تشخیص پدیدۀ خشکی و طغیان در پیل‌های سوختی غشای تبادل پروتون مبتنی بر منطق فازی چند ارزشی

نوع مقاله : مقاله پژوهشی

نویسندگان

استادیار، گروه مهندسی برق، دانشگاه صنعتی همدان، همدان، ایران

10.22059/ses.2026.409883.1209

چکیده

پیل‌های سوختی غشای تبادل پروتون به ‌عنوان یکی از گزینه‌های مهم برای تولید انرژی پاک در صنایع خودروسازی مطرح هستند، اما عملکرد آن‌ها به‌شدت تحت تأثیر مدیریت آب درون سامانه قرار دارد. در این پژوهش رویکردی نوین برای تشخیص و آشکارسازی وضعیت تعادل آب در پیل سوختی ارائه شده که بر پایۀ ترکیب منطق فازی چند ارزشی و پارامترهای هندسی طیف‌سنجی امپدانس الکتروشیمیایی بنا شده است. منطق فازی چند ارزشی امکان مدل‌سازی شرایط میانی و مرزی میان حالت‌های خشکی، نرمال و طغیان را فراهم می‌آورد. تحلیل هندسی طیف‌های امپدانس، سه پارامتر کلیدی مقاومت اهمی، شعاع نیم‌دایرۀ نفوذ و مؤلفۀ حقیقی مرکز آن را استخراج کرده و به‌ عنوان ورودی سیستم فازی با ۶۴۰ قانون مورد استفاده قرار گرفته است. نتایج شبیه‌سازی در نرم‌افزار متلب روی ۵۰ حالت عملیاتی (شامل ۹ حالت نرمال، ۱۵ حالت خشکی و ۲۶ حالت طغیان) نشان می‌دهد روش پیشنهادی با دقت کلی 98 درصد قادر به تشخیص نوع خطا است و شدت پدیده‌ها را با میانگین خطای مطلق 45/1 درصد تخمین می‌زند. میانگین خطای شدت برای حالت نرمال 17/0 درصد، خشکی 1/2 درصد و طغیان 7/1 درصد به دست آمده است. این روش در مقایسه با روش‌های مرسوم نظیر شبکۀ عصبی بازگشتی حافظۀ بلند ـ کوتاه‌ مدت با دقت 94 درصد، شبکۀ عصبی کانولوشنی عمیق با دقت 90 درصد و منطق فازی نوع-۱ با دقت 80 درصد، برتری چشمگیری داشته و به ‌عنوان ابزاری کارآمد برای پایش آنلاین و بهبود قابلیت اطمینان پیل‌های سوختی قابل به‌کارگیری است. این دستاورد می‌تواند زمینه‌ساز توسعۀ سامانه‌های هوشمند کنترل و افزایش عمر مفید پیل‌های سوختی در کاربردهای صنعتی و حمل‌ونقل باشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Detection of Dehydration and Flooding Phenomena in Proton Exchange Membrane Fuel Cells Based on Multi-Valued Fuzzy Logic

نویسندگان [English]

  • Pezhman Bayat
  • Peyman Bayat
Assistant Professor, Department of Electrical Engineering, Hamedan University of Technology, Hamedan, Iran
چکیده [English]

Proton exchange membrane fuel cells are considered one of the most important options for clean energy production in the automotive industry, but their performance is strongly influenced by water management within the system. In this study, a novel approach for detecting and diagnosing the water balance state in a fuel cell is presented, based on the combination of multi-valued fuzzy logic and geometric parameters of electrochemical impedance spectroscopy. Multi-valued fuzzy logic enables modeling of intermediate and boundary conditions between dehydration, normal, and flooding states. Geometric analysis of impedance spectra extracts three key parameters: ohmic resistance, the diffusion semicircle radius, and the real component of its center, which are used as inputs to a fuzzy system with 640 rules. Simulation results in MATLAB software on 50 operational states (including 9 normal, 15 dehydration, and 26 flooding states) show that the proposed method can diagnose the fault type with an overall accuracy of 98% and estimate the severity of phenomena with a mean absolute error of 1.45%. The mean severity errors are 0.17% for normal state, 2.1% for dehydration state, and 1.7% for flooding state. Compared to conventional methods such as long short-term memory recurrent neural network with 94% accuracy, deep convolutional neural network with 90% accuracy, and type-1 fuzzy logic with 80% accuracy, this method demonstrates significant superiority and can be employed as an efficient tool for online monitoring and improving the reliability of fuel cells. This achievement can pave the way for the development of intelligent control systems and extend the operational life of fuel cells in industrial and transportation applications.

