State-of-the-art in the proposed field of research and survey of the relevant literature¶
In the context of soc fuel cells, building first principle models requires very precise knowledge about the soc microstructure, its porosity, electrode thickness, structure of the individual layers, and other factors (Zou, Manzie, and Nesic 2015). Models range from very simple calculations of the specific reactions, without detailed consideration of the cell microstructure and kinetics (Badur et al. 2018), detailed information on mass transport, heterogeneous chemistry and porous media transport (Kupecki et al. 2018) all the way to very detailed 2D-models for reversibly operated and industrial scale solid oxide cells (Subotić et al. 2020).
Various fault modes have profound influence on the behaviour of soc systems too. Typical cases include carbon depositions, sulphur poisoning, or nickel reoxidation on the anode side (Moçoteguy and Brisse 2013). These mechanisms can bring about the irreversible deterioration of the cell’s electrochemical and micro-structural performance, thus significantly shortening its life-time.
For accurate implementation of the above listed approaches, accelerated and long term testing is usually needed. Such experiments allow very detailed chemical and electrochemical characterisations of soc systems. However, experimental investigations are time-consuming and expensive. There are very few published results in the field of soc. Researchers from FZ Jülich as one of the pioneers in the field of sofc among the first performed almost a decade long experiment (Blum et al. 2016). Similar results but more detailed analysis on almost 30,000 hours long experiment are also available (Menzler, Sebold, and Guillon 2017). In the area of soec, the available results are even scarcer (Yan et al. 2017; Tietz et al. 2012)
In the above results, the characterisation of soc systems was almost exclusively done by fairly straightforward approaches such as polarisation curves, eis or drt. There have been only a limited number of cases addressing the actual non-linear nature of these systems (Subotić et al. 2021, 2020) A logical continuation is the application of various data-driven techniques in order to characterise and predict the performance of soc systems. An overview of the published results in the field of soc systems is shown in Table 1. It is clear that electrolyses, i.e. soecs and dual-mode (reversible soc) systems are underrepresented.
soc systems
SOEC
SOFC
catalyst
rSOC
control
(Jurado 2003; X.-J. Wu et al. 2007; Huo et al. 2008; Hajimolana et al. 2013; Marchetti et al. 2011) S
design parameter o ptimization
(Nassef et al. 2019; Song et al. 2020; Bozorgmehri and Hamedi 2012; Yan et al. 2019)
des ign/process parameter o ptimization
(Le, Nguyen, and Nguyen 2019)
fault detection
(Wu and Ye 2016; Zhang et al. 2018; Pahon et al. 2016)
mu lti-physics model enhancement
(Grondin et al. 2012)
performance o ptimization
(Xu et al. 2020) S
performance prediction
(Zahadat and Milewski 2015; Han et al. 2019; Zhang et al. 2017)
(Arriagada 2002; Marra et al. 2013; X.-j. Wu et al. 2007; Milewski and Świrski 2009; Chaichana et al. 2011; Baldinelli et al. 2018; Chakraborty 2009; Entchev and Yang 2007; Sorrentino et al. 2014; Gebregergis et al. 2008; Chen, Chen, and Zhang 2019; Song et al. 2021)
(Günay et al. 2011)
p erformance/ degradation prediction
(Dolenc et al. 2017)
process parameter o ptimisation
(Ahn et al. 2019) S
(Salehi and Gh olaminezhad 2018)
[tab:soa]
Preliminary results¶
Members of both teams have a substantial track record in the field of soc electro-chemical characterisation (Königshofer, Pongratz, et al. 2021; Höber et al. 2021), modelling (Žnidarič et al. 2021) and performing fault detection of various soc based systems (Königshofer, Boškoski, et al. 2021; Nusev et al. 2021). In the last year tug and jsi teams have carried out preliminary investigations on using various data driven techniques on soc systems.
tug team members have successfully implemented vanilla deep-neural networks for modelling soc systems (Mütter 2021; Subotić, Eibl, and Hochenauer 2021). The results show very good potential to predict sofc performance by modelling polarisation curves and eis characteristics.
Additionally, the jsi team has addressed the issues of stochastic model parameters of lumped sofc models (Žnidarič et al. 2021). Using the vb approach it was shown that the parameters of the resulting lumped model have indeed stochastic nature. As a result, each frequency point of the obtained impedance curves is described with its own posterior distribution that accommodates the underlying uncertainties (both measurement and system’s). Despite these promising results, the issues of explainability and more importantly incorporating experts knowledge are still open issues.
