A fault diagnosis model for proton exchange membrane fuel cell based on impedance identification with differential evolution algorithm

An effective online fault diagnosis system is of great significance to improve the reliability of fuel cell vehicles. In this paper, a fault diagnosis model for proton exchange membrane fuel cells is proposed. Firstly, the tests of electrochemical impedance spectroscopy under different fault types (flooding, drying, air starvation) and fault degrees (minor, moderate, severe) are carried out, and each polarization loss of the fuel cell is denoted by an equivalent circuit model (ECM). Then, the parameters of the ECM are identified by the proposed random mutation differential evolution algorithm. Furthermore, the parameters identified under different fault conditions are used to train and test a probabilistic neural network-based fault diagnosis model. The fault diagnosis model achieves diagnosis accuracies of 100% for the fault type and 96.67% for the fault degree. By setting operating conditions with different fault degrees, the fault diagnosis model proposed in this paper can realize the fault type and fault degree diagnosis, effectively avoiding the misjudgment of fault types, and is effective for improving the reliability of the fuel cell system.     

On-line fault diagnostic system for proton exchange membrane fuel cells

In this paper, a supervisor system, able to diagnose different types of faults during the operation of a proton exchange membrane fuel cell is introduced. The diagnosis is developed by applying Bayesian networks, which qualify and quantify the cause–effect relationship among the variables of the process. The fault diagnosis is based on the on-line monitoring of variables easy to measure in the machine such as voltage, electric current, and temperature. The equipment is a fuel cell system which can operate even when a fault occurs. The fault effects are based on experiments on the fault tolerant fuel cell, which are reproduced in a fuel cell model. A database of fault records is constructed from the fuel cell model, improving the generation time and avoiding permanent damage to the equipment.     

Chloride contamination effects on proton exchange membrane fuel cell performance and durability

Chlorine is a major fuel contaminant when by-product hydrogen from the chlor-alkali industry is used as the fuel for proton exchange membrane (PEM) fuel cells. Understanding the effects of chlorine contamination on fuel cell performance and durability is essential to address fuel cell applications for the automotive and stationary markets. This paper reports our findings of chloride contamination effects on PEM fuel cell performance and durability, as our first step in understanding the effects of chlorine contamination.Fuel cell contamination tests were conducted by injecting ppm levels of contaminant into the fuel cell from either the fuel stream or the air stream. In situ and ex situ diagnosis were performed to investigate the contamination mechanisms. The results show that cell voltage during chloride contamination is characterized by an initial sudden drop followed by a plateau, regardless of which side the contaminant is introduced into the fuel cell. The drop in cell performance is predominantly due to increased cathode charge transfer resistance as a result of electrochemical catalyst surface area (ECSA) loss attributable to the blocking of active sites by Cl⁻ and enhanced Pt dissolution.     

Proton exchange membrane fuel cell multi-physical dynamics and stack spatial non-homogeneity analyses

This paper presents a multi-physical dynamic fuel cell stack model. This model covers three major physical domains: electrical, fluidic and thermal. The dynamic model in each domain is presented. The fuel cell stack model is obtained by stacking method from a generalized single cell model, thus the spatial effect through the stack can be modelled and observed. The stack model is validated temporally and spatially against a Ballard NEXA 1.2 kW 47 cells fuel cell stack. Then, the dynamic behaviour in each physical domain is analysed. It can be approximated by a first order system, thus the expressions of time constants in different domain are obtained. Finally, the fuel cell stack spatial non-homogeneity is analysed. From the results, a fuel cell stack model reduction method is proposed in order to reduce the computation time during simulations. The reduced fuel cell stack model is validated against the full model.     

基于KMO-PCA-BP的燃料电池堆输出电压预测方法

质子交换膜燃料电池输出电压为燃料电池健康状态和故障诊断的重要指标,输出电压受单电池电压、工作温度、气体流量、物质流量等参数的影响难以准确预测.为此根据燃料电池实验平台采集的数据集,进行KMO(Kaiser Meyer Olkin)相关性分析,验证数据集适合主成分分析.采用主成分分析随原始数据进行降维处理,确定影响燃料电...     

Numerical study of assembly pressure effect on the performance of proton exchange membrane fuel cell

The performance of the fuel cell is affected by many parameters. One of these parameters is assembly pressure that changes the mechanical properties and dimensions of the fuel cell components. Its first duty, however, is to prevent gas or liquid leakage from the cell and it is important for the contact behaviors of fuel cell components. Some leakage and contact problems can occur on the low assembly pressures whereas at high pressures, components of the fuel cell, such as bipolar plates (BPP), gas diffusion layers (GDL), catalyst layers, and membranes, can be damaged. A finite element analysis (FEA) model is developed to predict the deformation effect of assembly pressure on the single channel PEM fuel cell in this study. Deformed fuel cell single channel model is imported to three-dimensional, computational fluid dynamics (CFD) model which is developed for simulating proton exchange membrane (PEM) fuel cells. Using this model, the effect of assembly pressure on fuel cell performance can be calculated. It is found that, when the assembly pressure increases, contact resistance, porosity and thickness of the gas diffusion layer (GDL) decreases. Too much assembly pressure causes GDL to destroy; therefore, the optimal assembly pressure is significant to obtain the highest performance from fuel cell. By using the results of this study, optimum fuel cell design and operating condition parameters can be predicted accordingly.     