کلیدواژه‌ها [English]

  • Dehydration Phenomena
  • Flooding Phenomena
  • Proton Exchange Membrane Fuel Cells
  • Electrochemical Impedance Spectroscopy
  • Multi-Valued Fuzzy Logic
[1] Zadorozhna DB, Grajeda JS, López LO, Benavides O, Ramírez SF. Assessing the accuracy and replicability of water formation modeling in PEM fuel cells: a sensitivity analysis of key performance parameters using computational fluid dynamics. International Journal of Hydrogen Energy. 2025 Feb 14. https://doi.org/10.1016/j.ijhydene.2025.02.009  
[2] Ma L, Zhao H, Qu Y, Zhao S, Yu Y, Wei W. Reduced‐order active disturbance rejection control method for PEMFC air intake system based on the estimation of oxygen excess ratio. IET Renewable Power Generation. 2023;17(4):951-63. https://doi.org/10.1049/rpg2.12647
[3] Zhao L, Dai H, Pei F, Ming P, Wei X, Zhou J. A comparative study of equivalent circuit models for electro-chemical impedance spectroscopy analysis of proton exchange membrane fuel cells. Energies. 2022;15(1):386. https://doi.org/10.3390/en15010386
[4] Guo Z, Ma R, Ma H, Li Z, Xiong P, Jiang W, Zhou Y. An Online Fault Diagnosis Method for PEMFC Based on Output Voltage and Transfer Convolutional Neural Network. IEEE Transactions on Industrial Electronics. 2025. https://doi.org/10.1109/TIE.2024.3525115
[5] Kamal MM, Yu DW, Yu DL. Fault detection and isolation for PEM fuel cell stack with independent RBF model. Engineering Applications of Artificial Intelligence. 2014 Feb 1;28:52-63. https://doi.org/10.1016/j.engappai.2013.10.002
[6] Bäumler A, Azib T, Benterki A, Meng J, Boukhnifer M. A Learning-based Energy Management Strategy Considering Flooding and Drying Faults for Fuel Cell-Battery Hybrid Vehicles. Psycoloquy. 2024:828-33. https://doi.org/10.1109/MED61351.2024.10566230
[7] Sani M, Piffard M, Heiries V. Fault detection for pem fuel cells via analytical redundancy: A critical review and prospects. Energies. 2023;16(14):5446. https://doi.org/10.3390/en16145446
[8] Yu D, Li X, Zhou F, Araya SS, Sahlin SL, Subramanian VR, Liso V. Online fault detection and isolation of PEMFC based on EIS and data-driven methods: Feasibility study and prospects. Journal of Power Sources. 2025;641:236915. https://doi.org/10.1016/j.jpowsour.2025.236915
[9] Li Y, Huang Q, Yuan H, Wang X, Wei X, Zhu J, Ma R, Gao L, Dai H. A review of polarization dynamics analysis of proton exchange membrane fuel cell: Distribution of relaxation time based method. Science China Technological Sciences. 2025;68(10):2010102. https://doi.org/10.1007/s11431-025-3017-4
[10] Zhang T, Hou Z, Li X, Chen Q, Wang Q, Lüddeke C, Wu L, Wu X, Sun W. A novel multivariable prognostic approach for PEMFC degradation and remaining useful life prediction using random forest and temporal convolutional network. Applied Energy. 2025;385(C). https://doi.org/10.1016/j.apenergy.2025.125569
[11] Ao Y, Laghrouche S, Depernet D. Diagnosis of proton exchange membrane fuel cell system based on adaptive neural fuzzy inference system and electrochemical impedance spectroscopy. Energy Conversion and Management. 2022;256:115391. https://doi.org/10.1016/j.enconman.2022.115391
[12] Liu Q, Zang W, Zhang W, Zhang Y, Tong Y, Feng Y. Steady-State Model Enabled Dynamic PEMFC Performance Degradation Prediction via Recurrent Neural Network. Energies. 2025;18(10):2665. https://doi.org/10.3390/en18102665