Ahn, Ji Ho, Min Jae Kim, Yeon Woo Cho, and Tong Seop Kim. 2019. “A Quadruple Power Generation System for Very High Efficiency and Its Performance Optimization Using an Artificial Intelligence Method.” Applied Thermal Engineering 168: 114861. https://doi.org/10.1016/j.applthermaleng.2019.114861.
Arriagada, J. 2002. “Artificial Neural Network Simulator for Sofc Performance Prediction.” Journal of Power Sources 112 (1): 54–60. https://doi.org/10.1016/s0378-7753(02)00314-2.
Badur, Janusz, Marcin Lemański, Tomasz Kowalczyk, Paweł Ziółkowski, and Sebastian Kornet. 2018. “Zero-Dimensional Robust Model of an SOFC with Internal Reforming for Hybrid Energy Cycles.” Energy 158: 128–38. https://doi.org/10.1016/j.energy.2018.05.203.
Baldinelli, Arianna, Linda Barelli, Gianni Bidini, Fabio Bonucci, and Feride Iskenderoğlu. 2018. “Regarding Solid Oxide Fuel Cells Simulation Through Artificial Intelligence: A Neural Networks Application.” Applied Sciences 9 (1): 51. https://doi.org/10.3390/app9010051.
Blum, Ludger, L. G. J. de Haart, Jürgen Malzbender, Nikolaos Margaritis, and Norbert H. Menzler. 2016. “Anode-Supported Solid Oxide Fuel Cell Achieves 70 000 Hours of Continuous Operation.” Energy Technology 4 (8): 939–42. https://doi.org/10.1002/ente.201600114.
Bozorgmehri, S., and M. Hamedi. 2012. “Modeling and Optimization of Anode-Supported Solid Oxide Fuel Cells on Cell Parameters via Artificial Neural Network and Genetic Algorithm.” Fuel Cells 12 (1): 11–23. https://doi.org/10.1002/fuce.201100140.
Chaichana, Kattiyapon, Yaneeporn Patcharavorachot, Bhawasut Chutichai, Dang Saebea, Suttichai Assabumrungrat, and Amornchai Arpornwichanop. 2011. “Neural Network Hybrid Model of a Direct Internal Reforming Solid Oxide Fuel Cell.” International Journal of Hydrogen Energy 37 (3): 2498–2508. https://doi.org/10.1016/j.ijhydene.2011.10.051.
Chakraborty, Uday Kumar. 2009. “Static and Dynamic Modeling of Solid Oxide Fuel Cell Using Genetic Programming.” Energy 34 (6): 740–51. https://doi.org/10.1016/j.energy.2009.02.012.
Chen, Jinwei, Yao Chen, and Huisheng Zhang. 2019. “Study on Fuel Utilization Dynamic Model of a Sofc-Gt Hybrid System Based on Deep Learning Technique.” E3S Web of Conferences 113: 02010. https://doi.org/10.1051/e3sconf/201911302010.
Dolenc, B., P. Boškoski, M. Stepančič, A. Pohjoranta, and Đ. Juričić. 2017. “State of Health Estimation and Remaining Useful Life Prediction of Solid Oxide Fuel Cell Stack.” Energy Conversion and Management 148: 993–1002. https://doi.org/10.1016/j.enconman.2017.06.041.
Entchev, Evgueniy, and Libing Yang. 2007. “Application of Adaptive Neuro-Fuzzy Inference System Techniques and Artificial Neural Networks to Predict Solid Oxide Fuel Cell Performance in Residential Microgeneration Installation.” Journal of Power Sources 170 (1): 122–29. https://doi.org/10.1016/j.jpowsour.2007.04.015.
Gebregergis, A., P. Pillay, D. Bhattacharyya, and R. Rengaswemy. 2008. “Solid Oxide Fuel Cell Modeling.” IEEE Transactions on Industrial Electronics 56 (1): 139–48. https://doi.org/10.1109/tie.2008.2009516.
Grondin, D., J. Deseure, P. Ozil, J.-P. Chabriat, B. Grondin-Perez, and A. Brisse. 2012. “Solid Oxide Electrolysis Cell 3D Simulation Using Artificial Neural Network for Cathodic Process Description.” Chemical Engineering Research and Design 91 (1): 134–40. https://doi.org/10.1016/j.cherd.2012.06.003.
Günay, M. Erdem, Fatma Akpinar, Z. Ilsen Onsan, and Ramazan Yildirim. 2011. “Investigation of Water Gas-Shift Activity of Pt–Mox–Ceo2/Al2o3 (M = K, Ni, Co) Using Modular Artificial Neural Networks.” International Journal of Hydrogen Energy 37 (3): 2094–2102. https://doi.org/10.1016/j.ijhydene.2011.09.148.
