车用燃料电池空气供给系统故障诊断研究

doi:10.19562/j.chinasae.qcgc.2025.07.006

摘要/Abstract

摘要：

为了提升质子交换膜燃料电池（PEMFC）空气供给系统的稳定性、安全性，并延长其使用寿命，本文提出了一种基于残差模型的燃料电池空气供给系统故障诊断方法，提出空气供给系统4阶状态空间模型，验证模型误差在1%以内，确保了所建模型的精度和有效性。设计了空气供给系统滑模观测器，引入高斯噪声模拟实际传感器中的噪声，结果表明在测量值噪声的影响下观测器能较好地跟踪实际值，且估计误差在2%以内。通过观测器实时生成残差对系统故障进行检测，针对残差信号无法准确识别故障类型的问题，引入相对故障敏感度函数建立理论故障敏感度特征矩阵，计算系统实时状态量与理论故障敏感度之间的欧式距离，实现对空气供给系统的故障诊断和隔离，结果表明该方法能够迅速准确地识别并隔离出空压机故障、管道泄漏故障及堵塞故障。

关键词: 燃料电池, 空气供给系统, 滑模观测器, 故障诊断

Abstract:

In order to improve the stability and safety of the air supply system of proton exchange membrane fuel cell （PEMFC） and extend its service life， in this paper， a residual model-based fault diagnosis method for the fuel cell air supply system is proposed. A fourth-order state space model of the air supply system model is proposed， and the model error is verified to be within 1%， which ensures the accuracy and validity of the constructed model. A sliding mode observer for the air supply system is designed， and Gaussian noise is introduced to simulate the noise in the actual sensors. The results show that the observer can track the actual values better， and the estimation error is within 2%. The residuals are generated by the observer in real time to detect the system faults. For the problem of inaccurate identification of fault types by residual signals， the relative fault sensitivity function is introduced to establish the theoretical fault sensitivity feature matrix， and the Euclidean distance between the real-time system state quantities and the theoretical fault sensitivity is calculated to achieve the fault diagnosis and isolation of the air supply system. The results show that the method can quickly and accurately identify and isolate air compressor faults， pipe leakage faults and blockage faults.

Key words: fuel cell, air supply systems, sliding mode observer, fault detection

严浩华,李从心,伊力德,刘颖,刘怡康,张欣. 车用燃料电池空气供给系统故障诊断研究[J]. 汽车工程, 2025, 47(7): 1285-1295.

Haohua Yan,Congxin Li,Lide Yi,Ying Liu,Yikang Liu,Xin Zhang. Research on Air Supply System Fault Diagnosis for Vehicle Fuel Cells[J]. Automotive Engineering, 2025, 47(7): 1285-1295.

图/表 25

表1

模型变量的物理含义"

变量	定义	变量	定义
$x 1 = ω c p$	空压机转速/（rad·s^-1）	$x 4 = p o m$	排气管道压力/Pa
$x 2 = p s m$	供给管道压力/Pa	$U c m$	空压机输入电压/V
$x 3 = p c a$	阴极流道压力/Pa	$I s t$	负载电流/A

表1

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表2

空气供给系统中的故障［9，33-34］"

故障	故障描述	大小
$f 1$	空压机内阻增加	$Δ R c m = ± 20 % R c m$
$f 2$	供给管道泄漏	$Δ k s m, o u t = ± 10 % k s m, o u t$
$f 3$	阴极流道堵塞	$Δ k c a, o u t = ± 10 % k c a, o u t$
$f 4$	排气管道泄漏	$Δ l = ± 15 % W s m, o u t$

表2

图12

图13

图14

图15

图16

表3

故障特征矩阵"

故障	S1	S2	S3	S4
$f 1$	1	1	0	1
$f 2$	1	1	1	1
$f 3$	0	1	1	1
$f 4$	0	1	1	1

表3

表4

理论相对故障敏感度矩阵"

