Artificial intelligence based structural optimization of solid oxide fuel cell with three-dimensional reticulated trapezoidal flow field

Three-dimensional Reticulated trapezoidal flow field (RTFF) is promising in improving the performance and durability of the solid oxide fuel cell (SOFC). However, the structural complexity makes it challenging for the geometry configuration of the splitter and mixer. To this end, an intelligent optimization framework is proposed by coupling artificial neural network (ANN) and non-dominated sorting genetic algorithm-II (NSGA-II), in order to maximize the net power density and oxygen uniformity simultaneously. The ANN prediction model is trained to obtain the computationally efficient surrogate model of the computational fluid dynamics (CFD) numerical simulation. NSGA-II is used for the multi-objective optimization of the RTFF structural parameters. The results illustrate that the prediction model is of high prediction precision and generalization capability. In comparison to SOFC with conventional parallel flow fields (CPFF), the degree of the performance improvement of SOFC with optimized RTFF depends on the working condition, i.e., fuel and air flow rates and operating temperatures. The SOFC with the optimal RTFF achieves a higher molar concentration of oxygen and a more uniform distribution of oxygen and current density than the CPFF SOFC. The proposed optimization framework provides an efficient design method for the development of the next-generation SOFC flow field.     

A novel surrogate model for channel geometry optimization of PEM fuel cell based on Bagging-SVM Ensemble Regression

Channel structure plays an important role on the performance of proton exchange membrane fuel cell (PEMFC). In this study, the channel geometry of a PEMFC is optimized through genetic algorithm to obtain better performance. For the first time, a machine learning method called Bagging Ensemble Regression is employed as the surrogate model to calculate the fitness value of the algorithm, which accelerates the optimization process. First, a three-dimensional PEMFC simulation model is developed as the optimization prototype through CFD technology. Second, the Bagging ensemble model is trained through training data obtained from the CFD model. Then the Bagging ensemble model is integrated into the genetic algorithm to conduct the optimization process. Finally, the optimal model obtained is compared with the optimization prototype in terms of polarization curves, pressure drop, and reactant distribution, and the advantages of using Bagging ensemble model are discussed. Results show that the optimal model has a smaller pressure drop and a more uniform reactant distribution than the basic model at the expense of just a little power density. The presented surrogate model shows high prediction accuracy with only a small amount of training data, which is superior to the commonly used surrogate models.     

Optimization of block structure parameters of PEMFC novel block channels using artificial neural network

Flow channel design is critically important to the performance of proton exchange membrane fuel cell (PEMFC) due to its great influence on liquid water removal and mass and heat transfer. Block flow channel shows good prospect to improve liquid water removal and mass transport, benefiting the PEMFC performance. In this study, the block structures, namely the length, width and height of the block, are optimized for a novel block channel using data-driven surrogate model based on the artificial neural network (ANN). The training/test datasets are obtained from a three-dimensional multi-phase model based on the volume of fluid (VOF) method, with the water removal time (T) and the maximum channel pressure drop (ΔP) taken as the output and optimization objectives. The results show that the ANN prediction agrees well with the physical model results, with the coefficient of determination (R²) of T and ΔP are 0.99598 and 0.99677, respectively. The block parameters are further optimized using the comprehensive scoring method considering both T and ΔP. The block parameters with the length of 0.8 mm, width of 0.375 mm and height of 0.75 mm are found to be the optimum in terms of the highest score. The optimum parameters obtained from the data-driven surrogate model are verified by the physical model, indicating that the ANN model is an effective and fast method to optimize block structure of block flow channel from the perspective of liquid water removal and channel pressure drop.     

