Machine learning-enabled design and lifetime prediction of solid oxide fuel cells

Abstract

This review covers the latest advancements in the application of machine learning (ML) to the design optimization, failure analysis, and lifetime prediction of solid oxide fuel cells (SOFCs). At the material design level, ML accelerates the screening of perovskite materials and optimizes microstructures, significantly enhancing electrode performance. In stack structural design, ML aids multiphysics-coupled analysis to optimize flow channel layouts and thermal management. For electrode degradation issues such as cathode chromium poisoning and anode carbon deposition, ML models enable precise diagnosis and prediction by analyzing experimental data. Furthermore, ML techniques demonstrate high efficiency and adaptability in stack system fault diagnosis and lifetime prediction, offering a new paradigm for SOFC reliability research. Despite challenges such as data scarcity and model complexity, the integration of ML with physical models and the development of multiscale approaches provide critical support for the commercialization of SOFCs.

Keywords

Solid oxide fuel cell / machine learning / design and optimization / failure diagnosis / lifetime prediction

References

[1] Park S,Gorte RJ.Direct oxidation of hydrocarbons in a solid-oxide fuel cell.Nature2000;404:265-7

[2] Duan C,Zhu H.Highly efficient reversible protonic ceramic electrochemical cells for power generation and fuel production.Nat Energy2019;4:230-40

[3] Wachsman ED.Lowering the temperature of solid oxide fuel cells.Science2011;334:935-9

[4] Zakaria Z,Abu Hassan SH.A review of solid oxide fuel cell component fabrication methods toward lowering temperature.Int J Energy Res2020;44:594-611

[5] Vinchhi P,Chaudhary K.Recent advances on electrolyte materials for SOFC: a review.Inorg Chem Commun2023;152:110724

[6] Rafique M,Shahid Rafique M,Nabi G.Material and method selection for efficient solid oxide fuel cell anode: recent advancements and reviews.Int J Energy Res2019;43:2423-46

[7] Ahmad MZ,Chen RS,Hazan R.Review on recent advancement in cathode material for lower and intermediate temperature solid oxide fuel cells application.Int J Hydrogen Energy2022;47:1103-20

[8] Dhanasekaran A,Omeiza LA.Computational fluid dynamics for protonic ceramic fuel cell stack modeling: a brief review.Energies2023;16:208

[9] Yokokawa H,Yoda M.Achievements of NEDO Durability Projects on SOFC stacks in the light of physicochemical mechanisms.Fuel Cells2019;19:311-39

[10] Xu Y,Chi B.Technological limitations and recent developments in a solid oxide electrolyzer cell: a review.Int J Hydrogen Energy2024;50:548-91

[11] Irvine JTS,Verbraeken MC,Graves C.Evolution of the electrochemical interface in high-temperature fuel cells and electrolysers.Nat Energy2016;1:15014

[12] Chen K.Surface segregation in solid oxide cell oxygen electrodes: phenomena, mitigation strategies and electrochemical properties.Electrochem Energ Rev2020;3:730-65

[13] Khan M,Knibbe R.Air electrodes and related degradation mechanisms in solid oxide electrolysis and reversible solid oxide cells.Renew Sustaina Energy Rev2021;143:110918

[14] Lin C,Chyou Y.Thermal stress analysis of a planar SOFC stack.J Power Sources2007;164:238-51

[15] Brus G,Iwai H,Yoshida H.Tortuosity of an SOFC anode estimated from saturation currents and a mass transport model in comparison with a real micro-structure.Solid State Ionics2014;265:13-21

[16] Zhang Y,Guan D.Thermal-expansion offset for high-performance fuel cell cathodes.Nature2021;591:246-51

[17] Choi S,Liang Y.Exceptional power density and stability at intermediate temperatures in protonic ceramic fuel cells.Nat Energy2018;3:202-10

[18] Chen Y,Tang Y.A robust fuel cell operated on nearly dry methane at 500 °C enabled by synergistic thermal catalysis and electrocatalysis.Nat Energy2018;3:1042-50

[19] Machado M,Bernadet L.Functional thin films as cathode/electrolyte interlayers: a strategy to enhance the performance and durability of solid oxide fuel cells.J Mater Chem A2022;10:17317-25

[20] Pirou S,Brodersen K.Production of a monolithic fuel cell stack with high power density.Nat Commun2022;13:1263 PMCID:PMC8913829

[21] Jeong H,Son J.Advancing towards ready-to-use solid oxide fuel cells: 5 minute cold start-up with high-power performance.J Mater Chem A2023;11:7415-21

[22] Gao Z,Miller EC,Barnett SA.A perspective on low-temperature solid oxide fuel cells.Energy Environ Sci2016;9:1602-44

[23] Qiu P,Liu B,Li J.Materials of solid oxide electrolysis cells for H₂O and CO₂ electrolysis: a review.J Adv Ceram2023;12:1463-510

