Parametric analysis of proton exchange membrane fuel cell performance by using the Taguchi method and a neural network

This study proposes a novel parameter optimization method, capable of integrating the neural network and the Taguchi method for parametric analysis of proton exchange membrane fuel cell (PEMFC) performance. Numerous parameters affecting the PEMFC performance are analyzed, such as fuel cell operating temperatures, cathode and anode humidification temperatures, operating pressures, and reactant flow rate. In the traditional design of experiments, the Taguchi method has been popularly utilized in engineering. However, the parameter levels selected to form the orthogonal array in the Taguchi method are discrete, preventing the estimation of the real optimum. This study used the Taguchi method to acquire the primary optimums of the operating parameters in the PEMFC. Each row in the orthogonal array together with its relative responses was used to establish a set of training patterns (input/target pair) to the neural network. The neural network can then construct relationships between the control factors and responses in the PEMFC. The actual optimums of the operating parameters in the PEMFC were obtained by the trained neural network. Experimental results are presented for identifying the proposed approach, which is useful in improving performance for PEMFC and developing electrical system on advanced vehicles and ships.     

Analysis of operating parameters considering flow orientation for the performance of a proton exchange membrane fuel cell using the Taguchi method

This study has applied the L₁₈ 2 × 3⁷ orthogonal array of the Taguchi method to determine the optimal combination of six primary operating parameters (flow orientation, temperature of fuel cell, anode and cathode humidification temperatures, anode, and cathode stoichiometric flow ratios) of a PEM fuel cell. The optimal combination factor is co-flow, a cell temperature of 333 K, an anode humidification temperature of 353 K, a cathode humidification temperature of 333 K, a stoichiometric flow ratio for hydrogen of 2, and a stoichiometric flow ratio for oxygen of 3; and the amount of maximum power is 17.61 W. The results for the experiment indicate that flow orientation, temperature of fuel cell, and anode and cathode humidification temperatures are significant factors for affecting the performance. Furthermore, this study simulates the transport phenomenon and electrochemical reactions using a finite-element method at the optimal combination factor from the experimental results of Taguchi method.     

Parametric analysis of the proton exchange membrane fuel cell performance using design of experiments

Proton exchange membrane fuel cell (PEMFC) performance depends on different fuel cell operating temperatures, humidification temperatures, operating pressures, flow rates, and various combinations of these parameters. This study employed the method of the design of experiments (DOE) to obtain the optimal combination of the six primary operating parameters (fuel cell operating temperatures, operating pressures, anode and cathode humidification temperatures, anode and cathode stoichiometric flow ratios). In the first stage, this study adopted a 2^k−2 fractional factorial design of the DOE to determine whether these factors have significant effects on a response and the interactions between various parameters. Second, the L₂₇(3¹³) orthogonal array of the Taguchi method is utilized to determine the optimal combination of factors for a fuel cell. Based on this study, the operating pressure, the operating temperature, and the interactions between operating temperature and operating pressure have a significant effect on the fuel cell performance. Among them, the operating pressure is the most important contributor. When the operating pressure increases, it should simultaneously lower the effects of other factors. While both the operating temperature and pressure increase simultaneously with that, the other factors are at appropriate conditions, it is possible to improve the fuel cell performance.     

The optimal parameters estimation for rectangular cylinders installed transversely in the flow channel of PEMFC from a three-dimensional PEMFC model and the Taguchi method

The study first applies a three-dimensional model to analyze the cell performance of PEMFCs using rectangular cylinders with various numbers transversely inserted at the axis in the channel, and finds the higher performance with reasonable pressure drop. The Taguchi optimization methodology is then combined with the three-dimensional PEMFC model to determine the optimal combination of five primary operating parameters for the best arrangement of the rectangular cylinders in the channel. The results indicate that the optimal combination factor is a cell temperature of 313 K, an anode humidification temperature of 333 K, a cathode humidification temperature of 333 K, a hydrogen stoichiometric flow ratio of 1.9, and an oxygen stoichiometric flow ratio of 2.7. This study also examines the pressure drop for the channels with rectangular cylinders transversely inserted. Using experimental data verifies the numerical results of the flow field design with rectangular cylinders.     