Numerical analysis on the effects of manifold design on flow uniformity in a large proton exchange membrane fuel cell stack

The size and configuration of manifold can affect the flow characteristics and uniformity in proton exchange membrane fuel cell (PEMFC) stack; then its efficiency and service life. Based on the simulation results of a single fuel cell considering electrochemical reaction, a stack model with 300 porous media is established to numerically investigate the performances of a large commercial PEMFC stack. The effects of manifold width and configuration type on the pressure drop and species concentration are studied by computational fluid dynamics (CFD). The results show that the uniformity for most cases of U-type configuration is better than those of Z-type configuration. For U-type configuration, a very good uniformity can be obtained by selecting anode inlet manifold width of 20 mm and anode outlet manifold in range from 25 to 30 mm; the uniformity is bad for all cathode inlet manifold width, relatively better uniformity can be achieved by adjusting cathode outlet manifold width. For Z-type configuration, bad uniformity is found for cathode inlet and outlet manifold with all width; a relatively good uniformity can be obtained with suitable anode manifold width of 35 mm. The research can provide some references to improve gas distribution uniformity in large PEMFC stacks.     

CFD investigating the effects of different operating conditions on the performance and the characteristics of a high-temperature PEMFC

The effects of different operating conditions on the performance and the characteristics of a high-temperature proton exchange membrane fuel cell (PEMFC) are investigated using a three-dimensional (3-D) computational fluid dynamics (CFD) fuel-cell model. This model consists of the thermal-hydraulic equations and the electrochemical equations. Different operating conditions studied in this paper include the inlet gas temperature, system pressure, and inlet gas flow rate, respectively. Corresponding experiments are also carried out to assess the accuracy of this CFD model. Under the different operating conditions, the PEMFC performance curves predicted by the model correspond well with the experimentally measured ones. The performance of PEMFC is improved as the increase in the inlet temperature, system pressure or flow rate, which is precisely captured by the CFD fuel cell model. In addition, the concentration polarization caused by the insufficient supply of fuel gas can be also simulated as the high-temperature PEMFC is operated at the higher current density. Based on the calculation results, the localized thermal-hydraulic characteristics within a PEMFC can be reasonably captured. These characteristics include the fuel gas distribution, temperature variation, liquid water saturation distribution, and membrane conductivity, etc.     

Optimal design of baffles locations with interdigitated flow channels of a centimeter-scale proton exchange membrane fuel cell

In the present study, the simplified conjugate-gradient method (SCGM) is combined with commercial CFD code to build an optimizer for designing the baffles locations with interdigitated channels of a centimeter-scale proton exchange membrane fuel cell (PEMFC). Using the optimizer, the locations of the baffles are adjusted toward the maximization of the average current density of the flow field. The approach is developed by using the commercial CFD code as the direct problem solver, which is able to provide the numerical solutions for the three-dimensional mass, momentum and species transport equations as well as to predict the electron conduction and proton migration taking place in a PEMFC. Results show that the optimal design process of the locations of the baffles can be completed by using the present optimization approach in just a finite number of iterations. The optimization process may lead to an appreciable increase by 14% in the power output from the fuel cell.     

Numerical simulation analysis of the performance on the PEMFC with a new flow field designed based on constructal-theory

The design of the flow field structure has an important impact on the performance of PEMFC. An excellent design of the flow field will optimize the gas-liquid distribution inside the fuel cell, and enhance the diffusion of the reactant gases while reducing problems such as water flooding or uneven mass transfer of reactants, thus improving the overall performance of the cell. A new form of flow field based on the design ideas of Constructal-theory and Murray's Law was proposed in this paper. In this study, the PEMFC with the new and conventional flow fields were compared under the same conditions, and it is proved that the cell with the new flow field has a more balanced performance on output power and global pressure drop in contrast with conventional flow fields. In this study, the output power density of the PEMFC with the new flow field increased by an average of 1.35% compared to the PEMFC with Parallel flow field and Single Channel Serpentine flow field, and the pressure drop was reduced by 47.67% and 90.06% respectively compared to the PEMFC with the Single Channel Serpentine flow field and Double Channel Serpentine flow field. Meanwhile, the distribution of current density characteristics in a PEMFC with the new flow field was investigated and optimization of its structure size is analyzed. The reason for its non-uniform distribution of current density was revealed in this study, and an improvement scheme was proposed to improve the uniformity of current density, and the results of structural optimization research will have a certain guiding effect on practical applications.     

