Performance Degradation Prediction of Proton Exchange Membrane Fuel Cell Based on CEEMDAN-KPCA and DA-GRU Networks

In order to improve the performance degradation prediction accuracy of proton exchange membrane fuel cell(PEMFC),a fusion prediction method(CKDG)based on adaptive noise complete ensemble empirical mode decomposition(CEEMDAN),kernel principal component analysis(KPCA)and dual attention mechanism gated recurrent unit neural network(DA-GRU)was proposed.CEEMDAN and KPCA were used to extract the input feature data sequence,reduce the influence of random factors,and capture essential feature components to reduce the model complexity.The DA-GRU network helps to learn the feature mapping relationship of data in long time series and predict the changing trend of performance degradation data more accurately.The actual aging experimental data verify the performance of the CKDG method.The results show that under the steady-state condition of 20%training data prediction,the CKDA method can reduce the root mean square error(RMSE)by 52.7%and 34.6%,respectively,compared with the traditional LSTM and GRU neural networks.Compared with the simple DA-GRU network,RMSE is reduced by 15%,and the degree of over-fitting is reduced,which has higher accuracy.It also shows excellent prediction performance under the dynamic condition data set and has good universality.

Effects of baffle position in serpentine flow channel on the performance of proton exchange membrane fuel cells

This study used a three-dimensional numerical model of a proton exchange membrane fuel cell with five types of channels:a smooth channel(Case 1);eight rectangular baffles were arranged in the upstream(Case 2),midstream(Case 3),downstream(Case 4),and the entire cathode flow channel(Case 5)to study the effects of baffle position on mass transport,power density,net power,etc.Moreover,the effects of back pressure and humidity on the voltage were investigated.Results showed that compared to smooth channels,the oxygen and water transport facilitation at the diffusion layer-channel interface were added 11.53%-20.60%and 7.81%-9.80%at 1.68 A·cm^(-2)by adding baffles.The closer the baffles were to upstream,the higher the total oxygen flux,but the lower the flux uniformity the worse the water removal.The oxygen flux of upstream baffles was 8.14%higher than that of downstream baffles,but oxygen flux uniformity decreased by 18.96%at 1.68 A·cm^(-2).The order of water removal and voltage improvement was Case 4>Case 5>Case 3>Case 2>Case 1.Net power of Case 4 was 9.87%higher than that of the smooth channel.To the Case 4,when the cell worked under low back pressure or high humidity,the voltage increments were higher.The potential increment for the back pressure of 0 atm was 0.9%higher than that of 2 atm(1 atm=101.325 kPa).The potential increment for the humidity of 100%was 7.89%higher than that of 50%.

Probing the Efficiency of PPMG-Based Composite Electrolytes for Applications of Proton Exchange Membrane Fuel Cell

PPMG-based composite electrolytes were fabricated via the solution method using the polyvinyl alcohol and polyvinylpyrrolidone blend reinforced with various contents of sulfonated inorganic filler.Sulfuric acid was employed as the sulfonating agent to functionalize the external surface of the inorganic filler,i.e.,graphene oxide.The proton conductivities of the newly prepared proton exchange membranes(PEMs)were increased by increasing the temperature and content of sulfonated graphene oxide(SGO),i.e.,ranging from 0.025 S/cm to 0.060 S/cm.The induction of the optimum level of SGO is determined to be an excellent route to enhance ionic conductivity.The single-cell performance test was conducted by sandwiching the newly prepared PEMs between an anode(0.2 mg/cm^(2) Pt/Ru)and a cathode(0.2 mg/cm^(2) Pt)to prepare membrane electrode assemblies,followed by hot pressing under a pressure of approximately 100 kg/cm^(2) at 60℃for 5–10 min.The highest power densities achieved with PPMG PEMs were 14.9 and 35.60 mW/cm^(2) at 25℃and 70℃,respectively,at ambient pressure with 100%relative humidity.Results showed that the newly prepared PEMs exhibit good electrochemical performance.The results indicated that the prepared composite membrane with 6 wt%filler can be used as an alternative membrane for applications of high-performance proton exchange membrane fuel cell.