Hajimolana, S. A., S. M. Tonekabonimoghadam, M. A. Hussain, M. H. Chakrabarti, N. S. Jayakumar, and M. A. Hashim. 2013. “Thermal Stress Management of a Solid Oxide Fuel Cell Using Neural Network Predictive Control.” Energy 62: 320–29. https://doi.org/10.1016/j.energy.2013.08.031.
Han, Jing, Xi Wang, Limei Yan, and Aida Dahlak. 2019. “Modelling the Performance of an Soec by Optimization of Neural Network with Mpso Algorithm.” International Journal of Hydrogen Energy 44 (51): 27947–57. https://doi.org/10.1016/j.ijhydene.2019.09.055.
Höber, Michael, Benjamin Königshofer, Philipp Wachter, Gjorgji Nusev, Pavle Boskoski, Christoph Hochenauer, and Vanja Subotić. 2021. “Holistic Approach to Design, Test, and Optimize Stand-Alone Sofc-Reformer Systems.” Processes 9 (2): 348. https://doi.org/10.3390/pr9020348.
Huo, Hai-Bo, Xin-Jian Zhu, Wan-Qi Hu, Heng-Yong Tu, Jian Li, and Jie Yang. 2008. “Nonlinear Model Predictive Control of Sofc Based on a Hammerstein Model.” Journal of Power Sources 185 (1): 338–44. https://doi.org/10.1016/j.jpowsour.2008.06.064.
Jurado, Francisco. 2003. “Power Supply Quality Improvement with a Sofc Plant by Neural-Network-Based Control.” Journal of Power Sources 117 (1-2): 75–83. https://doi.org/10.1016/s0378-7753(03)00309-4.
Königshofer, Benjamin, Pavle Boškoski, Gjorgji Nusev, Markus Koroschetz, Martin Hochfellner, Marcel Schwaiger, :raw-latex:`DJ`ani Juričić, Christoph Hochenauer, and Vanja Subotić. 2021. “Performance Assessment and Evaluation of Soc Stacks Designed for Application in a Reversible Operated 150 kW rSOC Power Plant.” Applied Energy 283: 116372. https://doi.org/10.1016/j.apenergy.2020.116372.
Königshofer, Benjamin, Gernot Pongratz, Gjorgji Nusev, Pavle Boškoski, Michael Höber, :raw-latex:`DJ`ani Juričić, Mihails Kusnezoff, et al. 2021. “Development of Test Protocols for Solid Oxide Electrolysis Cells Operated Under Accelerated Degradation Conditions.” Journal of Power Sources 497: 229875. https://doi.org/10.1016/j.jpowsour.2021.229875.
Kupecki, Jakub, Davide Papurello, Andrea Lanzini, Yevgeniy Naumovich, Konrad Motylinski, Marcin Blesznowski, and Massimo Santarelli. 2018. “Numerical Model of Planar Anode Supported Solid Oxide Fuel Cell Fed with Fuel Containing H2s Operated in Direct Internal Reforming Mode.” Applied Energy 230: 1573–84. https://doi.org/10.1016/j.apenergy.2018.09.092.
Le, Minh-Vien, Tuan-Anh Nguyen, and T.-Anh-Nga Nguyen. 2019. “Modeling and Optimization of the Bscf-Based Single-Chamber Solid Oxide Fuel Cell by Artificial Neural Network and Genetic Algorithm.” Journal of Chemistry 2019: 1–9. https://doi.org/10.1155/2019/7828019.
Marchetti, A., A. Gopalakrishnan, B. Chachuat, D. Bonvin, L. Tsikonis, A. Nakajo, Z. Wuillemin, and J. Van herle. 2011. “Robust Real-Time Optimization of a Solid Oxide Fuel Cell Stack.” Journal of Fuel Cell Science and Technology 8 (5). https://doi.org/10.1115/1.4003976.
Marra, Dario, Marco Sorrentino, Cesare Pianese, and Boris Iwanschitz. 2013. “A Neural Network Estimator of Solid Oxide Fuel Cell Performance for on-Field Diagnostics and Prognostics Applications.” Journal of Power Sources 241: 320–29. https://doi.org/10.1016/j.jpowsour.2013.04.114.
Menzler, Norbert H., Doris Sebold, and Olivier Guillon. 2017. “Post-Test Characterization of a Solid Oxide Fuel Cell Stack Operated for More Than 30,000 Hours: The Cell.” Journal of Power Sources 374: 69–76. https://doi.org/10.1016/j.jpowsour.2017.11.025.
