Yapay zeka teknikleriyle PEMFC membran elektrot yapısının polarizasyon eğrilerinin tahmini

Yıl 2024, Cilt: 13 Sayı: 4, 1538 - 1544, 15.10.2024

Haydar Bayar , Erkan Dursun

https://doi.org/10.28948/ngumuh.1536258

Öz

Proton değişim membranlı yakıt hücreleri (PEMFC) otomobiller, otobüsler, kesintisiz güç kaynakları ve kombine ısı güç sistemlerinde ticari olarak kullanılmaktadır ve yakıt hücresi pazarında önemli bir yere sahiptir. Yakıt hücresi performansı, tasarım ve üretim süreçlerinde polarizasyon eğrileri ile karakterize edilir. Bu çalışma, farklı çalışma koşullarında eğitilip test edilen karşılaştırmalı yapay zeka (AI) modelleri kullanarak bir PEMFC'nin polarizasyon eğrilerini tahmin etmektedir. AI model girdileri hücre sıcaklığı, nem, anot-katot akışı ve membran direncidir. Çıktılar ise hücre voltajı ve akım yoğunluğudur. Model çıktıları, MATLAB yazılımı kullanılarak 50°C, %100 nem koşullarındaki deneysel değerlerle karşılaştırılmıştır. ANFIS tahmini için hataların ortalama karekökü (RMSE) 0.056112 iken, ANN tahmini için 0.011919'dur. Bu sonuçlar, Yapay Sinir Ağı (ANN) yönteminin, PEMFC'nin Membran Elektrot Yapısının (MEA) davranışını tahmin etmede Uyarlamalı Nöro Bulanık Çıkarım Sistemi (ANFIS) yönteminden daha iyi performans gösterdiğini göstermektedir. Modeller yüksek doğrulukla umut verici sonuçlar vermiştir.

Anahtar Kelimeler

Yapay zeka, Elektrokimyasal cihazlar, Enerji Dönüşümü, Yakıt hücreleri

Prediction of polarization curves of PEMFC membrane electrode assembly using artificial intelligence technics

Öz

Proton exchange membrane fuel cells (PEMFCs) are used commercially in automobiles, buses, uninterruptible power supplies, and combined heat power systems, holding a significant place in the fuel cell market. Fuel cell performance is characterized by polarization curves in design and manufacturing processes. This study predicts a PEMFC’s polarization curves using comparative artificial intelligence (AI) models trained and tested under different operational conditions. The AI model inputs are cell temperature, humidity, anode-cathode flow, and membrane resistance. The outputs are cell voltage and current density. The model outputs are compared with experimental values for 50°C, 100% humidity using MATLAB software. The average Root Mean Square Error (RMSE) for the ANFIS prediction is 0.056112, while for the ANN prediction it is 0.011919. These results indicate that the Artificial Neural Network (ANN) method outperforms the Adaptive Neuro Fuzzy Inference System (ANFIS) in predicting the behavior of the PEMFC’s Membrane Electrode Assembly (MEA). The models showed promising results with high accuracy.

Anahtar Kelimeler

Artificial intelligence, electrochemical devices, energy conversion, fuel cells

Teşekkür

Authors would you like to thank UNIDO-ICHET and Prof. Mehmet Suha Yazıcı for providing support to this study.