[24] Yang Y,Yan M.A review on the preparation of thin-film YSZ electrolyte of SOFCs by magnetron sputtering technology.Sep Purif Technol2022;298:121627

[25] Hwang S,Kang G.A hydrogel-assisted GDC chemical diffusion barrier for durable solid oxide fuel cells.J Mater Chem A2021;9:11683-90

[26] Menzler NH,Sohn YJ.Post-test characterization of a solid oxide fuel cell after more than 10 years of stack testing.J Power Sources2020;478:228770

[27] Fang Q,Stolten D.Electrochemical performance and degradation analysis of an SOFC short stack following operation of more than 100,000 hours.J Electrochem Soc2019;166:F1320-5

[28] Khan MZ,Song R,Lee S.A simplified approach to predict performance degradation of a solid oxide fuel cell anode.J Power Sources2018;391:94-105

[29] Gallo M,Mougin J,Pianese C.Coupling electrochemical impedance spectroscopy and model-based aging estimation for solid oxide fuel cell stacks lifetime prediction.Appl Energy2020;279:115718

[30] Wang Y.A bi-objective AHP-MINLP-GA approach for flexible alternative supplier selection amid the COVID-19 pandemic.Soft Comput Lett2021;3:100016

[31] Xue F,Cheng T.Phase-field modeling of crack growth and mitigation in solid oxide cells.Int J Hydrogen Energy2023;48:9845-60

[32] Su Y,Jiao Z.A novel multi-physics coupled heterogeneous single-cell numerical model for solid oxide fuel cell based on 3D microstructure reconstructions.Energy Environ Sci2022;15:2410-24

[33] Monaco F,Vulliet J.Degradation of Ni-YSZ electrodes in solid oxide cells: impact of polarization and initial microstructure on the Ni evolution.J Electrochem Soc2019;166:F1229-42

[34] Yuan B,Tang C,Ye S.How AI guided the development of green hydrogen production: in the case of solid oxide electrolysis cell?.J Mater Inf2025;5:25

[35] Liu B,Shaham S,Farokhi F.When machine learning meets privacy: a survey and outlook.ACM Comput Surv2022;54:1-36

[36] Lu X,Li J.FIND: a forward–inverse navigation and discovery platform for hydrogen storage alloys powered by data-driven machine learning.J Mater Inf2025;5:48

[37] Di H,Xiao M.Exploring hydration of air electrodes for protonic ceramic cells: a review.Chem Eng J2025;507:160759

[38] Xiong X,Ma G.Three-dimensional multi-physics modelling and structural optimization of SOFC large-scale stack and stack tower.Int J Hydrogen Energy2023;48:2742-61

[39] AK, Pollok, S, Hagen, A. Degradation studies using machine learning on novel solid oxide cell database.Fuel Cells2021;21:566-76

[40] Li H,Lyu Z,Sun K.An agile layer-resolved SOFC stack model using physics-informed neural network.Int J Hydrogen Energy2024;54:586-600

[41] Gong W,Yang J,Jian L.Parameter identification of an SOFC model with an efficient, adaptive differential evolution algorithm.Int J Hydrogen Energy2014;39:5083-96

[42] Jacobs R,Abernathy H.Machine learning design of perovskite catalytic properties.Adv Energy Mater2024;14:2303684

[43] Sciazko A,Nakamura A,Hara T.3D microstructures of solid oxide fuel cell Ni-YSZ anodes with carbon deposition.Chem Eng J2023;460:141680

[44] Zhang G,Lin L,Ke Z.Fast ionic conduction and boosted cathode reaction enabled by BSCF–YSZ for LT-SOFC application.J Mater Sci Mater Electron2023;34:11355

[45] Zhai S,Cui P.A combined ionic Lewis acid descriptor and machine-learning approach to prediction of efficient oxygen reduction electrodes for ceramic fuel cells.Nat Energy2022;7:866-75

[46] Wang N,Tang C.Machine-learning-accelerated development of efficient mixed protonic-electronic conducting oxides as the air electrodes for protonic ceramic cells.Adv Mater2022;34:e2203446

[47] Zhang Q,Ding J.Hole conductivity in the electrolyte of proton-conducting SOFC: mathematical model and experimental investigation.J Alloys Compd2019;801:343-51

[48] Wang N,Zheng F.Machine‐learning assisted screening proton conducting Co/Fe based oxide for the air electrode of protonic solid oxide cell.Adv Funct Mater2024;34:2309855

[49] Tang C,Zhang X.Rationally designed air electrode boosting electrochemical performance of protonic ceramic cells.Adv Energy Mater2025;15:2402654

[50] Niu Z,Wu B.π Learning: a performance‐informed framework for microstructural electrode design.Adv Energy Mater2023;13:2300244