故障	$r 1 / r 2$	$r 3 / r 2$	$…$	$r n / r 2$
$f 1$	$S r 1, r 2, f 1 r e l, t h e o$	$S r 3, r 2, f 1 r e l, t h e o$	$…$	$S r n, r 2, f 1 r e l, t h e o$
$f 2$	$S r 1, r 2, f 2 r e l, t h e o$	$S r 3, r 2, f 2 r e l, t h e o$	$…$	$S r n, r 2, f 2 r e l, t h e o$
$f 3$	$S r 1, r 2, f 3 r e l, t h e o$	$S r 3, r 2, f 3 r e l, t h e o$	$…$	$S r n, r 2, f 3 r e l, t h e o$
$?$	$?$	$?$	$?$	$?$
$f n$	$S r 1, r 2, f n r e l, t h e o$	$S r 3, r 2, f n r e l, t h e o$	$…$	$S r n, r 2, f n r e l, t h e o$

表4

表5

理论相对故障敏感度矩阵计算结果"

故障	$r 1 / r 2$	$r 3 / r 2$	$r 4 / r 2$
$f 1$	71.432 5	0.668 5	0.116 5
$f 2$	0.202 0	25.941 9	4.569 4
$f 3$	9.97 $×$ 10^-4	253.691 4	2.570 4
$f 4$	0.014 9	8.371 7	1.471 7

