fuel cell systems[J]. Proceedings of the CSEE, 2024, 44(1): 407-427.
2	李兰心, 潘牧, 郭伟. 质子交换膜燃料电池在线监测方法研究进展[J]. 材料导报, DOI:10.11896/cldb.22070018 .
	Li L X, Pan M, Guo W. Research progress of online monitoring methods for proton exchange membrane fuel cells[J]. Materials Reports. DOI:10.11896/cldb.22070018 .
3	Wang J B, Yang B, Zeng C Y, et al. Recent advances and summarization of fault diagnosis techniques for proton exchange membrane fuel cell systems: a critical overview[J]. Journal of Power Sources, 2021, 500: 229932.
4	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.
5	Kim J, Lee I, Tak Y, et al. Impedance-based diagnosis of polymer electrolyte membrane fuel cell failures associated with a low frequency ripple current[J]. Renewable Energy, 2013, 51: 302-309.
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	Hinaje M, Béthoux O, Krebs G, et al. Nonintrusive diagnosis of a PEMFC[J]. IEEE Transactions on Magnetics, 2015, 51(3): 1-4.
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	Kamal M M, Yu D W, Yu D L. Fault detection and isolation for PEM fuel cell stack with independent RBF model[J]. Engineering Applications of Artificial Intelligence, 2014, 28: 52-63.
10	刘嘉蔚, 李奇, 陈维荣, 等. 基于概率神经网络和线性判别分析的PEMFC水管理故障诊断方法研究[J]. 中国电机工程学报, 2019, 39(12): 3614-3622.
	Liu J W, Li Q, Chen W R, et al. Research on PEMFC water management fault diagnosis method based on probabilistic neural network and linear discriminant analysis[J]. Proceedings of the CSEE, 2019, 39(12): 3614-3622.
11	Quan R, Liang W L, Wang J H, et al. An enhanced fault diagnosis method for fuel cell system using a kernel extreme learning machine optimized with improved sparrow search algorithm[J]. International Journal of Hydrogen Energy, 2024, 50: 1184-1196.
12	Yuan H, Dai H F, Wei X Z, et al. Model-based observers for internal states estimation and control of proton exchange membrane fuel cell system: a review[J]. Journal of Power Sources, 2020, 468: 228376.
13	Liu J W, Li Q, Yang H Q, et al. Sequence fault diagnosis for PEMFC water management subsystem using deep learning with t-SNE[J]. IEEE Access, 2019, 7: 92009-92019.
14	Liu Z Y, Pei M L, He Q B, et al. A novel method for polymer electrolyte membrane fuel cell fault diagnosis using 2D data[J]. Journal of Power Sources, 2021, 482: 228894.
15	Zhou S, Fan L, Zhang G, et al. A review on proton exchange membrane multi-stack fuel cell systems: architecture, performance, and power management[J]. Applied Energy, 2022, 310: 118555.
16	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.
17	Gu X, Hou Z J, Cai J. Data-based flooding fault diagnosis of proton exchange membrane fuel cell systems using LSTM networks[J]. Energy and AI, 2021, 4: 100056.
18	Zhou S, Wang K, Shan J, et al. Data-driven multi-type and multi-level fault diagnosis of proton exchange membrane fuel cell systems using artificial intelligence algorithms[C]//SAE Technical Paper Series. Warrendale, PA, United States: SAE International, 2022.
19	Mao L, Jackson L. Effect of sensor set size on polymer electrolyte membrane fuel cell fault diagnosis[J]. Sensors, 2018, 18(9): 2777.
20	Ceylan C, Devrim Y. Design and simulation of the PV/PEM fuel cell based hybrid energy system using MATLAB/Simulink for greenhouse application[J]. International Journal of Hydrogen Energy, 2021, 46(42): 22092-22106.
21	Dickinson E J F, Smith G. Modelling the proton-conductive membrane in practical polymer electrolyte membrane fuel cell (PEMFC) simulation: a review[J]. Membranes, 2020, 10(11): 310.
22	Zhou S W, Dhupia J S. RETRACTED: online adaptive water management fault diagnosis of PEMFC based on orthogonal linear discriminant analysis and relevance vector machine[J]. International Journal of Hydrogen Energy, 2020, 45(11): 7005-7014.
23	Qais M H, Hasanien H M, Alghuwainem S. Transient search optimization: a new meta-heuristic optimization algorithm[J]. Applied Intelligence, 2020, 50(11): 3926-3941.
24	Fatani A, Abd Elaziz M, Dahou A, et al. IoT intrusion detection system using deep learning and enhanced transient search optimization[J]. IEEE Access, 2021, 9: 123448-123464.
25	滕志军, 吕金玲, 郭力文, 等. 一种基于Tent映射的混合灰狼优化的改进算法[J].哈尔滨工业大学学报, 2018, 50(11): 40-49.
	Teng Z J, Lv J L, Guo L W, et al. An improved hybrid grey wolf optimization algorithm based on Tent mapping[J]. Journal of Harbin Institute of Technology, 2018, 50(11): 40-49.
26	陈娟, 赵嘉, 肖人彬, 等. 基于动态反向学习和莱维飞行的双搜索模式萤火虫算法[J]. 信息与控制, 2023, 52(5): 607-615.
	Chen J, Zhao J, Xiao R B, et al. Double search mode firefly algorithm based on dynamic reverse learning and levy flight[J]. Information and Control, 2023, 52(5): 607-615.
27	Chollet F. Xception: deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, HI, USA: IEEE, 2017: 1800-1807.
28	Poulose A, Reddy C S, Kim J H, et al. Foreground extraction based facial emotion recognition using deep learning xception model[C]//2021 Twelfth International Conference on Ubiquitous and Future Networks (ICUFN). Jeju Island, Korea: IEEE, 2021: 356-360.
29	张扬, 李晓杰, 马兹林, 等. 锂离子电池故障诊断算法研究综述[J]. 重庆理工大学学报(自然科学), 2023, 37(9): 49-61.
	Zhang Y, Li X J, Ma Z L, et al. A review of fault diagnosis for lithium ion batteries[J]. Journal of Chongqing University of Technology(Natural Science), 2023, 37(9): 49-61.
30	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.