Statistical design of experiment approach for modeling and optimization of PEM fuel cell

Polymer electrolyte membrane (PEM) fuel cell has many input factors and it is very difficult to find which input factor affects response or output factor significantly. The general method of changing one factor at a time is statistically not correct because the interaction of the factors also affects the response in most of the cases. Mathematical and simulation models are important tools for designing and analysis of fuel cell-based systems. In this paper, first, a protocol for development of a 25-cm² active area, high performance, PEM fuel cell is presented and then its simulation model is developed using the first principle in MATLAB SIMULINK. Full factorial statistical design of experiment methodology is used to develop first- and second-order Metamodels (Mathematical model of simulation model) for PEM fuel cell to find which input factors affect the response variables significantly. Validation of the Metamodels is checked by various statistical tests, viz, normality, regression analysis, analysis of variance, and lack of fit. Steepest ascent method is used to find the maximum power delivered by PEM fuel cell within the defined ranges of input factors.     

Diagnosis of polymer electrolyte fuel cells failure modes (flooding & drying out) by neural networks modeling

Fault diagnosis and durability of Polymer Electrolyte Fuel Cells (PEFCs) have been identified among the critical issues that need to be overcome for a commercial viability of these power sources.Fuel cells fault diagnosis requires the knowledge of a number of fundamental parameters such as applied current, air inlet flow rate Q, stack temperature and dew point temperature that usually need a special monitoring system and a specifically adapted fuel cell geometry. This might be difficult and even impossible in many fuel cell stacks. Such a constraint could only be possible in a laboratory setup and is not adapted to real application. Moreover, for the transportation application, which aims at minimizing the embedded instrumentation, simple diagnosis methods involving non-intrusive and easy-to-monitor parameters are highly desired.This paper presents a diagnosis procedure of water management issues in fuel cell, namely flooding and drying out, based on a limited number of parameters that are, besides, easy-to-monitor.This procedure uses a black-box model based on neural networks that simulates, in case of healthy operation, the evolution of pressure drop at the cathode as well as fuel cell voltage. Two residuals are generated from the comparison between the actual operation of the fuel cell and the parameters calculated by a neural network in case of normal operation.The two residuals analysis permits the detection (by the means of comparison with a pre-determined threshold) and the classification of fuel cell’s states-of-health between flooding, drying out or normal operation.     

Dynamic modeling and simulation of air-breathing proton exchange membrane fuel cell

Small fuel cells have shown excellent potential as alternative energy sources for portable applications. One of the most promising fuel cell technologies for portable applications is air-breathing fuel cells. In this paper, a dynamic model of an air-breathing PEM fuel cell (AB-PEMFC) system is presented. The analytical modeling and simulation of the air-breathing PEM fuel cell system are verified using Matlab, Simulink and SimPowerSystems Blockset. To show the effectiveness of the proposed AB-PEMFC model, two case studies are carried out using the Matlab software package. In the first case study, the dynamic behavior of the proposed AB-PEMFC system is compared with that of a planar air-breathing PEM fuel cell model. In the second case study, the validation of the air-breathing PEM fuel cell-based power source is carried out for the portable application. Test results show that the proposed AB-PEMFC system can be considered as a viable alternative energy sources for portable applications.     

Effects of water induced pore blockage and mitigation strategies in low temperature PEM fuel cells – A simulation study

Ineffective water management in proton exchange membrane fuel cells (PEMFCs) can cause performance degradation. A simple mathematical model capturing the effect of water on the overall performance of the fuel cell system is of immense use in developing tools for water management. In this work, a computationally efficient first principles dynamic model for PEMFC system simulations and concomitant water management studies are developed. The steady-state version of this model is validated with experimental data. The effect of various operating conditions and design parameters on the performance of the fuel cell is studied using this model. Various control strategies for improving fuel cell performance in the presence of flooding are evaluated using the model. The simplicity and adequate predictive capability of the model make it amenable to be used in a model-based feedback control framework for online water management.     

State-of-health diagnosis based on hamming neural network using output voltage pattern recognition for a PEM fuel cell

This work investigates a pattern recognition-based diagnosis approach as an application of the Hamming neural network to the identification of suitable fuel cell model parameters, which aim to diagnose state-of-health (SOH) for a polymer electrolyte membrane (PEM) fuel cell. The fuel cell output voltage (FCOV) patterns of the 20 PEM fuel cells were measured, together with the model parameters, as representative patterns. Through statistical analysis of the FCOV patterns for 20 single cells, the Hamming neural network is applied for identification of the representative FCOV pattern that matches most closely of the pattern of the arbitrary cell to be measured. Considering the equivalent circuit fuel cell model, the purpose is to select a representative loss ΔR_d, defined as the sum of two losses (activation and concentration losses). Consequently, the selected cell’s ΔR_d is properly applied to diagnose SOH of an arbitrary cell through the comparison with those of fully fresh and aged cells with the minimum and maximum of the ΔR_d in experimental cell group, respectively. This avoids the need for repeated parameter measurement. Therefore, these results could lead to interesting perspectives for diagnostic fuel cell SOH.     