Kaynakça

• V. Lakshminarayanan and P. Karthikeyan, Performance enhancement of interdigitated flow channel of PEMFC by scaling up study. Energy Sources Part A: Recovery, Utilization, and Environmental Effects, 42 (14), 1785–1796, 2019. https://doi.org/10.1080/15567036.2019.1604889.
• M. Wei, S. J. Smith and M. D. Sohn, Experience curve development and cost reduction disaggregation for fuel cell markets in Japan and the US. Applied Energy, 191, 346-357, 2017. https://doi.org/10.1016/j.apenergy.2017.01.056.
• U.S. Department of Energy, 2019 Annual Progress Report, DOE Hydrogen and Fuel Cells Program. https://www.hydrogen.energy.gov/library/annual-progress/annual_progress19, Accessed 10 January 2024.
• X. Lü, Y. Qu, Y. Wang, C. Qin and G. Liu, A comprehensive review on hybrid power system for PEMFC-HEV: Issues and strategies. Energy Conversion and Management, 171, 1273-1291, 2018. https://doi.org/10.1016/j.enconman.2018.06.065.
• L. James and D. Andrew, Fuel Cell Systems Explained. Wiley, New York, 2003.
• C. Spiegel, PEM Fuel Cell Modeling and Simulation Using MATLAB. Academic Press, 2008.
• Z. Li, S. Jemei, R. Gouriveau, D. Hissel and N. Zerhouni, Remaining useful life estimation for PEMFC in dynamic operating conditions. Proceedings of IEEE Vehicle Power and Propulsion Conference (VPPC), pp. 1-6, Hangzhou, China, 2016.
• Y. Vural, D. B. Ingham, and M. Pourkashanian, Performance prediction of a proton exchange membrane fuel cell using the ANFIS model. International Journal of Hydrogen Energy, 34 (22), 9181-9187, 2009. https://doi.org/10.1016/j.ijhydene.2009.08.096.
• M. Seyhan, Y. E. Akansu, M. Murat, Y. Korkmaz, and S. O. Akansu, Performance prediction of PEM fuel cell with wavy serpentine flow channel by using artificial neural network. International Journal of Hydrogen Energy, 42 (40), 25619-25629, 2017. https://doi.org/10.1016/j.ijhydene.2017.04.001.
• M. Mehrpooya, B. Ghorbani, B. Jafari, M. Aghbashlo and M. Pouriman, Modeling of a single cell micro proton exchange membrane fuel cell by a new hybrid neural network method. Thermal Science and Engineering Progress, 7, 8-19, 2018. https://doi.org/10.1016/j.tsep.2018.04.012.
• X. Wu, X. Zhu, G. Cao and H. Tu, Nonlinear modeling of a SOFC stack based on ANFIS identification. Simulation Modelling Practice and Theory, 16 (4), 399-409, 2008. https://doi.org/10.1016/j.simpat.2008.01.004.
• F. Barbir, PEM Fuel Cells: Theory and Practice. Academic Press, 2005.
• Q. Li, W. Chen, Y. Wang, J. Jia and M. Han, Nonlinear robust control of proton exchange membrane fuel cell by state feedback exact linearization. Journal of Power Sources, 194 (1), 338-348, 2009. https://doi.org/10.1016/j.jpowsour.2009.04.077.
• D. Zhou, F. Gao, E. Breaz, A. Ravey, A. Miraoui and K. Zhang, Dynamic phenomena coupling analysis and modeling of proton exchange membrane fuel cells. IEEE Transactions on Energy Conversion, 31 (4), 1399-1412, 2016. https://doi.org/10.1109/TEC.2016.2587162.
• D. Yu and S. Yuvarajan, A novel circuit model for PEM fuel cells. Proceedings of Nineteenth Annual IEEE Applied Power Electronics Conference and Exposition, pp. 362-366, Anaheim, CA, USA, 2004.
• J. Jia, Y. Wang, M. Han and Y.T. Cham, Dynamic characteristic study of proton exchange membrane fuel cell. Proceedings of IEEE Sustainable Energy Technologies, pp. 24-27 Singapore, 2008.
• G. S. Avcioglu, B. Ficicilar and I. Eroglu, Effect of PTFE nanoparticles in catalyst layer with high Pt loading on PEM fuel cell performance. International Journal of Hydrogen Energy, 41(23), 10010-10020, 2016. https://doi.org/10.1016/j.ijhydene.2016.03.048.
• N. M. Zahari and A. A. Aziz, Effect of platinum catalyst loading on membrane electrode assembly (MEA) in proton exchange membrane fuel cell (PEMFC). 10th IEEE Int. Conf. Semiconductor Electronics (ICSE), pp. 669-673, Kuala Lumpur, Malaysia, 19-21 September 2012.
• Y. Wang, K. S. Chen, J. Mishler, S. C. Cho and X. C. Adroher, A review of polymer electrolyte membrane fuel cells: Technology, applications, and needs on fundamental research. Applied Energy, Volume 88(4), 981-1007, 2011. https://doi.org/10.1016/j.apenergy.2010.09.030.
• C. Wang, M. H. Nehrir and S. R. Shaw, Dynamic models and model validation for PEM fuel cells using electrical circuits. IEEE Transactions on Energy Conversion, 20(2), 442-451, 2005, https://doi.org/10.1109/TEC.2004.842357.
• D. Zhou, Y. Wu, F. Gao, E. Breaz, A. Ravey and A. Miraoui, Degradation prediction of PEM fuel cell stack based on multi-physical aging model with particle filter approach. IEEE Industry Applications Society Annual Meeting, pp, 1-8, Portland, USA, 02-06 October 2016.
• E. Dursun, G. Y. Ozalp and O. Kilic, Experimental Analysis and Electrical Modeling of PEM Fuel Cell's MEA. International Review Of Electrical Engineering-Iree Part:A, 5, 1595-1599, 2010.
• L. Khotseng, Fuel Cell Thermodynamics. in: P. Vizureanu, (Eds.), Thermodynamics and Energy Engineering, IntechOpen, pp, 1-17, 2019.
• A. H. Abdulwahid and S. Wang, A new protection approach for microgrid based upon combined ANFIS with Symmetrical Components. 2016 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC), pp, 1984-1989, Xi'an, China, 2016.
• S. Wayan and M.A. Kemal, Modeling of Tropospheric Delays Using ANFIS. Springer, Switzerland, 2016.
• B. B. Jovanovic, I. S. Reljin and B. D. Reljin, Modified ANFIS architecture - improving efficiency of ANFIS technique. 7th Seminar on Neural Network Applications in Electrical Engineering, pp, 215-220 Belgrade, Serbia, 2004.
• M Sugeno and G.T Kang, Structure identification of fuzzy model. Fuzzy Sets and Systems, 28(1), 15-33, 1988, https://doi.org/10.1016/0165-0114(88)90113-3.
• M. Alakhras, M. Oussalah and M. Hussein, ANFIS: General description for modeling dynamic objects. IEEE/ACS 12th International Conference of Computer Systems and Applications (AICCSA), pp, 1-8, Marrakech, Morocco, 2015.
• J.S.R. Jang, Input selection for ANFIS Learning. IEEE Int. Conf. Fuzzy Systems, pp. 1493-1499, New Orleans, LA, USA, 1996.
• S. Sumathi and S. Paneerselvam, Computational intelligence paradigms: theory and applications using MATLAB. CRC Press, Florida, 2010.