状态	氢气供气系统	空气供气系统	水热管理系统
水淹	供应气体压力低	空压机喘振	水泵压力过低
膜干	氢气泄漏	空气管道泄漏	水管堵塞
短路	高压氢气阀故障	空气过滤器堵塞	循环水导电率过高
过载	氢气管堵塞	风机故障	水量不足
催化剂中毒	循环泵、尾气阀	—	冷却风扇损坏
致命故障	—	—	散热器故障

状态	氢气供气系统	空气供气系统	水热管理系统
水淹	供应气体压力低	空压机喘振	水泵压力过低
膜干	氢气泄漏	空气管道泄漏	水管堵塞
短路	高压氢气阀故障	空气过滤器堵塞	循环水导电率过高
过载	氢气管堵塞	风机故障	水量不足
催化剂中毒	循环泵、尾气阀	—	冷却风扇损坏
致命故障	—	—	散热器故障

参数	数值
有效活化面积/cm²	100
额定功率/W	80
膜厚度/mm	25
铂担量/(mg/cm²)	0.2
气体扩散层厚度/mm	415

参数	数值
有效活化面积/cm²	100
额定功率/W	80
膜厚度/mm	25
铂担量/(mg/cm²)	0.2
气体扩散层厚度/mm	415

序号	变量	单位
1	电压	V
2	电流	A
3	阴极入口流速	SPLM
4	阳极入口流速	SPLM
5	阴极相对湿度	%
6	阳极相对湿度	%
7	阴极入口压力	bar
8	阳极入口压力	bar
9	阴极出口压力	bar
10	阳极出口压力	bar
11	阴极入口温度	℃
12	阳极入口温度	℃
13	电堆温度	℃
14	加热器温度	℃