Parameter design on the multi-objectives of PEM fuel cell stack using an adaptive neuro-fuzzy inference system and genetic algorithms

This work considers a design of a PEM fuel cell (PEMFC) stack that consists of 10 cells and expects to carry out an analysis of performance. In this work, PEMFC performance as affected by different combinations of control factors, such as the cathode and anode operating pressures, the humidification temperatures, and the stoichiometric flow ratio of reaction gas, is studied. On the PEMFC stack performance, the gas supply that is expected to be the minimum and the output power that is hoped to be the maximum are a result of the demand of the multi-objectives characteristics. Due to the Taguchi orthogonal array, the screen experiment is carried out by using a fractional factorial design in order to determine main factors and interaction effects first, and then the robust design is conducted. The intelligent parameter design is developed via an Adaptive Neuro-Fuzzy Inference System combined with the definition of percentage reduction of quality loss (PRQL) in order to supply a fitness function to the genetic algorithms (GA). The best parameter design is proposed after an analysis and comparison is conducted. Finally, the adaptability of prediction for the model created by this approach is confirmed by the confirmation experiment. This work shows that the PEMFC performance is improved by 35.8% via the average PRQL.     

Continuous bubble humidification and control of relative humidity of H2 for a PEMFC system

The proton conductivity of perfluorinated ionomer membrane used in a proton exchange membrane fuel cell (PEMFC) depends largely on the extent of hydration state of the membrane. Sufficient membrane hydration is achieved typically through the humidification of gases prior to feeding them into the fuel cell. Further, hydrogen humidification is known to have a larger impact on the performance of a PEMFC than the oxygen humidification. Bubble humidification has been a widely used method to externally humidify hydrogen. However, to-date a continuous bubble humidification system, which is essential to the continuous operation of the PEMFC system, has not been implemented. The main contributions of this work are (i) a design for continuous humidification of hydrogen for the PEMFC system and (ii) a method to maintain the RH of hydrogen between 93 and 95% (at desired temperature) over a wide range of gas flow rates. One of the key advantages of the proposed design is the flexibility of using recirculated stack coolant water to increase the energy efficiency of the PEMFC system. The design is first tested off-line and then online with a 1 kW stack. Results obtained from both the off-line and online tests indicate that the design successfully meets the demands of an online operation. It is observed that with the use of the proposed humidification scheme, the stack efficiency in terms of power output increases by about 6–19% of the power obtained under dry hydrogen conditions.     

Effects of operating temperatures on performance and pressure drops for a 256 cm proton exchange membrane fuel cell: An experimental study

Cell performance and pressure drop were experimentally investigated for two commercial size 16 cm × 16 cm serpentine flow field proton exchange membrane fuel cells with Core 5621 and Core 57 membrane electrode assemblies at various cell temperatures and humidification temperatures. At cell temperature lower than the humidification temperature, the cell performance improved as the cell temperature increased, while reversely at cell temperature higher than the humidification temperature. At a specified cell temperature, increasing the cathode and/or anode humidification temperature improved the cell performance, and their effects weakened as cell temperature decreased. The effects of the cell and the humidification temperature on the pressure drops were closely related to the reactant feed mode. For the constant stoichiometric flow rate mode, both cathode and anode pressure drops increased as humidification temperature and average current density increased. For the constant mass flow rate mode, both cathode and anode pressure drops increased as humidification temperature increased, while anode pressure drops decreased and cathode pressure drops increased as average current density increased. The optimal cell performance occurred at cell temperature of 65 °C and humidification temperature of 70 °C. The effects of these operating parameters on the cell performance and pressure drop were analyzed based on the catalytic activity, membrane hydration, and cathode flooding.     