[13] Rubio GA, Agila WE. A fuzzy model to manage water in polymer electrolyte membrane fuel cells. Processes. 2021;9(6):904. https://doi.org/10.3390/pr9060904
[14] Omer Abbaker AM, Wang H, Tian Y. Robust model-free adaptive interval type-2 fuzzy sliding mode control for PEMFC system using disturbance observer. International Journal of Fuzzy Systems. 2020;22(7):2188-203. https://doi.org/10.1007/s40815-020-00916-8
[15] Fan L, Ma X. Maximum power point tracking of PEMFC based on hybrid artificial bee colony algorithm with fuzzy control. Scientific Reports. 2022;12(1):4316. https://doi.org/10.1038/s41598-022-08327-5
[16] Franco EE, Henao Santa S, Cabrera JJ, Laín S. Air Flow Monitoring in a Bubble Column Using Ultrasonic Spectrometry. Fluids. 2024;9(7):163. https://doi.org/10.3390/fluids9070163
[17] Rostan K, Kruglov R, Seiß V, Thiel S, Eichelbaum M, Engelbrecht R. In-situ Temperature and Humidity Measurement in PEM Fuel Cells with Off-the-shelf FBG. In Optical Fiber Sensors 2023. p. Tu3-36. Optica Publishing Group. https://doi.org/10.1364/OFS.2023.Tu3.36
[18] Li Q, Wang H, Wang T, Li X, Liu Y, Chen W, You Z. Online diagnosis method of water management faults based on hybrid-frequency electrochemical impedance spectroscopy for PEMFC. IEEE Transactions on Transportation Electrification. 2024. https://doi.org/10.1109/TTE.2024.3427401
[19] Cao TF, Lin H, Chen L, He YL, Tao WQ. Numerical investigation of the coupled water and thermal management in PEM fuel cell. Applied energy. 2013;112:1115-25. https://doi.org/10.1016/j.apenergy.2013.02.031
[20] Duque L, Molinero A, Oller JC, Barcala JM, Diaz‐Alvarez E, Folgado MA, Chaparro AM. Study of Mass Transport in the Anode of a Proton Exchange Membrane Fuel Cell with a New Hydrogen Flow‐Rate Modulation Technique. ChemElectroChem. 2024;11(14):e202400100. https://doi.org/10.1002/celc.202400100
[21] Lv J, Yu Z, Zhang H, Sun G, Muhl P, Liu J. Transformer based long-term prognostics for dynamic operating PEM fuel cells. IEEE Transactions on Transportation Electrification. 2023;10(1):1747-57. https://doi.org/10.1109/TTE.2023.3266803
[22] Li T, Bao Z, Yao R, Pan X, Bai F, Peng Z, Jiao K, Liu Z. Two-phase flow in the gas diffusion layer with different perforation of proton exchange membrane fuel cell. International Journal of Green Energy. 2025;22(6):1063-71. https://doi.org/10.1080/15435075.2024.2347269
[23] Cheikh A, Steiner NY, Pahon E, Damour C, Benne M, Hissel D. Fault diagnosis of PEMFC using semi-empirical signal processing and K-means clustering. In Symposium de Génie Electrique 2023. https://hal.science/hal-04452049
[24] Romey W, Vijayaraghavan K. Extended Kalman Filter for Normal and Oxygen-starved PEM Fuel Cells using a Lumped Pseudo-2D Model. In2022 IEEE International Symposium on Advanced Control of Industrial Processes (AdCONIP). 2022. p. 263-268). IEEE. https://doi.org/10.1109/AdCONIP55568.2022.9894212   
[25] Huo H, Chen J, Wang K, Wang F, Jin G, Chen F. State estimation of membrane water content of PEMFC based on GA-BP neural network. Sustainability. 2023;15(11):9094. https://doi.org/10.3390/su15119094
[26] Wei Y, Zhao Y, Yun H. Estimating PEMFC ohmic internal impedance based on indirect measurements. Energy Science & Engineering. 2021;9(8):1134-47. https://doi.org/10.1002/ese3.878
[27] Zhou S, Zheng S, Hu Z. Proton Exchange Membrane Fuel Cell Fault Rapid Diagnosis Method Based on Electrochemical Impedance Spectroscopy and Fuzzy c-Means Algorithm. SAE Technical Paper 2019-01-5032; 2019. https://doi.org/10.4271/2019-01-5032
