Prediction of impedance responses of protonic ceramic cells using artificial neural network tuned with the distribution of relaxation times

A deep-learning-based framework is proposed to predict the impedance response and underlying electrochemical behavior of the reversible protonic ceramic cell(PCC) across a wide variety of different operating conditions.Electrochemical impedance spectra(EIS) of PCCs were first acquired under a variety of opera ting conditions to provide a dataset containing 36 sets of EIS spectra for the model.An artificial neural network(ANN) was then trained to model the relationship between the cell operating condition and EIS response.Finally,ANN model-predicted EIS spectra were analyzed by the distribution of relaxation times(DRT) and compared to DRT spectra obtained from the experimental EIS data,enabling an assessment of the accumulative errors from the predicted EIS data vs the predicted DRT.We show that in certain cases,although the R^(2)of the predicted EIS curve may be> 0.98,the R^(2)of the predicted DRT may be as low as~0.3.This can lead to an inaccurate ANN prediction of the underlying time-resolved electrochemical response,although the apparent accuracy as evaluated from the EIS prediction may seem acceptable.After adjustment of the parameters of the ANN framework,the average R^(2)of the DRTs derived from the predicted EIS can be improved to 0.9667.Thus,we demonstrate that a properly tuned ANN model can be used as an effective tool to predict not only the EIS,but also the DRT of complex electrochemical systems.

Rational design of stretchable and conductive hydrogel binder for highly reversible SiP2 anode

The emerging SiP2with large capacity and suitable plateau is proposed to be the alternative anode for Li-ion batteries.However,typical SiP2still suffers from serious volume expansion and structural destruction,resulting in much Li-consumption and capacity fading.Herein,a novel stretchable and conductive Li-PAA@PEDOT:PSS binder is rationally designed to improve the cyclability and reversibility of SiP2.Interestingly,such Li-PAA@PEDOT:PSS hydrogel enables a better accommodation of volume expansion than PVDF binder(e.g.5.94% vs.68.73% of expansivity).More specially,the SiP2electrode with LiPAA@PEDOT:PSS binder is surprisingly found to enable unexpected structural recombination and selfhealing Li-storage processes,endowing itself with a high initial Coulombic efficiency(ICE) up to 93.8%,much higher than PVDF binder(ICE=70.7%) as well.Such unusual phenomena are investigated in detail for Li-PAA@PEDOT:PSS,and the possible mechanism shows that its Li-PAA component enables to prevent the pulverization of SiP2nanoparticles while the PEDOT:PSS greatly bridges fast electronic connection for the whole electrode.Consequently,after being further composited with carbon matrix,the SiP2/C with LiPAA@PEDOT:PSS hydrogel exhibits high reversibility(ICE> 93%),superior cyclability(>450 cycles),and rate capability(1520 mAh/g at 2000 mA/g) for LIBs.This highly stretchable and conductive binder design can be easily extended to other alloying materials toward advanced energy storage.

Correlation between microstructures and macroscopic properties of nickel/ yttria-stabilized zirconia (Ni-YSZ) anodes: Meso-scale modeling and deep learning with convolutional neural networks

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.