The effect of catalyst layer design on catalyst utilization in PEMFC studied via stochastic reconstruction method

Catalyst utilization is an important determinant of proton exchange membrane fuel cell performance,and increasing the catalyst utilization is one of the most critical approaches to reducing the catalyst loading in PEMFC.4-phase stochastic reconstruction method based on the variable-resolution Quartet Structure Generation Set(QSGS)algorithm is utilized to elucidate the influence of different parameters of electrode preparation,including the porosity,the dispersion degree of carbon agglomerate,ionomer content,and carbon support size,on the catalyst utilization in the catalyst layer.It was found that there exist optimal values for the porosity,dispersion degree of carbon agglomerate,ionomer content,and carbon support sizes in CLs and any deviations from these optimal values would lead to transport issues of electron,proton and mass within CLs.Taking electron,proton and mass transport into consideration simultaneously,the optimal Pt utilization is 46.55%among 48 cases in this investigation,taken at the carbon support diameter of 40 nm,the porosity of 0.4,the agglomerate spatial density of 25μm^(−3) and I/C at 0.7.The selection of porosity,ultrasonic dispersion technique and ionomer content for conventional electrode preparation requires compromises on mass,electron and proton transport,leading to catalyst utilization in CLs hardly exceeding 50%.Therefore,the next generation of catalyst layer design and preparation technology is desired.

A novel feature susceptibility approach for a PEMFC control system based on an improved XGBoost-Boruta algorithm

Data-driven modelling methods are being developed in the quest to achieve more accurate performance prediction of protons exchange membrane fuel cell (PEMFC) systems in response to their complicated physicochemical phenomena. However, there is little research in this field detailing the pre-processing and selection of balance of plants (BOP) features for the input layer of system performance prediction at different current densities. Furthermore, most of the previous research applies neural networks based on simulation data rather than real-time bench or vehicle operation datasets which leads to low robustness and unreliable practical results. This paper details the application of a novel algorithm denoted XGBoost-Boruta, which utilises the combination of an ensemble learning approach and a wrapping approach, to improve the robustness of feature selection and to increase the accuracy and robustness of PEMFC system performance prediction. By introduction of the Z score and shadow features to eliminate the randomness of conventional ensemble learning methods, seven key controllable BOP variables of the hydrogen anode, air cathode and cooling subsystems are selected as the original input variables to determine their dependency on the stack voltage. Two case studies are presented for verification and validation of the proposed algorithm based on the real-time dataset of bench experimental data and data obtained from heavy truck operation at current densities ranging from 100 to 1500 mA/cm2. The feature selection strategy, based on the proposed XGBoost-Boruta algorithm, largely decreases the RMSE by 23.8% and 14.1% and the R^(2) increases by 0.06 and 0.04 of both the bench experimental and the heavy truck validation datasets respectively.

Positive direction of polarization-induced electric field improves formic acid electrooxidation on Pd

Adjusting the adsorption energy of adsorbates on catalyst can directly regulate the catalytic performance and reaction pathways of heterogeneous catalysis.Herein,we report a novel strategy,introducing polarization-induced electric field(PIEF)with different directions,to manipulate the adsorption energy of intermediates and reaction pathway of formic acid electrooxidation on Pd.Tourmaline nanoparticles are applied as the PIEF provider,of which the direction is successfully controlled via aligning the dipoles in tourmaline in a strong external electric field.Experimental and theoretical results systematically reveal that positive PIEF leads to an electron-deficient state of Pd,reduced adsorption energy of COad,enhanced adsorption energy of*HCOOH and*OH,and promoted formate pathway of formic acid electrooxidation.Pd/TNP+/FTO,with the aid of positive PIEF,shows three-fold enhancement in the formic acid electrooxidation(4.74 mA·cm^(−2))with high durability and anti-poisoning ability compared with pristine Pd.This study leads a new route to design formic acid electrocatalysts and provides an understanding on how to control the adsorption energy of adsorbates on electrocatalysts by an internal electric field.

Long short-term memory deep learning model for predicting the dynamic performance of automotive PEMFC system

As a high efficiency hydrogen-to-power device,proton exchange membrane fuel cell(PEMFC)attracts much attention,especially for the automotive applications.Real-time prediction of output voltage and area specific resistance(ASR)via the on-board model is critical to monitor the health state of the automotive PEMFC stack.In this study,we use a transient PEMFC system model for dynamic process simulation of PEMFC to generate the dataset,and a long short-term memory(LSTM)deep learning model is developed to predict the dynamic per-formance of PEMFC.The results show that the developed LSTM deep learning model has much better perfor-mance than other models.A sensitivity analysis on the input features is performed,and three insensitive features are removed,that could slightly improve the prediction accuracy and significantly reduce the data volume.The neural structure,sequence duration,and sampling frequency are optimized.We find that the optimal sequence data duration for predicting ASR is 5 s or 20 s,and that for predicting output voltage is 40 s.The sampling frequency can be reduced from 10 Hz to 0.5 Hz and 0.25 Hz,which slightly affects the prediction accuracy,but obviously reduces the data volume and computation amount.