[51] Peng X.Unraveling impacts of polycrystalline microstructures on ionic conductivity of ceramic electrolytes by computational homogenization and machine learning.J Appl Phys2024;136:105101

[52] Yang K,Wang Y.Machine-learning-assisted prediction of long-term performance degradation on solid oxide fuel cell cathodes induced by chromium poisoning.J Mater Chem A2022;10:23683-90

[53] Yu F,Zhang Y.New insights into carbon deposition mechanism of nickel/yttrium-stabilized zirconia cermet from methane by in situ investigation.Appl Energy2019;256:113910

[54] Lyu Z,Sciazko A.Co‐generation of electricity and chemicals from methane using direct internal reforming solid oxide fuel cells.Adv Energy Mater2025;15:2403869

[55] Holzer L,Iwanschitz B,Hocker T.Quantitative relationships between composition, particle size, triple phase boundary length and surface area in nickel-cermet anodes for solid oxide fuel cells.J Power Sources2011;196:7076-89

[56] Mogensen MB,Frandsen HL.Ni migration in solid oxide cell electrodes: review and revised hypothesis.Fuel Cells2021;21:415-29

[57] Shimura T,Hara S.Quantitative analysis of solid oxide fuel cell anode microstructure change during redox cycles.J Power Sources2014;267:58-68

[58] Sciazko A,Yokoi R,Shikazono N.Effects of mass fraction of La_0.9Sr_0.1Cr_0.5Mn_0.5O_3-δ and Gd_0.1Ce_0.9O_2-δ composite anodes for nickel free solid oxide fuel cells.J Eur Ceram Soc2022;42:1556-67

[59] Jeangros Q,Hébert C,Hessler-Wyser A.A TEM study of Ni interfaces formed during activation of SOFC anodes in H₂: influence of grain boundary symmetry and segregation of impurities.Acta Mater2016;103:442-7

[60] Harris WM,Nelson GJ.Three-dimensional microstructural imaging of sulfur poisoning-induced degradation in a Ni-YSZ anode of solid oxide fuel cells.Sci Rep2014;4:5246 PMCID:PMC4050380

[61] Sciazko A,Shimura T.Prediction of electrode microstructure evolutions with physically constrained unsupervised image-to-image translation networks.npj Comput Mater2024;10:1228

[62] Pawłowski P,Prokop T,Brus G.Microstructure evolution of solid oxide fuel cell anodes characterized by persistent homology.Energy AI2023;14:100256

[63] Zheng Y,Zhao D.Data-driven fault diagnosis method for the safe and stable operation of solid oxide fuel cells system.J Power Sources2021;490:229561

[64] Le GT,Brouwer J.Simulation-informed machine learning diagnostics of solid oxide fuel cell stack with electrochemical impedance spectroscopy.J Electrochem Soc2022;169:034530

[65] Wu X,Peng J,Kupecki J.Novel hybrid modeling and analysis method for steam reforming solid oxide fuel cell system multifault degradation fusion assessment.ACS Omega2023;8:36876-92 PMCID:PMC10568590

[66] He Y,Kwong S.Bayesian classifiers based on probability density estimation and their applications to simultaneous fault diagnosis.Inform Sci2014;259:252-68

[67] Zhang Z,Xiao Y.Intelligent simultaneous fault diagnosis for solid oxide fuel cell system based on deep learning.Appl Energy2019;233-4:930-42

[68] Liu Y,Yu Y.A novel integral reinforcement learning-based control method assisted by twin delayed deep deterministic policy gradient for solid oxide fuel cell in DC microgrid.IEEE Trans Sustain Energy2023;14:688-703

[69] Mozdzierz M,Kimijima S,Brus G.An afterburner-powered methane/steam reformer for a solid oxide fuel cells application.Heat Mass Transfer2018;54:2331-41

[70] Ghorbani B.Developing a virtual hydrogen sensor for detecting fuel starvation in solid oxide fuel cells using different machine learning algorithms.Int J Hydrogen Energy2020;45:27730-44

[71] Ba L,Yang Z,Ge B.A novel multi-physics and multi-dimensional model for solid oxide fuel cell stacks based on alternative mapping of BP neural networks.J Power Sources2021;500:229784

[72] Lyu Z,Sciazko A.Prediction of fuel cell performance degradation using a combined approach of machine learning and impedance spectroscopy.J Energy Chem2023;87:32-41

[73] Wu X,Cai S.Data-driven approaches for predicting performance degradation of solid oxide fuel cells system considering prolonged operation and shutdown accumulation effect.J Power Sources2024;598:234186

[74] Barredo Arrieta A,Del Ser J.Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI.Inf Fusion2020;58:82-115

[75] Tao F,Qi Q,Zhang H.Digital twin-driven product design, manufacturing and service with big data.Int J Adv Manuf Technol2018;94:3563-76