Milewski, Jarosław, and Konrad Świrski. 2009. “Modelling the Sofc Behaviours by Artificial Neural Network.” International Journal of Hydrogen Energy 34 (13): 5546–53. https://doi.org/10.1016/j.ijhydene.2009.04.068.
Moçoteguy, Philippe, and Annabelle Brisse. 2013. “A Review and Comprehensive Analysis of Degradation Mechanisms of Solid Oxide Electrolysis Cells.” International Journal of Hydrogen Energy 38 (36): 15887–15902. https://doi.org/10.1016/j.ijhydene.2013.09.045.
Mütter, Felix. 2021. “Artificial Neural Network Modeling and Genetic Algorithm Optimization of Process Parameters of Solid Oxide Fuel Cell Systems.” Master’s thesis, Inffeldgasse 25/B, 8010 Graz, Austria: Graz University of Technology.
Nassef, Ahmed M., Ahmed Fathy, Enas Taha Sayed, Mohammad Ali Abdelkareem, Hegazy Rezk, Waqas Hassan Tanveer, and A. G. Olabi. 2019. “Maximizing Sofc Performance Through Optimal Parameters Identification by Modern Optimization Algorithms.” Renewable Energy 138: 458–64. https://doi.org/10.1016/j.renene.2019.01.072.
Nusev, Gjorgji, Bertrand Morel, Julie Mougin, :raw-latex:`DJ`ani Juričić, and Pavle Boškoski. 2021. “Condition Monitoring of Solid Oxide Fuel Cells by Fast Electrochemical Impedance Spectroscopy: A Case Example of Detecting Deficiencies in Fuel Supply.” Journal of Power Sources 489: 229491. https://doi.org/10.1016/j.jpowsour.2021.229491.
Pahon, E., N. Yousfi Steiner, S. Jemei, D. Hissel, M. C. Péra, K. Wang, and P. Moçoteguy. 2016. “Solid Oxide Fuel Cell Fault Diagnosis and Ageing Estimation Based on Wavelet Transform Approach.” International Journal of Hydrogen Energy 41 (31): 13678–87. https://doi.org/10.1016/j.ijhydene.2016.06.143.
Salehi, Zahra, and Iman Gholaminezhad. 2018. “Multi-Objective Modeling, Uncertainty Analysis, and Optimization of Reversible Solid Oxide Cells.” International Journal of Energy and Environmental Engineering 9 (3): 295–304. https://doi.org/10.1007/s40095-018-0269-5.
Song, Changhee, Sanghoon Lee, Bonhyun Gu, Ikwhang Chang, Gu Young Cho, Jong Dae Baek, and Suk Won Cha. 2020. “A Study of Anode-Supported Solid Oxide Fuel Cell Modeling and Optimization Using Neural Network and Multi-Armed Bandit Algorithm.” Energies 13 (7): 1621. https://doi.org/10.3390/en13071621.
Song, Shaohui, Xingyu Xiong, Xin Wu, and Zhenzhong Xue. 2021. “Modeling the Sofc by Bp Neural Network Algorithm.” International Journal of Hydrogen Energy 46 (38): 20065–77. https://doi.org/10.1016/j.ijhydene.2021.03.132.
Sorrentino, M., D. Marra, C. Pianese, M. Guida, F. Postiglione, K. Wang, and A. Pohjoranta. 2014. “On the Use of Neural Networks and Statistical Tools for Nonlinear Modeling and on-Field Diagnosis of Solid Oxide Fuel Cell Stacks.” Energy Procedia 45: 298–307. https://doi.org/10.1016/j.egypro.2014.01.032.
Subotić, Vanja, Michael Eibl, and Christoph Hochenauer. 2021. “Artificial Intelligence for Time-Efficient Prediction and Optimization of Solid Oxide Fuel Cell Performances.” Energy Conversion and Management 230: 113764. https://doi.org/https://doi.org/10.1016/j.enconman.2020.113764.
Subotić, Vanja, Philipp Harter, Mihails Kusnezoff, Teko W. Napporn, Hartmuth Schroettner, and Christoph Hochenauer. 2021. “Identification of Carbon Deposition and Its Removal in Solid Oxide Fuel Cells by Applying a Non-Conventional Diagnostic Tool.” Sustainable Energy & Fuels 5 (7): 2065–76. https://doi.org/10.1039/d0se01914c.
Subotić, Vanja, Norbert H. Menzler, Vincent Lawlor, Qingping Fang, Stefan Pofahl, Philipp Harter, Hartmuth Schroettner, and Christoph Hochenauer. 2020. “On the Origin of Degradation in Fuel Cells and Its Fast Identification by Applying Unconventional Online-Monitoring Tools.” Applied Energy 277: 115603. https://doi.org/10.1016/j.apenergy.2020.115603.