Comparative review of corrosion-resistant coatings on metal bipolar plates of proton exchange membrane fuel cells

In the realm of proton exchange membrane fuel cells(PEMFCs),the bipolar plates(BPs)are indispensable and serve pivotal roles in distributing reactant gases,collecting current,facilitating product water removal,and cooling the stack.Metal BPs,characterized by outstanding manufacturability,cost-effectiveness,higher power density,and mechanical strength,are emerging as viable alternatives to traditional graphite BPs.The foremost challenge for metal BPs lies in enhancing their corrosion resistance and conductivity under acidic conditions,necessitating the application of various coatings on their surfaces to ensure superior performance.This review summarizes and compares recent advancements in the research of eight distinct types of coatings for BPs in PEMFCs,including noble metal,carbide,ni-tride,and amorphous carbon(a-C)/metal compound composite coatings.The various challenges encountered in the manufacturing and fu-ture application of these coatings are also delineated.

Surface decoration prompting the decontamination of active sites in high-temperature proton exchange membrane fuel cells

In electrochemical energy devices,the operating conditions always exert enormous influence on electrocatalysts'performances.Phosphoric acid(PA),acted as the proton carriers,can be adsorbed on Pt surface,block active sites and affect the electronic structure of Pt unfavorably,which severely restricts the performance of high-temperature proton exchange membrane fuel cells(HT-PEMFCs).Herein,simply basic organic compounds,such as dicyandiamide(DCD),melamine(Mel)and cyanuric acid(CA),are decorated on Pt surface(DCD-Pt/C,Mel-Pt/C and CA-Pt/C)to induce the adsorption transfer of proton carriers.The decoration can not only inject electrons to Pt and enhance oxygen reduction reaction(ORR)activity but also can induce PA to transfer from Pt surface to organic compounds,decontaminating active sites.In addition,the organic compounds with the larger conjugated system and the smaller electronegativity of ligating atoms would have a greater interaction with Pt,causing a larger decoration amount on Pt surface,which leads to more excellent ORR activity and resistance to PA blockage effect.Therefore,MelPt/C shows a peak power density of 629 mW/cm^(2),exceeding commercial Pt/C(437 mW/cm^(2)),DCD-Pt/C(539 m W/cm^(2))and CA-Pt/C(511 mW/cm^(2))with the same loading.

Intermolecular Acid-Base-Pairs Containing Poly(p-Terphenyl-co-lsatin Piperidinium)for High Temperature Proton Exchange Membrane Fuel Cells

How to optimize and regulate the distribution of phosphoric acid in matrix,and pursuing the improved electrochemical performance and service lifetime of high temperature proton exchange membrane(HT-PEMs)fuel cell are significant challenges.Herein,bifunctional poly(p-terphenyl-co-isatin piperidinium)copolymer with tethered phosphonic acid(t-PA)and intrinsic tertiary amine base groups are firstly prepared and investigated as HT-PEMs.The distinctive architecture of the copolymer provides a well-designed platform for rapid proton transport.Protons not only transports through the hydrogen bond network formed by the adsorbed free phosphoric acid(f-PA)anchored by the tertiary amine base groups,but also rely upon the proton channel constructed by the ionic cluster formed by the t-PA aggregation.Thorough the design of the structure,the bifunctional copolymers with lower PA uptake level(<100%)display prominent proton conductivities and peak power densities(99 mS cm^(-1),812 mW cm^(-2)at 160℃),along with lower PA leaching and higher voltage stability,which is a top leading result in disclosed literature.The results demonstrate that the design of intermolecular acid-base-pairs can improve the proton conductivity without sacrificing the intrinsic chemical stability or mechanical property of the thin membrane,realizing win-win demands between the mechanical robustness and electrochemical properties of HT-PEMs.