表5

图17

图18

图19

图20

参考文献 33

[1]	WANG Y， CHEN K S， MISHLER J， et al. A review of polymer electrolyte membrane fuel cells： technology， applications， and needs on fundamental research［J］. Applied Energy， 2011， 88（4）： 981-1007.
[2]	WU D， LI K， GAO Y， et al. Design and simulation of proton exchange membrane fuel cell system［J］. Energy Reports， 2021， 7： 522-530.
[3]	BENMOUNA A， BECHERIF M， DEPERNET D， et al. Fault diagnosis methods for proton exchange membrane fuel cell system［J］. International Journal of Hydrogen Energy， 2017， 42（2）： 1534-1543.
[4]	WON J， OH H， HONG J， et al. Hybrid diagnosis method for initial faults of air supply systems in proton exchange membrane fuel cells［J］. Renewable Energy， 2021， 180： 343-352.
[5]	ZHENG Z， PETRONE R， PÉRA M C， et al. A review on non-model based diagnosis methodologies for PEM fuel cell stacks and systems［J］. International Journal of Hydrogen Energy， 2013， 38（21）： 8914-8926.
[6]	PETRONE R， ZHENG Z， HISSEL D， et al. A review on model-based diagnosis methodologies for PEMFCs［J］. International Journal of Hydrogen Energy， 2013， 38（17）： 7077-7091.
[7]	YANG D， WANG Y， CHEN Z. Robust fault diagnosis and fault tolerant control for PEMFC system based on an augmented LPV observer［J］. International Journal of Hydrogen Energy， 2020， 45（24）： 13508-13522.
[8]	SERON M M， DE DONÁ J A. Robust fault estimation and compensation for LPV systems under actuator and sensor faults［J］. Automatica， 2015， 52： 294-301.
[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]	SINHA V， MONDAL S. Adaptive unknown input observer approach for multi-fault diagnosis of PEM fuel cell system with time-delays［J］. Journal of Control and Decision， 2021， 8（2）： 222-232.
[11]	SHAO M， ZHU X J， CAO H F， et al. An artificial neural network ensemble method for fault diagnosis of proton exchange membrane fuel cell system［J］. Energy， 2014， 67： 268-275.
[12]	LI Z， OUTBIB R， GIURGEA S， et al. Diagnosis for PEMFC systems： a data-driven approach with the capabilities of online adaptation and novel fault detection［J］. IEEE Transactions on Industrial Electronics， 2015， 62（8）： 5164-5174.
[13]	LIU Z， PEI M， HE Q， et al. A novel method for polymer electrolyte membrane fuel cell fault diagnosis using 2D data［J］. Journal of Power Sources， 2021， 482： 228894.
[14]	周苏，杨铠，胡哲.FCM方法和SVM方法在燃料电池故障诊断模式识别中的对比研究［J］.机电一体化，2016，22（5）：3-7，21.
	ZHOU Su，YANG Kai，HU Zhe．Comparison on methods of pattern recognition in PEMFC faults diagnosis based on FCM and SVM［J］．Mechatronics，2016，22（5）：3-7， 21．
[15]	TANG Z， HUANG Q A， WANG Y J， et al. Recent progress in the use of electrochemical impedance spectroscopy for the measurement， monitoring， diagnosis and optimization of proton exchange membrane fuel cell performance［J］. Journal of Power Sources， 2020， 468： 228361.
[16]	REN P， PEI P， LI Y， et al. Diagnosis of water failures in proton exchange membrane fuel cell with zero-phase ohmic resistance and fixed-low-frequency impedance［J］. Applied Energy， 2019， 239： 785-792.
[17]	TURHAN A， HELLER K， BRENIZER J S， et al. Passive control of liquid water storage and distribution in a PEFC through flow-field design［J］. Journal of Power Sources， 2008， 180（2）： 773-783.
[18]	AKITOMO F， SASABE T， YOSHIDA T， et al. Investigation of effects of high temperature and pressure on a polymer electrolyte fuel cell with polarization analysis and X-ray imaging of liquid water［J］. Journal of Power Sources， 2019， 431： 205-209.
[19]	CHEN H， ZHAO X， ZHANG T， et al. The reactant starvation of the proton exchange membrane fuel cells for vehicular applications： a review［J］. Energy Conversion and Management， 2019， 182： 282-298.
[20]	梁栋，侯明，窦美玲，等.质子交换膜燃料电池燃料饥饿现象［J］.电源技术，2010，34（8）：767-770.
	LIANG D，HOU M，DOU M L，et al. Study on behavior of proton exchange membrane fuel cell under fuel starvation conditions［J］. Chinese Journal of Power Sources，2010，34（8）：767-770.
[21]	刘嘉蔚，李奇，陈维荣，等.基于在线序列超限学习机和主成分分析的蒸汽冷却型燃料电池系统快速故障诊断方法［J］.电工技术学报，2019，34（18）：3949-3960.
	LIU J W，LI Q，CHEN W R，et al. Fast fault diagnosis method of evaporatively cooled fuel cell system based on online sequential extreme learning machine and principal component analysis［J］. Transactions China Electrotechnical Society，2019，34（18）：3949-3960.
[22]	PUKRUSHPAN J T， STEFANOPOULOU A G， PENG H. Control of fuel cell breathing［J］. IEEE Control Systems Magazine， 2004， 24（2）： 30-46.
[23]	ABOUOMAR M S， ZHANG H J， SU Y X. Fractional order fuzzy PID control of automotive PEM fuel cell air feed system using neural network optimization algorithm［J］. Energies， 2019， 12（8）： 1435.
[24]	DING S X. Model-based fault diagnosis techniques： design schemes， algorithms， and tools［M］. Springer Science & Business Media， 2008.
[25]	DE LIRA S， PUIG V， QUEVEDO J. PEM fuel cell system robust LPV model-based fault diagnosis［C］. 20th International Workshop on Principles of Diagnosis， 2009： 91-98.
[26]	AITOUCHE A， YANG Q， BOUAMAMA B O. Fault detection and isolation of PEM fuel cell system based on nonlinear analytical redundancy： an application via parity space approach［J］. The European Physical Journal-Applied Physics， 2011， 54（2）： 23408.
[27]	SCHMID M， GEBAUER E， HANZL C， et al. Active model-based fault diagnosis in reconfigurable battery systems［J］. IEEE Transactions on Power Electronics， 2020， 36（3）： 2584-2597.
[28]	ZHU J， ZHAO J， JIANG B. Actuator fault reconstruction for PEM fuel cell air-feed system using adaptive sliding mode observer［C］. 2020 Chinese Automation Congress （CAC）. IEEE， 2020： 4406-4411.
[29]	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.
[30]	杨朵.燃料电池空气供给系统控制与故障诊断策略研究［D］.合肥：中国科学技术大学，2021.
	YANG D. Research on control and fault diagnosis strategy of fuel cell air supply system［D］. Hefei： University of Science and Technology of China，2021.
[31]	LIU J， LIN W， ALSAADI F， et al. Nonlinear observer design for PEM fuel cell power systems via second order sliding mode technique［J］. Neurocomputing， 2015， 168： 145-151.
[32]	KULLAA J. Detection， identification， and quantification of sensor fault in a sensor network［J］. Mechanical Systems and Signal Processing， 2013， 40（1）： 208-221.
[33]	韩峰. 燃料电池发动机系统氢安全监测与故障诊断研究［D］. 北京：北京交通大学， 2020.