Accurate prediction of performance degradation in complex systems such as solid oxide fuel cells is crucial for expediting technological advancements.However,significant challenges still persist due to limited compreh...Accurate prediction of performance degradation in complex systems such as solid oxide fuel cells is crucial for expediting technological advancements.However,significant challenges still persist due to limited comprehension of degradation mechanisms and difficulties in acquiring in-situ features.In this study,we propose an effective approach that integrates long short-term memory(LSTM) neural network and dynamic electrochemical impedance spectroscopy(DEIS).This integrated approach enables precise prediction of future evolutions in both current-voltage and EIS features using historical testing data,without prior knowledge of degradation mechanisms.For short-term predictions spanning hundreds of hours,our approach achieves a prediction accuracy exceeding 0.99,showcasing promising prospects for diagnostic applications.Additionally,for long-term predictions spanning thousands of hours,we quantitatively determine the significance of each degradation mechanism,which is crucial for enhancing cell durability.Moreover,our proposed approach demonstrates satisfactory predictive ability in both time and frequency domains,offering the potential to reduce EIS testing time by more than half.展开更多
In the present study,two Ni/YSZ anodes with different volume ratios of Ni and YSZ,30:70 and 45:55 vol%,are operated in dry methane under open circuit and polarized conditions.Three-dimensional(3D)Ni/YSZ microstructure...In the present study,two Ni/YSZ anodes with different volume ratios of Ni and YSZ,30:70 and 45:55 vol%,are operated in dry methane under open circuit and polarized conditions.Three-dimensional(3D)Ni/YSZ microstructures after carbon deposition are reconstructed by the focused ion beam-scanning electron microscopy(FIB-SEM)with the help of machine learning segmentation.From the reconstructed mircostructures,volume fraction,connectivity,three phase boundary(TPB)density,and tortuosity are quantified.In addition,local carbon microstructures are quantitatively reconstructed,and the effect of polarization on carbon morphology is investigated.It is demonstrated that Ni surface in the vicinity of active TPB near the electrolyte is free from carbon formation,while remaining Ni surface at some distances from TPB exhibits severe carbon deposition.In average,total amount of carbon deposition is larger near the electrolyte.These observations imply complex interplay between the electrochemical steam generation and methane cracking on Ni surface which take place very locally near the active TPB.展开更多
Self-made conventional nickel-yttria-stabilized zirconia composite anodes after reduction and 500 h operation were analyzed by three-dimensional microstructure reconstruction based on focused ion beam-scanning electro...Self-made conventional nickel-yttria-stabilized zirconia composite anodes after reduction and 500 h operation were analyzed by three-dimensional microstructure reconstruction based on focused ion beam-scanning electron microscopy technique.Interfacial area,threephases-boundary density and phase volume fraction were measured based on the three-dimensional microstructure reconstruction to quantitatively study the statistical characterization of solid oxide fuel cell nickel-yttria-stabilizedzirconia anode microstructure before and after operation.It is found that for anode operated with long time,it is necessary to increase the corresponding three-dimensional reconstruction size to suppress the influence of microstructure variation caused by Ni agglomeration in order to obtain more accurate microstructural quantification information.展开更多
A deep learning based homogenization framework is proposed to link the microstructures of porous nickel/yttriastabilized zirconia anodes in solid oxide fuel cells(SOFCs)to their effective macroscopic properties.A vari...A deep learning based homogenization framework is proposed to link the microstructures of porous nickel/yttriastabilized zirconia anodes in solid oxide fuel cells(SOFCs)to their effective macroscopic properties.A variety of microstructures are generated by the discrete element method and the meso‑scale kinetic Monte Carlo method.Then,the finite element method and the homogenization theory are used to calculate the effective elastic modulus(E),Poisson’s ratio(υ),shear modulus(G)and coefficient of thermal expansion(CTE)of representative volume elements.In addition,the triple-phase boundary length density(LTPB)is also calculated.The convolutional neural network(CNN)based deep learning model is trained to find the potential relationship between the microstructures and the five effective macroscopic properties.The comparison between the ground truth and the predicted values of the new samples proves that the CNN model has an excellent predictive performance.This indicates that the CNN model could be used as an effective alternative to numerical simulations and homogenization because of its accurate and rapid prediction performance.Hence the deep learning-based homogenization framework could potentially accelerate the continuum modeling of SOFCs for microstructure optimization.展开更多
基金partly supported by Japan Society for the Promotion of Science (JSPS) Postdoctoral Fellowships for Research in Japan (P22370)by Key Project of Jiangsu Province (BE2022029) in China。
文摘Accurate prediction of performance degradation in complex systems such as solid oxide fuel cells is crucial for expediting technological advancements.However,significant challenges still persist due to limited comprehension of degradation mechanisms and difficulties in acquiring in-situ features.In this study,we propose an effective approach that integrates long short-term memory(LSTM) neural network and dynamic electrochemical impedance spectroscopy(DEIS).This integrated approach enables precise prediction of future evolutions in both current-voltage and EIS features using historical testing data,without prior knowledge of degradation mechanisms.For short-term predictions spanning hundreds of hours,our approach achieves a prediction accuracy exceeding 0.99,showcasing promising prospects for diagnostic applications.Additionally,for long-term predictions spanning thousands of hours,we quantitatively determine the significance of each degradation mechanism,which is crucial for enhancing cell durability.Moreover,our proposed approach demonstrates satisfactory predictive ability in both time and frequency domains,offering the potential to reduce EIS testing time by more than half.