Gel-state polybenzimidazole proton exchange membranes with flexible alkyl sulfonic acid side chains for a wider operating temperature range(25–240 ℃)

High-temperature proton exchange membrane fuel cells(HT-PEMFC) possess distinct technical advantages of high output power, simplified water/heat management, increased tolerance to fuel impurities and diverse fuel sources, within the temperature range of 120–200 ℃. However, for practical automobile applications, it was crucial to broaden their low-temperature operating window and enable cold start-up capability. Herein, gel-state phosphoric acid(PA) doped sulfonated polybenzimidazole(PBI) proton exchange membranes(PEMs) were designed and synthesized via PPA sol-gel process and in-situ sultone ring-opening reactions with various proton transport pathways based on absorbed PA, flexible alkyl chain connected sulfonic acid groups and imidazole sites. The effects of flexible alkyl sulfonic acid side chain length and content on PA doping level, proton conductivity, and membrane stability under different temperature and relative humidity(RH) were thoroughly investigated. The prepared gel-state membranes contained a self-assembled lamellar and porous structure that facilitated the absorption of a large amount of PA with rapid proton transporting mechanisms. At room temperature, the optimized membrane exhibited a proton conductivity of 0.069 S cm^(-1), which was further increased to 0.162 and 0.358 S cm^(-1)at 80 and 200 ℃, respectively, without additional humidification. The most significant contribution of this work was demonstrating the feasibility of gel-state sulfonated PBI membranes in expanding HT-PEMFC application opportunities over a wider operating range of 25 to 240 ℃.

Pore-Scale Investigation of Coupled Two-Phase and Reactive Transport in the Cathode Electrode of Proton Exchange Membrane Fuel Cells

A three-dimensional multicomponent multiphase lattice Boltzmann model(LBM)is established to model the coupled two-phase and reactive transport phenomena in the cathode electrode of proton exchange membrane fuel cells.The gas diff usion layer(GDL)and microporous layer(MPL)are stochastically reconstructed with the inside dynamic distribution of oxygen and liquid water resolved,and the catalyst layer is simplifi ed as a superthin layer to address the electrochemical reaction,which provides a clear description of the fl ooding eff ect on mass transport and performance.Diff erent kinds of electrodes are reconstructed to determine the optimum porosity and structure design of the GDL and MPL by comparing the transport resistance and per-formance under the fl ooding condition.The simulation results show that gradient porosity GDL helps to increase the reactive area and average concentration under fl ooding.The presence of the MPL ensures the oxygen transport space and reaction area because liquid water cannot transport through micropores.Moreover,the MPL helps in the uniform distribution of oxygen for an effi cient in-plane transport capacity.Crack and perforation structures can accelerate the water transport in the assembly.The systematic perforation design yields the best performance under fl ooding by separating the transport of liquid water and oxygen.

CFD Analysis of Spiral Flow Fields in Proton Exchange Membrane Fuel Cells

Proton exchange membrane fuel cells(PEMFCs)are largely used in various applications because of their pollution-free products and high energy conversion efficiency.In order to improve the related design,in the present work a new spiral flow field with a bypass is proposed.The reaction gas enters the flow field in the central path and diffuses in two directions through the flow channel and the bypass.The bypasses are arranged incrementally.The number of bypasses and the cross-section size of the bypasses are varied parametrically while a single-cell model of the PEMFC is used.The influence of the concentration of liquid water and oxygen in the cell on the performance of different flow fields is determined by means of Computational fluid dynamics(COMSOL Multiphysics software).Results show that when the bypass number is 48 and its cross-sectional area is 0.5 mm^(2),the cell exhibits the best performances.

In situ grown nanoscale platinum on carbon powder as catalyst layer in proton exchange membrane fuel cells(PEMFCs)

An extensive study has been conducted on the proton exchange membrane fuel cells （PEMFCs） with reducing Pt loading. This is commonly achieved by developing methods to increase the utilization of the platinum in the catalyst layer of the electrodes. In this paper, a novel process of the catalyst layers was introduced and investigated. A mixture of carbon powder and Nafion solution was sprayed on the glassy carbon electrode （GCE） to form a thin carbon layer. Then Pt particles were deposited on the surface by reducing hexachloroplatinic （IV） acid hexahydrate with methanoic acid. SEM images showed a continuous Pt gradient profile among the thickness direction of the catalytic layer by the novel method. The Pt nanowires grown are in the size of 3 nm （diameter） x l0 nm （length） by high solution TEM image. The novel catalyst layer was characterized by cyclic voltammetry （CV） and scanning electron microscope （SEM） as compared with commercial Pt/C black and Pt catalyst layer obtained from sputtering. The results showed that the platinum nanoparticles deposited on the carbon powder were highly utilized as they directly faced the gas diffusion layer and offered easy access to reactants （oxygen or hydrogen）.