Experimental investigation on the dynamic performance of a hybrid PEM fuel cell/battery system for lightweight electric vehicle application

A hybrid system combining a 2 kW air-blowing proton exchange membrane fuel cell (PEMFC) stack and a lead–acid battery pack is developed for a lightweight cruising vehicle. The dynamic performances of this PEMFC system with and without the assistance of the batteries are systematically investigated in a series of laboratory and road tests. The stack current and voltage have timely dynamic responses to the load variations. Particularly, the current overshoot and voltage undershoot both happen during the step-up load tests. These phenomena are closely related to the charge double-layer effect and the mass transfer mechanisms such as the water and gas transport and distribution in the fuel cell. When the external load is beyond the range of the fuel cell system, the battery immediately participates in power output with a higher transient discharging current especially in the accelerating and climbing processes. The DC–DC converter exhibits a satisfying performance in adaptive modulation. It helps rectify the voltage output in a rigid manner and prevent the fuel cell system from being overloaded. The dynamic responses of other operating parameters such as the anodic operating pressure and the inlet and outlet temperatures are also investigated. The results show that such a hybrid system is able to dynamically satisfy the vehicular power demand.     

Parametric analysis of simultaneous humidification and cooling for PEMFCs using direct water injection method

The effects of different operating parameters on humidification and cooling for proton exchange membrane fuel cells (PEMFCs) using direct water injection method were experimentally investigated. Experiments with various injection water temperature, operating pressure and relative humidity of cathode side were carried out. In order to quantitatively analyze the performance of direct water injection method, polarization curves and dew point temperatures of cathode outlet gas were measured. Also, the possible mechanisms of the effect of each parameter were discussed. The experimental results showed that elevation of the injection water temperature and relative humidity of cathode side led to the improvement of stack performance. It resulted from humidification and cooling effect by the evaporation of injected water. Operating pressure also had an effect on the performance of direct water injection method. In pressurized operating condition, the evaporation of injected water was difficult to occur, and the effect of direct water injection method decreased. Based on the experimental results, it was demonstrated that the stack performance was remarkably improved because of humidification and cooling effect from direct water injection method.     

Experimental analysis of cathode flow stoichiometry on the electrical performance of a PEMFC stack

The paper describes an experimental analysis on the effect of cathode flow stoichiometry on the electrical performance of a PEMFC stack. The electrical power output of a PEMFC stack is influenced by several independent variables (factors). In order to analyse their reciprocal influence, an experimental design methodology was adopted in a previous experimental session, to determine which factors deserve particular attention. In this work, a further experimental analysis has been carried out on a very significant factor: cathode stoichiometry. Its effects on the electrical power of the PEMFC stack have been investigated. The tests were performed on a 3.5 kW_el ZSW stack using the GreenLight GEN VI FC Test Station. The stack characteristics have been obtained running a predefined loading pattern. Some parameters were kept constant during the tests: anode and cathode inlet temperature, anode and cathode inlet relative humidity, anode stoichiometry and inlet temperature of the cooling water. The experimental analysis has shown that an increase in air stoichiometry causes a significant positive effect (increment) on electric power, especially at high-current density, and up to the value of 2 stoichs. These results have been connected to the cathode water flooding, and a discussion was performed concerning the influence of air stoichiometry on electrode flooding at different levels of current density operation.     

Water management in a novel proton exchange membrane fuel cell stack with moisture coil cooling

Water flooding causes severe degradation of the performance and lifetime of proton exchange membrane fuel cell (PEMFC). In this study, a novel PEMFC stack with in-built moisture coil cooling was designed and the effects of moisture coil cooling on water management in the new PEMFC stack under various operating conditions were investigated. The result showed that the performance of the PEMFC stack was significantly improved due to the moisture condensation under high current density, high operating temperature, high relative humidity and high operating pressure. The output power was increases by 21.62% (525.71 W) at 1600·mA cm⁻² while the increased parasitic power was no more than 35W. Moreover, degradation of the cathode catalyst layer after 100 h operation was also reduced by using moisture coil cooling. Compared with the situation without moisture condensation, the maximum decay rate of the cathode catalyst layer thickness after 100 h operation was reduced by 13.01%. Accordingly, the novel design is valuable and can be widely used in the future design of PEMFC.     