Elucidating the operating behavior of PEM fuel cell with nickel foam as cathode flow field

Metal foam material,which serves as an alternative replacement of the conventional flow distributor of proton exchange membrane(PEM)fuel cell,has been attracting much attention over last few decades.In this work,three-dimensional modeling work for PEM fuel cell containing metal foam as cathode flow distributor has been carried out.The fuel cell performance and operating characteristics of metal foam flow field and conventional parallel flow channel have been compared and discussed.The cell performance has been reasonably validated based on the corresponding experimental tests conducted in this study.The superior performance of PEM fuel cell with metal foam as cathode flow field benefits a lot from the uniform gas flow.The porous metal foam material provides more pathways for the water delivery at the interface of metal foam flow field and gas diffusion layer(GDL),accelerating water removal capability of cathode.Because of the significant oxygen transfer loss in diffusion limited parallel channel,the operation of PEM fuel cell with parallel channel is found to be more sensitive to cathode humidification and oxygen supply at inlet.Due to the more uniform and effective electron transport though the porous electrode,it is possible to use thinner GDL in metal foam PEM fuel cell.It is expected that this study could give a good baseline of operating behavior of PEM fuel cell with metal foam flow distributor.

Thermal annealing synthesis of double-shell truncated octahedral Pt-Ni alloys for oxygen reduction reaction of polymer electrolyte membrane fuel cells

Shape-controlled Pt-Ni alloys usually offer an exceptional electrocatalytic activity toward the oxygen reduction reaction(ORR)of polymer electrolyte membrane fuel ceils(PEMFCs),whose tricks lie in welldesigned structures and surface morphologies.In this paper,a novel synthesis of truncated octahedral PtNi_(3.5) alloy catalysts that consist of homogeneous Pt-Ni alloy cores enclosed by NiO-Pt double shells through thermally annealing defective heterogeneous PtNi35 alloys is reported.By tracking the evolution of both compositions and morphologies,the outward segregation of both PtOv and NiO are first observed in Pt-Ni alloys.It is speculated that the diffusion of low-coordination atoms results in the formation of an energetically favorable truncated octahedron while the outward segregation of oxides leads to the formation of NiO-Pt double shells.It is very attractive that after gently removing the NiO outer shell,the dealloyed truncated octahedral core-shell structure demonstrates a greatly enhanced ORR activity.The asobtained truncated octahedral Pt_(2.1)Ni core-shell alloy presents a 3.4-folds mass-specific activity of that for unannealed sample,and its activity preserves 45.4%after 30000 potential cycles of accelerated degradation test(ADT).The peak power density of the dealloyed truncated octahedral Pt2jNi core-shell alloy catalyst based membrane electrolyte assembly(MEA)reaches 679.8 mW/cm^(2),increased by 138.4 mW/cm^(2) relative to that based on commercial Pt/C.

Data-based flooding fault diagnosis of proton exchange membrane fuel cell systems using LSTM networks

Flooding fault diagnosis is critical to the stable and efficient operation of fuel cells,while the on-board embedded controller has limited computing power and sensors,making it difficult to incorporate the complex gas-liquid two-phase flow models.Then in fuel cell system for cars,the neural network modeling is usually regarded as an appropriate tool for the on-line diagnosis of water status.Traditional neural network classifiers are not good at processing time series data,so in this paper,Long Short-Term Memory(LSTM)network model is developed and applied to the flooding fault diagnosis based on the embedded platform.Moreover,the fuel cell auxiliary system statuses are adopted as the inputs of the diagnosis network,which avoids installing a large number of sensors in the fuel cell system,and contributes to reduce the total system cost.The bench test on the 92 kW vehicle fuel cell system proved that this model can effectively diagnose/pre-diagnose the fuel cell flooding,and thus help optimize the water management under vehicle conditions.

Prediction of high frequency resistance in polymer electrolyte membrane fuel cells using long short term memory based model

High-frequency resistance(HFR)is a critical quantity strongly related to a fuel cell system’s performance.It is beneficial to estimate the fuel cell system’s HFR from the measurable operating conditions without resorting to costly HFR measurement devices.In this study,we propose a data-driven approach for a real-time prediction of HFR.Specifically,we use a long short-term memory(LSTM)based machine learning model that takes into account both the current and past states of the fuel cell,as characterized through a set of sensors.These sensor signals form the input to the LSTM.The data is experimentally collected from a vehicle lab that operates a 100 kW automotive fuel cell stack running on an automotive-scale test station.Our current results indicate that our prediction model achieves high accuracy HFR predictions and outperforms other frequently used regression models.We also study the effect of the extracted features generated by our LSTM model.Our study finds that only very few dimensions of the extracted feature are influential in HFR prediction.The study highlights the potential to monitor HFR condition accurately and timely on a car.