Influences of assembly pressure and flow channel size on performances of proton exchange membrane fuel cells based on a multi-model

In this work, assembly pressure and flow channel size on proton exchange membrane fuel cell performance are optimized by means of a multi-model. Based on stress-strain data of the SGL-22BB GDL obtained from its initial compression experiments, Young's modulus with different ranges of assembly pressure fits well through modeling. A mechanical model is established to analyze influences of assembly pressure on various gas diffusion layer parameters. Moreover, a CFD calculation model with different assembly pressures, channel width, and channel depth are established to calculate PEMFC performances. Furthermore, a BP neural network model is utilized to explore optimal combination of assembly pressure, channel width and channel depth. Finally, the CFD model is used to validate effect of size optimization on PEMFC performance. Results indicate that gap change of GDL below bipolar ribs is more remarkable than that below channels under action of the assembly pressure, making liquid water easily transported under high porosity, which is conducive to liquid water to the channels, reduces the accumulation of liquid water under the ribs, and enhances water removal in the PEMFC. Affected by the assembly force, change of GDL porosity affects its diffusion rate, permeability and other parameters, which is not conducive to mass transfer in GDL. Optimizing the depth and different dimensions through width of the flow field can effectively compensate for this effect. Therefore, the PEMFC performance can be enhanced through the comprehensive optimization of the assembly force, flow channel width and flow channel depth. The optimal parameter is obtained when assembly pressure, channel width and channel depth are set as 0.6 MPa, 0.8 mm, and 0.8 mm, respectively. The parameter optimization enhances the mass transfer, impedance, and electrochemical characteristics of PEMFC. Besides, it effectively enhances the quality transfer efficiency inside GDL, prevents flooding, and reduces concentration loss and ohmic loss.     

Neural network model of 100 W portable PEM fuel cell and experimental verification

The inherent properties of artificial neural networks (ANNs) such as low sensitivity to noise and incomplete information make the ANN a promising candidate to model the fuel cell system. In this paper, an ANN-based model of 100 W portable direct hydrogen fed proton exchange membrane fuel cell (PEMFC) is presented. The model is built based on experimentally collected data from a portable 100 W direct hydrogen fed PEMFC in the authors’ laboratory. A multilayer feedforward ANN with back-propagation training algorithm is used to model the portable PEMFC. The ANN consists of fully connected four layers network with two hidden layers. The PEMFC ANN model is trained using extracted data from experimentally measured and calculated parameters. To validate the model, the outputs of the PEMFC ANN are compared against experimental data and results from a dynamic model of portable direct hydrogen fed PEMFC. In addition, three statistical indices to measure variations, unbiasedness (precision), and accuracy in voltage, power, and hydrogen flow are used to evaluate the PEMFC ANN model performance. The indices indicate that the maximum variations, unbiasedness, and accuracy of the voltage, power, and hydrogen flow are 1.45%, 2.04%, and 1.90%, respectively, which shows a close agreement between the outputs of the PEMFC ANN and the experimental results.     

Experimental study and optimization of flow field structures in proton exchange membrane fuel cell under different anode modes

As one of the critical components in the proton exchange membrane fuel cell (PEMFC), the flow field is crucial to the improvement of cell performance. However, the current research on flow field structure lacks consideration of the influence of different anode modes, which makes the existing flow field structure rules have limitations in the practical application of PEMFC. In this paper, the PEMFC characteristics of parallel flow field, S-shaped flow field, multi-serpentine flow field and single-serpentine flow field at the cathode side are compared experimentally in the dead-end anode (DEA) mode and hydrogen circulation anode (HCA) mode, respectively. Especially, the spatial current density distribution and parasitic power of different flow field structures are measured. The results show that the performance trends of different flow field structures change with the DEA and HCA anode modes. In DEA mode, the PEMFC is prone to flooding, and the flow field with high gas velocity in the channel has better drainage ability, which can obtain higher cell performance. The HCA mode is helpful for the discharge of water in the PEMFC, which effectively alleviates the adverse impact of water accumulation on the overall performance, and the mass transport ability of the flow field structure plays a leading role in the cell performance improvement. In addition, although the high gas flow velocity has better drainage ability in the flow field, it may lead to a decrease in the current density distribution uniformity and PEMFC net output power density. Based on the comprehensive consideration of the experimental results, the multi-serpentine flow field is more suitable for DEA mode, and the S-shaped flow field is more suitable for HCA mode.     