Simulation of an air conditioning absorption refrigeration system in a co-generation process combining a proton exchange membrane fuel cell

In this work, a computer simulation program was developed to determine the optimum operating conditions of an air conditioning system during the co-generation process. A 1 kW PEMFC was considered in this study with a chemical/electrical theoretical efficiency of 40% and a thermal efficiency of 30% applying an electrical load of 100%. A refrigeration-absorption cycle (RAC) operating with monomethylamine–water solutions (MMA–WS), with low vapor generation temperatures (up to 80 °C) is proposed in this work. The computer simulation was based on the refrigeration production capacity at the maximum power capacity of the PEMFC. Heat losses between the fuel cell and the absorption air conditioning system at standard operating conditions were considered to be negligible. The results showed the feasibility of using PEMFC for cooling, increasing the total efficiency of the fuel cell system.     

Maximization of high-temperature proton exchange membrane fuel cell performance with the optimum distribution of phosphoric acid

A proton exchange membrane fuel cell (PEMFC) using a controlled amount of phosphoric acid (PA) in a membrane-electrode assembly (MEA) is operated at 150 °C without humidification of the cells. The effects on MEA performance of Pt loading and the amount of PA in the cathode are investigated. The catalyst utilization is maximized by optimizing the PA content in the cathodes and results in lowering of the Pt loading in the MEA. In-situ cyclic voltammetry is used to confirm that the highest value of the active electrochemical area is achieved with the optimum amount of PA in the cathode. The transient response of cell voltage during current density–voltage experiments (I–V curve) is also found to be affected by the amount of PA in the electrodes.     

Intelligent uninterruptible power supply system with back-up fuel cell/battery hybrid power source

This paper presents the development of an intelligent uninterruptible power supply (UPS) system with a hybrid power source that comprises a proton-exchange membrane fuel cell (PEMFC) and a battery. Attention is focused on the architecture of the UPS hybrid system and the data acquisition and control of the PEMFC. Specifically, the hybrid UPS system consists of a low-cost 60-cell 300 W PEMFC stack, a 3-cell lead–acid battery, an active power factor correction ac–dc rectifier, a half-bridge dc–ac inverter, a dc–dc converter, an ac–dc charger and their control units based on a digital signal processor TMS320F240, other integrated circuit chips, and a simple network management protocol adapter. Experimental tests and theoretical studies are conducted. First, the major parameters of the PEMFC are experimentally obtained and evaluated. Then an intelligent control strategy for the PEMFC stack is proposed and implemented. Finally, the performance of the hybrid UPS system is measured and analyzed.     

Externally reformed solid oxide fuel cell–micro-gas turbine (SOFC–MGT) hybrid systems fueled by methanol and di-methyl-ether (DME)

Solid oxide fuel cell–micro-gas turbine (SOFC–MGT) hybrid power plants integrate a solid oxide fuel cell and a micro-gas turbine and can achieve efficiencies of over 60% even for small power outputs (200–500 kW). The SOFC–MGT systems currently developed are fueled with natural gas, which is reformed inside the same stack, but the use of alternative fuels can be an interesting option. In particular, as the reforming temperature of methanol and di-methyl-ether (DME) (200–350 °C) is significantly lower than that of natural gas (700–900 °C), the reformer can be sited outside the stack. External reforming in SOFC–MGT plants fueled by methanol and DME enhances efficiency due to improved exhaust heat recovery and higher voltage produced by the greater hydrogen partial pressure at the anode inlet. The study carried out in this paper shows that the main operating parameters of the fuel reforming section (temperature and steam-to-carbon ratio (SCR)) must be carefully chosen to optimise the hybrid plant performance. For the stoichiometric SCR values, the optimum reforming temperature for the methanol fueled hybrid plant is approximately 240 °C, giving efficiencies of about 67–68% with a SOFC temperature of 900 °C (the efficiency is about 72–73% at 1000 °C). Similarly, for DME the optimum reforming temperature is approximately 280 °C with efficiencies of 65% at 900 °C (69% at 1000 °C). Higher SCRs impair stack performance. As too small SCRs can lead to carbon formation, practical SCR values are around one for methanol and 1.5–2 for DME.     