[28] Chambers JE, Gunn DA, Wilkinson PB, Ogilvy RD, Ghataora GS, Burrow MP, Smith RT. Non-invasive time-lapse imaging of moisture content changes in earth embankments using electrical resistivity tomography (ERT). In Advances in transportation geotechnics. 2008. p. 489-494. CRC Press. https://nora.nerc.ac.uk/id/eprint/7001/1/CH059.pdf
[29] Singh K, Kumar R, Kumar P, Nehra V, Gupta RK, Yusuf M. Few-layer Si and WS2-based surface plasmon resonance sensor for water salinity concentration detection: theoretical insight. Plasmonics. 2024;19(6):3155-65. https://doi.org/10.1007/s11468-024-02209-4
[30] Mahdavi Nasab AM, Roghani Araghi A. Improving Gas Turbine Performance in an Island Energy System Using Fuel Cells.  Journal of Sustainable Energy Systems. 2024;3(4):401-17. https://doi.org/10.22059/ses.2024.382693.1098
[31] Lv J, Yu Z, Zhang H, Sun G, Muhl P, Liu J. Transformer based long-term prognostics for dynamic operating PEM fuel cells. IEEE Transactions on Transportation Electrification. 2023;10(1):1747-57. https://doi.org/10.1109/TTE.2023.3266803
[32] Moezzi SM, Shirazi MA, Monfared AR, Yousefi H. Comparison of classical statistical models for forecasting CO₂ emissions, GDP, and TBL cancer indicators: A comparative analysis of East and West Asia. Energy Nexus. 2026 Mar 1;21:100682. https://doi.org/10.1016/j.nexus.2026.100682
[33] Shirazi MA, Zahedi R, Yousefi H, Aslani A. Environmental and damage assessment of electric vehicles compared to internal combustion engine vehicles under various ambient temperature scenarios using the LCA approach. Energy Nexus. 2025 Nov 19:100606. https://doi.org/10.1016/j.nexus.2025.100606
[34] Ma Y, Wang X, Yuan H, Chang G, Zhu J, Dai H, Wei X. Review of electrochemical impedance spectroscopy in fault diagnosis for proton exchange membrane fuel cells. Renewable and Sustainable Energy Reviews. 2025 Apr 1;211:115226. https://doi.org/10.1016/j.rser.2024.115226
[35] Pivac I, Šimić B, Barbir F. Experimental diagnostics and modeling of inductive phenomena at low frequencies in impedance spectra of proton exchange membrane fuel cells. Journal of Power Sources. 2017 Oct 15;365:240-8. https://doi.org/10.1016/j.jpowsour.2017.08.087
[36] Yu D, Li X, Zhou F, Araya SS, Sahlin SL, Subramanian VR, Liso V. Online fault detection and isolation of PEMFC based on EIS and data-driven methods: Feasibility study and prospects. Journal of Power Sources. 2025 Jun 15;641:236915. https://doi.org/10.1016/j.jpowsour.2025.236915
[37] Liao Y, Wu J, Luo X. A Multi-valued Fuzzy Logic for Qualitative Reasoning in Healthcare. In The International Conference on Healthcare Science and Engineering 2018 Sep 10 (pp. 235-250). Singapore: Springer Singapore. https://doi.org/10.1007/978-981-13-6837-0_17
[38] Bhattacharjee D, Kim W, Chattopadhyay A, Waser R, Rana V. Multi-valued and fuzzy logic realization using TaOx memristive devices. Scientific reports. 2018 Jan 8;8(1):8. https://doi.org/10.1038/s41598-017-18329-3
[39] Kagan E, Rybalov A, Yager RR. Multi-Valued Logic for Decision-Making Under Uncertainty. Birkhäuser; 2025 Feb 17. https://doi.org/10.1007/978-3-031-74762-5
[40] Sakharov A. Multi-Valued Models for Intuitionistic Logic. In2025 IEEE 55th International Symposium on Multiple-Valued Logic (ISMVL) 2025 Jun 1 (pp. 21-25). IEEE Computer Society. https://doi.org/10.1109/ISMVL64713.2025.00013