Geometry optimization and performance analysis of a new tapered slope cathode flow field for PEMFC

In proton exchange membrane fuel cell (PEMFC), the cathode flow field structure affects the performance of PEMFC. In a previous study, we proposed a new tapered slope flow field (TSFF). In this study, Ansys Fluent software was used to simulate a PEMFC with a tapered slope cathode flow field structure. The results show that the performance of the TSFF is superior, the drainage efficiency is higher, and the oxygen mass fraction distribution is more uniform. Furthermore, comparing double-sided TSFF with different lengths, the PEMFC performance first increases and then decreases as the length of the tapered slope increases. In particular, the oxygen mass fraction and current density distributions are more uniform in the double-sided TSFF with L = 1.2 mm and the PEMFC performance is the best, and compared with the serpentine flow field, the maximum power density of PEMFC is increased by 5.89%. A detailed analysis of the geometric structure of the flow field can help us understand the reasons why the TSFF structure improves the performance of PEMFC and comprehensively evaluate the flow field performance. The TSFF enhances the flow rate of reactant diffusion to the CL and enhances the mass transfer downstream of the flow field. In particular, when L = 1.2 mm, the relative magnitude of the reactant flow resistance loss in the double-sided TSFF was 1.86% smaller than that of the serpentine flow field.     

Numerical investigation of the performance of symmetric flow distributors as flow channels for PEM fuel cells

This work reports on the performance of a single PEM fuel cell using symmetric flow patterns as gas delivery channels. Three flow patterns, two symmetric and one serpentine, are taken from the literature on cooling of electronics and they are implemented in a computational model as gas flow channels in the anode and cathode side of a PEMFC. A commercial CFD code was used to solve the physics involved in a fuel cell namely: the flow field, the mass conservation, the energy conservation, the species transport, and the electric/ionic fields under the assumptions of steady state and single phase. An important feature of the current modeling efforts is the analysis of the main irreversibilities at different current densities showing the main energy dissipation phenomena in each cell design. Also, the hydraulic performance of the flow patterns was studied by evaluating the pressure drop and pumping power. The first part of this work reveals the advantages of using a serpentine pattern over the base symmetric distributors. The second part is an optimization of the symmetric patterns using the entropy minimization criteria. Such an optimization led to the creation of a flow structure that promotes an improved performance from the point of view of power generation, uniformity of current density, and low pumping power.     

Channel geometry optimization using a 2D fuel cell model and its verification for a polymer electrolyte membrane fuel cell

This paper studies the optimization method of channel geometries for a proton exchange membrane fuel cell (PEMFC) using a genetic algorithm (GA). The channel and rib widths and channel height are selected as geometry variables. The fuel cell output power is chosen as the cost function for the optimization. In this paper, an in-house genetic algorithm is constructed, and the fuel cell output power is obtained using an interfacing program connected to a commercial computational fluid dynamics (CFD) tool, COMSOL, in a Matlab environment. The 2D PEMFC is used to calculate the performance cost function for computational time and cost. The calculated output power of the PEMFC is delivered to the in-house GA program to check for optimality. After the optimality is checked, the new geometry data is fed back to the COMSOL to calculate the PEMFC output power until the optimization process is finished. Experiments are conducted to support the optimized results using three different channel geometries: channel-to-rib width ratios of 0.5:1, 1:1, and 2:1. A full 3D PEMFC CFD model is constructed using COMSOL to support the 2D CFD optimization results. This paper shows the possibility of applying the geometry optimization process to sophisticated electrochemical reaction systems, such as a PEMFC, using a GA and a commercial CFD tool on the Matlab platform. The geometries and materials can be optimized using this approach to obtain the most efficient performance of an electrochemical system.     