A preliminary study of a miniature planar 6-cell PEMFC stack combined with a small hydrogen storage canister

The fabrication and performance evaluation of a miniature 6-cell PEMFC stack based on Micro-Electronic-Mechanical-System (MEMS) technology is presented in this paper. The stack with a planar configuration consists of 6-cells in serial interconnection by spot welding one cell anode with another cell cathode. Each cell was made by sandwiching a membrane-electrode-assembly (MEA) between two flow field plates fabricated by a classical MEMS wet etching method using silicon wafer as the original material. The plates were made electrically conductive by sputtering a Ti/Pt/Au composite metal layer on their surfaces. The 6-cells lie in the same plane with a fuel buffer/distributor as their support, which was fabricated by the MEMS silicon–glass bonding technology. A small hydrogen storage canister was used as fuel source. Operating on dry H₂ at a 40 ml min⁻¹ flow rate and air-breathing conditions at room temperature and atmospheric pressure, the linear polarization experiment gave a measured peak power of 0.9 W at 250 mA cm⁻² for the stack and average power density of 104 mW cm⁻² for each cell. The results suggested that the stack has reasonable performance benefiting from an even fuel supply. But its performance tended to deteriorate with power increase, which became obvious at 600 mW. This suggests that the stack may need some power assistance, from say supercapacitors to maintain its stability when operated at higher power.     

Heat and power management of a direct-methanol-fuel-cell (DMFC) system

In this paper, we describe the heat and the power management of a direct methanol fuel cell system. The system consists mainly of a direct methanol fuel cell stack, an anode feed loop with a heat exchanger and on the cathode side, a compressor/expander unit. The model calculations are carried out by analytical solutions for both mass and energy flows. The study is based on measurements on laboratory scale single cells to obtain data concerning mass and voltage efficiencies and temperature dependence of the cell power. In particular, we investigated the influence of water vaporization in the cathode on the heat management of a direct-methanol-fuel-cell (DMFC) system. Input parameters were the stack temperature, the cathode pressure and the air flow rate. It is shown that especially at operating temperatures above 90 °C, the combinations of pressure and air flow rate are limited because of heat losses due to vaporization of water in the cathode.     

High performance PEMFC stack with open-cathode at ambient pressure and temperature conditions

An open-air cathode proton exchange membrane fuel cell (PEMFC) was developed. This paper presents a study of the effect of several critical operating conditions on the performance of an 8-cell stack. The studied operating conditions such as cell temperature, air flow rate and hydrogen pressure and flow rate were varied in order to identify situations that could arise when the PEMFC stack is used in low-power portable PEMFC applications. The stack uses an air fan in the edge of the cathode manifolds, combining high stoichiometric oxidant supply and stack cooling purposes. In comparison with natural convection air-breathing stacks, the air dual-function approach brings higher stack performances, at the expense of having a lower use of the total stack power output. Although improving the electrochemical reactions kinetics and decreasing the polarization effects, the increase of the stack temperature lead to membrane excessive dehydration (loss of sorbed water), increasing the ohmic resistance of the stack (lower performance).     

Parameter optimization for a PEMFC model with a hybrid genetic algorithm

Many steady‐state models of polymer electrolyte membrane fuel cells (PEMFC) have been developed and published in recent years. However, models which are easy to be solved and feasible for engineering applications are few. Moreover, rarely the methods for parameter optimization of PEMFC stack models were discussed. In this paper, an electrochemical‐based fuel cell model suitable for engineering optimization is presented. Parameters of this PEMFC model are determined and optimized by means of a niche hybrid genetic algorithm (HGA) by using stack output‐voltage, stack demand current, anode pressure and cathode pressure as input–output data. This genetic algorithm is a modified method for global optimization. It provides a new architecture of hybrid algorithms, which organically merges the niche techniques and Nelder–Mead's simplex method into genetic algorithms (GAs). Calculation results of this PEMFC model with optimized parameters agreed with experimental data well and show that this model can be used for the study on the PEMFC steady‐state performance, is broader in applicability than the earlier steady‐state models. HGA is an effective and reliable technique for optimizing the model parameters of PEMFC stack. Copyright © 2005 John Wiley & Sons, Ltd.