Particle Swarm Optimization based predictive control of Proton Exchange Membrane Fuel Cell (PEMFC)

Proton Exchange Membrane Fuel Cells (PEMFCs) are the main focus of their current development as power sources because they are capable of higher power density and faster start-up than other fuel cells. The humidification system and output performance of PEMFC stack are briefly analyzed. Predictive control of PEMFC based on Support Vector Regression Machine (SVRM) is presented and the SVRM is constructed. The processing plant is modelled on SVRM and the predictive control law is obtained by using Particle Swarm Optimization (PSO). The simulation and the results showed that the SVRM and the PSO re-ceding optimization applied to the PEMFC predictive control yielded good performance.

Performance Characteristics of an Irreversible Proton Exchange Membrane (PEM) Fuel Cell

A model of an irreversible proton exchange membrane （PEM） fuel cell working at steady-state was established, in which overpotenfials, internal currents, and crossover losses were taken into account. The expressions of some key parameters of the fuel cell were derived from the point of electrochemistry and thermodynamics. Based on the irreversible model of the PEM fuel ceil, the influence of multi-irreversibilities on fuel cell performance were characterized and compared systematically. The general performance characteristic curves were generated. Moreover, when the electrical circuit was dosed with a load in it, the relations between the load resistance and power output density and efficiency were analyzed. The results provide a theoretical basis for both the operation and optimal design of real PEM fuel cells.

基于LSTM-MPC的PEMFC运行状态建模与容错控制

质子交换膜燃料电池(proton exchange membrane fuel cell,PEMFC)具有多物理场耦合特性易产生不同故障且难以控制。为了能在故障状态下快速有效控制,提出基于模型预测控制(modelpredictivecontrol,MPC)的容错控制方案。首先,以长短时记忆神经网络(long short-term memory,LSTM)的预测误差为遗传算法的适应度函数,寻优获取LSTM的最优超参数组合,基于数据驱动构建PEMFC系统在4种不同运行状态下的LSTM预测模型作为预测模型模块。然后,建立基于神经网络的控制器作为优化控制器模块,根据上述模块制定以PEMFC系统阴阳极输入气体压强为控制量、电堆电压为输出量的容错控制方案。最后,仿真验证LSTM预测模型与容错控制方案得到,LSTM预测模型在训练集和测试集的评估指标均方根误差(root mean square error,RMSE)指标值分别为0.0489和0.0558,具有较好的拟合效果。在不同故障状态下,MPC相较于传统PID容错控制方案电压恢复时间缩短50%及以上,并在氢气泄露故障状态下,最大压降降低22.2%,证明了所提控制策略的有效性和正确性。

兆瓦级PEMFC系统的设计和应用

质子交换膜燃料电池(PEMFC)可实现电力和热力的联合供应,是支持零碳能源战略的重要技术路径。对兆瓦级PEMFC系统进行介绍与分析,对工程化应用中的实践提供逆变器、变压器、板式换热器和能量管理系统等部件的选型依据与建议,并指出在系统运行中自耗电占比最高的部件为空压机和散热风扇,分别占自耗电总功率的82.0%和10.7%。兆瓦级PEMFC系统在氯碱工厂中的商业化应用,可将原本排空的氢气发电,提高厂区能量利用效率,创造经济效益。

PEMFC船形堵块阴极流场的性能

建立流体体积(VOF)两相流模型,研究船形堵块流道的排水性能。建立不同开孔率的船形堵块流道三维模型,研究船形堵块及开孔率对质子交换膜燃料电池(PEMFC)性能的影响。船形堵块流道峰值净功率密度相较于传统直流道可提升9.4%,相较于同堵塞率下的梯形堵块流道可提高2.9%,具有较好的强化传质作用。通过提高船形堵块流道的开孔率,PEMFC可以获得更好的性能。在相同开孔率下,船形堵块流道的氧气摩尔浓度较直流道和梯形堵块流道分别提高28.6%和14.0%。结果表明,相较于传统直流道,船形堵块流道可降低排水周期和流道内平均水含量,具有更好的排水性能。