Thermal and electrochemical performance analysis of a proton exchange membrane fuel cell under assembly pressure on gas diffusion layer

In this study, the effect of clamping pressure on the performance of a proton exchange membrane fuel cell (PEMFC) is investigated for three different widths of channel. The deformation of gas diffusion layer (GDL) due to clamping pressure is modeled using a finite element method, and the results are applied as inputs to a CFD model. The CFD analysis is based on finite volume method in non-isothermal condition. Also, a comparison is made between three cases to identify the geometry that has the best performance. The distribution of temperature, current density and mole fraction of oxygen are investigated for the geometry with best performance. The results reveal that by decreasing the width of channel, the performance of PEMFC improves due to increase of flow velocity. Also, it is found that intrusion of GDL into the gas flow channel due to assembly pressure deteriorates the PEMFC performance, while decrease of GDL thickness and GDL porosity have smaller effects. It is shown that assembly pressure has a minor effect on temperature profile in the membrane-catalyst interface at cathode side. Also, assembly pressure has a significant effect on ohmic and concentration losses of PEMFC at high current densities.     

Shape Optimization of a Dimpled Channel to Enhance Heat Transfer Using a Weighted-Average Surrogate Model

Shape optimization of a rectangular channel with the opposite walls roughened by staggered arrays of dimples has been performed not only to enhance turbulent heat transfer but also to reduce friction loss. The dimpled channel shape is defined by three geometric design variables, and the design points within design space are selected using Latin hypercube sampling. The shape of the channel is optimized with three-dimensional (3-D) Reynolds-averaged Navier–Stokes analysis and surrogate approximation methods. A weighted-sum method for multi-objective optimization is applied to integrate multiple objectives related to heat transfer and friction loss into a single objective. A weighted-average surrogate model is employed for this optimization. By the optimization, the objective function value is improved largely and heat transfer rate is increased much higher than pressure loss increase due to shape deformation. The optimum design results in lower channel height, wider dimple spacing, and deeper dimple. The flow mechanism shows the heat transfer rate is increased mainly in the rear portion of the dimple.     

基于CFD模拟的某低速柴油机排气集管结构优化设计

为判断某低速柴油机排气集管设计的合理性,对该排气集管的内部流场进行了 CFD分析.分析表明:原始排气集管结构设计存在问题.对此进行了优化改进.优化前后的CFD对比分析表明:优化后排气集管内部流道得到改善,内截面速度均匀性提高,压力损失减小,排气集管整体性能得到明显提高.     

Novel biometric flow slab design for improvement of PEMFC performance

Designing a better flow slab is important to cell performance because of its significant influence on the total pressure drop and flow uniformity. Two novel biometric flow slabs, BFF1 and BFF2, which are addressed in this study, are believed to enhance the capability of oxygen transportation and promote the liquid water removal. Hence, its possession of a higher flow uniformity and lower pressure drop would produce a better power performance than the serpentine and parallel flow. These findings with respect to the design of biometric flow slab could be useful to promote the cell performance of PEMFC, and could even be expanded to other cell types.     

Experimental analysis of optimal performance for a 5 kW PEMFC system

This paper investigates the issue of performance optimization for proton exchange membrane fuel cell (PEMFC) system. In PEMFC system, the system efficiency is the key parameters to evaluate the system performance which is sensitive to the air flow rate. Thus, the careful selection of the air flow rate is crucial to ensure efficient, reliable and durable operation of the PEMFC system. In this paper, the dynamic response of the system under variable air flow rate is studied in detail by means of experiments on the built 5 kW PEMFC system with 110 cells and a catalyst active area of 250 cm². The oxygen excess ratio (OER) is defined to indicate the state of oxygen supply. The experimental results show that the maximum efficiency is existed under certain net current. The OER conditions have the optimal characteristic for system efficiency. Through the optimization of system performance, the system efficiency can be increased by 12.2% on average. At the same time, the system dynamic characteristic under oxygen starvation and oxygen saturation are analyzed in detail based on the experimental data.