Subotić, Vanja, Thomas Thaller, Benjamin Königshofer, Norbert H. Menzler, Edith Bucher, Andreas Egger, and Christoph Hochenauer. 2020. “Performance Assessment of Industrial-Sized Solid Oxide Cells Operated in a Reversible Mode: Detailed Numerical and Experimental Study.” International Journal of Hydrogen Energy 45 (53): 29166–85. https://doi.org/10.1016/j.ijhydene.2020.07.165.
Tietz, F., D. Sebold, A. Brisse, and J. Schefold. 2012. “Degradation Phenomena in a Solid Oxide Electrolysis Cell After 9000 H of Operation.” Journal of Power Sources 223: 129–35. https://doi.org/10.1016/j.jpowsour.2012.09.061.
Wu, XiaoJuan, and Qianwen Ye. 2016. “Fault Diagnosis and Prognostic of Solid Oxide Fuel Cells.” Journal of Power Sources 321: 47–56. https://doi.org/10.1016/j.jpowsour.2016.04.080.
Wu, Xiao-juan, Xin-jian Zhu, Guang-yi Cao, and Heng-yong Tu. 2007. “Nonlinear Modelling of a Sofc Stack by Improved Neural Networks Identification.” Journal of Zhejiang University-SCIENCE A 8 (9): 1505–9. https://doi.org/10.1631/jzus.2007.a1505.
Wu, Xiao-Juan, Xin-Jian Zhu, Guang-Yi Cao, and Heng-Yong Tu. 2007. “Predictive Control of Sofc Based on a Ga-Rbf Neural Network Model.” Journal of Power Sources 179 (1): 232–39. https://doi.org/10.1016/j.jpowsour.2007.12.036.
Xu, Haoran, Jingbo Ma, Peng Tan, Bin Chen, Zhen Wu, Yanxiang Zhang, Huizhi Wang, Jin Xuan, and Meng Ni. 2020. “Towards Online Optimisation of Solid Oxide Fuel Cell Performance: Combining Deep Learning with Multi-Physics Simulation.” Energy and AI 1: 100003. https://doi.org/10.1016/j.egyai.2020.100003.
Yan, Y., Q. Fang, L. Blum, and W. Lehnert. 2017. “Performance and Degradation of an Soec Stack with Different Cell Components.” Electrochimica Acta 258: 1254–61. https://doi.org/10.1016/j.electacta.2017.11.180.
Yan, Z., A. He, S. Hara, and N. Shikazono. 2019. “Modeling of Solid Oxide Fuel Cell (Sofc) Electrodes from Fabrication to Operation: Microstructure Optimization via Artificial Neural Networks and Multi-Objective Genetic Algorithms.” Energy Conversion and Management 198: 111916. https://doi.org/10.1016/j.enconman.2019.111916.
Zahadat, Pouya, and Jaroslaw Milewski. 2015. “Modeling Electrical Behavior of Solid Oxide Electrolyzer Cells by Using Artificial Neural Network.” International Journal of Hydrogen Energy 40 (23): 7246–51. https://doi.org/10.1016/j.ijhydene.2015.04.042.
Zhang, Caizhi, Qinglin Liu, Qi Wu, Yifeng Zheng, Juan Zhou, Zhengkai Tu, and Siew Hwa Chan. 2017. “Modelling of Solid Oxide Electrolyser Cell Using Extreme Learning Machine.” Electrochimica Acta 251: 137–44. https://doi.org/10.1016/j.electacta.2017.08.113.
Zhang, Zehan, Shuanghong Li, Yawen Xiao, and Yupu Yang. 2018. “Intelligent Simultaneous Fault Diagnosis for Solid Oxide Fuel Cell System Based on Deep Learning.” Applied Energy 233-234: 930–42. https://doi.org/10.1016/j.apenergy.2018.10.113.
Žnidarič, Luka, Gjorgji Nusev, Bertrand Morel, Julie Mougin, :raw-latex:`DJ`ani Juričić, and Pavle Boškoski. 2021. “Evaluating Uncertainties in Electrochemical Impedance Spectra of Solid Oxide Fuel Cells.” Applied Energy 298: 117101. https://doi.org/10.1016/j.apenergy.2021.117101.
Zou, Changfu, Chris Manzie, and Dragan Nesic. 2015. “A Framework for Simplification of Pde-Based Lithium-Ion Battery Models.” IEEE Transactions on Control Systems Technology 24 (5): 1594–1609. https://doi.org/10.1109/tcst.2015.2502899.