基于改进鲸鱼算法优化GRU的PEMFC老化预测

为提高质子交换膜燃料电池(protonexchange membranefuelcells,PEMFC)老化预测的可控性和预测精度,提出一种基于改进的鲸鱼优化算法(improvedwhale optimizationalgorithm, IWOA)优化门控循环单元(gated recurrent unit,GRU)神经网络的PEMFC电压预测方法。采用IWOA获得GRU的最优超参数组,再利用GRU准确预测PEMFC电压。采用静态、准动态和动态工况下3组老化实验数据集,将提出的方法与反向传播神经网络、极限学习机、循环神经网络、长短期记忆神经网络、GRU和鲸鱼算法优化门控循环单元这6种方法相比较,所提出方法具有最高的老化预测和剩余使用寿命(remainingusefullife,RUL)估计精度。在静态、准动态和动态工况下,训练集占比为50%时,相比于GRU,所提出方法的预测结果的均方根误差分别降低56.99%、35.12%和9.95%。因此,该方法能够实现高精度PEMFC老化趋势和RUL预测。

PEMFC空气系统流量和压力协同控制策略设计

为提高质子交换膜燃料电池(PEMFC)空气系统的动态响应性能,避免局部缺气而导致其输出性能降低等问题的出现,针对空气系统存在流量和压力耦合的问题,分别采用PID、前馈解耦控制和模型预测控制(MPC)对空气系统进行控制,通过仿真和台架测试,验证控制算法的有效性。结果表明,两种控制算法相比较PID均具有较好的控制效果,空气流量和空气压力均能快速跟随设定值,PEMFC发动机的输出性能平稳。

加长加宽的PEMFC电堆应力分布一致性仿真与优化

质子交换膜燃料电池可以通过扩大电堆的活性区域反应面积来获得更高的功率,但电堆反应面积扩大后,容易导致膜电极应力分布的不均匀性增加,从而引起燃料电池电化学性能的下降.为此,本研究设计了4种不同结构尺寸的燃料电池电堆,结合等效刚度模型法和有限元软件,分析了扩大反应面积的电堆结构对膜电极应力分布均匀性的影响,并进一步优化电堆内钢带的安装位置,以提升电堆内部接触压力分布均匀性.研究结果表明,膜电极接触压力分布的均匀性对反应区域宽度的变化较为敏感,当活性区域尺寸加宽,电堆内部活性区域的平均应力标准差增加了23.2%.而当活性区域加长,或同时加长和加宽时,相应增加一根捆扎钢带使电堆内部活性区域的平均应力标准差分别减小了8.6%和8.7%,表明适当增加捆扎钢带的数量可以提高电堆内部接触压力分布的均匀性.此外,钢带位置优化结果显示,电堆外侧钢带越靠近端板侧面时,电堆内部活性区域的应力分布越均匀.

考虑耐久性的PEM燃料电池有轨电车自适应优化控制策略

针对燃料电池/锂电池/超级电容混合储能有轨电车在动态负载、启停循环、怠速循环、大功率运行时质子交换膜(PEM)燃料电池寿命衰减情况,提出Pontryagin极小值原理(PMP)与耐久性结合的能量管理策略。通过启停控制策略控制燃料电池的启动与停止,有效降低燃料电池启动次数;利用储能系统总体氢气消耗为经济性代价,燃料电池性能衰退指数为耐久性代价,构建联合代价函数;在满足期望条件下,实现协态变量随荷电状态实时变化的在线适应;将所提策略与传统极小值策略和状态机策略进行仿真对比。结果表明:城市循环工况中所提策略较于传统Pontryagin策略燃料电池峰值电流降低了33.2%,氢气消耗下降了12.50%;郊区循环工况中所提策略较传统Pontryagin策略峰值电流降低了21.88%,氢气消耗下降了40.39%。所提管理策略在不同工况下均有良好的适应能力,解决了传统PMP只能离线应用的缺点,将启停次数控制在较低水平,具有延寿燃料电池的能力。