基金partly supported by the New Energy and Industrial Technology Development Organization(NEDO)by the Japan Society for the Promotion of Science KAKENHI(21K14090)+3 种基金the National Key R&D Program of China(2019YFE0122000)the Scientific Research Foundation of Graduate School of Southeast University(YBPY2106)the China Scholarship Councilby the Advanced Research Infrastructure for Materials and Nanotechnology in Japan(ARIM Japan)sponsored by the Ministry of Education,Culture,Sport,Science and Technology(MEXT),Japan。
文摘In the present study,two Ni/YSZ anodes with different volume ratios of Ni and YSZ,30:70 and 45:55 vol%,are operated in dry methane under open circuit and polarized conditions.Three-dimensional(3D)Ni/YSZ microstructures after carbon deposition are reconstructed by the focused ion beam-scanning electron microscopy(FIB-SEM)with the help of machine learning segmentation.From the reconstructed mircostructures,volume fraction,connectivity,three phase boundary(TPB)density,and tortuosity are quantified.In addition,local carbon microstructures are quantitatively reconstructed,and the effect of polarization on carbon morphology is investigated.It is demonstrated that Ni surface in the vicinity of active TPB near the electrolyte is free from carbon formation,while remaining Ni surface at some distances from TPB exhibits severe carbon deposition.In average,total amount of carbon deposition is larger near the electrolyte.These observations imply complex interplay between the electrochemical steam generation and methane cracking on Ni surface which take place very locally near the active TPB.
基金supported by the New Energy and Industrial Technology Development Organization(NEDO)under the Development of System and Elemental Technology on Solid Oxide Fuel Cell(SOFC)Project
文摘Self-made conventional nickel-yttria-stabilized zirconia composite anodes after reduction and 500 h operation were analyzed by three-dimensional microstructure reconstruction based on focused ion beam-scanning electron microscopy technique.Interfacial area,threephases-boundary density and phase volume fraction were measured based on the three-dimensional microstructure reconstruction to quantitatively study the statistical characterization of solid oxide fuel cell nickel-yttria-stabilizedzirconia anode microstructure before and after operation.It is found that for anode operated with long time,it is necessary to increase the corresponding three-dimensional reconstruction size to suppress the influence of microstructure variation caused by Ni agglomeration in order to obtain more accurate microstructural quantification information.
基金This work was supported by the National Natural Science Foundation of China(Nos.11932005,12172104)the National Key R&D Program of China(No.2018YFB1502602)Shenzhen Science and Technology Innovation Commission(JCYJ20200109113439837).
文摘A deep learning based homogenization framework is proposed to link the microstructures of porous nickel/yttriastabilized zirconia anodes in solid oxide fuel cells(SOFCs)to their effective macroscopic properties.A variety of microstructures are generated by the discrete element method and the meso‑scale kinetic Monte Carlo method.Then,the finite element method and the homogenization theory are used to calculate the effective elastic modulus(E),Poisson’s ratio(υ),shear modulus(G)and coefficient of thermal expansion(CTE)of representative volume elements.In addition,the triple-phase boundary length density(LTPB)is also calculated.The convolutional neural network(CNN)based deep learning model is trained to find the potential relationship between the microstructures and the five effective macroscopic properties.The comparison between the ground truth and the predicted values of the new samples proves that the CNN model has an excellent predictive performance.This indicates that the CNN model could be used as an effective alternative to numerical simulations and homogenization because of its accurate and rapid prediction performance.Hence the deep learning-based homogenization framework could potentially accelerate the continuum modeling of SOFCs for microstructure optimization.