Non intrusive diagnosis of polymer electrolyte fuel cells by wavelet packet transform

Fuel cell is a promising technology for both automotive and stationary applications. However, its reliability and its lifetime remain major hurdles to its wide access to these markets.It is therefore necessary to develop reliable diagnosis tools adapted to these two applications’ requirements. More particularly, online and real time tools for diagnosis will permit an early faults diagnosis and therefore an increase of the system reliability and performance.Most of the existing fault diagnosis methodologies in fuel cells require the knowledge of numerous parameters that may lead to a special inner parameter monitoring setup, which is difficult, even impossible to obtain, considering constraints like fuel cell stacks’ geometry. Moreover, considering the final fuel cell stack end-uses, for instance in transportation applications in which the “on-board” instrumentation has to be minimized, a model using a minimal number of parameter is highly desirable.In this paper, a simple and low-cost flooding diagnosis method applied to a PEFC (Polymer Electrolyte Fuel Cell) is described. This method only uses the stack voltage and can be adapted to a large set of fuel cell configurations and applications.Coming from the signal-processing domain, the diagnosis consists in a signal feature extraction by multiscale decomposition using discrete wavelet transform, followed by fault identification and classification. Results obtained in this work showed that the wavelet analysis method allows the identification of the flooding based on the patterns obtained from the wavelet packet coefficients.The application of wavelet theory to fuel cell diagnosis is innovative and very promising and the experimental results obtained in this study proved its feasibility and reliability to classify correctly PEFC experimental states into flooded and non-flooded state of health.     

Efficient fault diagnosis method of PEMFC thermal management system for various current densities

The temperature of a fuel cell has a considerable impact on the saturation of a membrane, electrochemical reaction speed, and durability. So thermal management is considered one of the critical issues in polymer electrolyte membrane fuel cells. Therefore, the reliability of the thermal management system is also crucial for the performance and durability of a fuel cell system. In this work, a methodology for component-level fault diagnosis of polymer electrolyte membrane fuel cell thermal management system for various current densities is proposed. Specifically, this study suggests fault diagnosis using limited data, based on an experimental approach. Normal and five component-level fault states are diagnosed with a support vector machine model using temperature, pressure, and fan control signal data. The effects of training data at different operating current densities on fault diagnosis are analyzed. The effects of data preprocessing method are investigated, and the cause of misdiagnosis is analyzed. On this basis, diagnosis results show that the proposed methodology can realize efficient component-level fault diagnosis using limited data. The diagnosis accuracy is over 92% when the residual basis scaling method is used, and data at the highest operating current density is used to train the support vector machine.     

2D modeling of a defective PEMFC

A dysfunctioning of the heart of the fuel cell might affect the whole system, and thus the demand of electric power. To be able to estimate the damage of the fuel cell, the default has to be detected precisely. As it is well known, the physico-chemical processes involved in proton exchange membrane fuel cell (PEMFC) are strongly coupled, as such that putting apart a phenomenon by experimental measurement can be quite difficult. To this end, simulations of an online or offline diagnosis, for instance by electrochemical impedance spectroscopy (EIS) method are interesting. It can help also to analyze what happens locally in the heart of cell. The main aim of the presented work is to highlight the interest of using PEMFC dynamic model as a diagnosis tool. To illustrate this potential, EIS method has been implemented in 2D dynamic single cell in both simulated cases of defective and healthy cells.     

Transient model of oxygen-starved proton exchange membrane fuel cell for predicting voltages and hydrogen emissions

Transfer (crossover) leaks initiated by the chemical deterioration of the PEM and the resulting performance degradation has been previously identified as one the primary life-limiting factors in fuel cells. The leaks result in reduced oxygen levels in affected cells, where a secondary factor intimately related to this is high hydrogen emissions in the cathode exhaust when some cells operate in fully-oxygen-starved conditions. This paper builds on previous work that developed a unified fuel cell model that predicts cell voltage behavior under driving (normal) and driven (oxygen-starved) conditions, where this latest analysis now explicitly includes hydrogen pumping and emissions release when operating under oxygen-depleted conditions. In addition to considering diffusion effects and electrochemical effects, the model tracks the evolution of hydrogen in the cell cathode when no oxygen remains to generate water. The voltage response of the model under normal (non-starved) conditions is first validated for steady-state and transient (current step-change) conditions against previously published experiments, and then the model is used to simulate the cell voltage and stack hydrogen emissions behavior measured from three different commercially available fuel cell stacks. In the first fuel cell stack, a 9-cell commercial short stack, only one cell was fully oxygen-starved. Excellent agreement is seen between the measured and simulated hydrogen release concentrations (where air injection was used downstream of the stack to ensure adequate oxygen levels for measurement with a catalytic hydrogen sensor and to condense water vapor in the exhaust), where the role of hydrogen pumping is seen to contribute significantly to the release behavior. The first fuel cell stack is then used transiently in comparison with testing performed where the hydrogen injection level in the cell is changed quickly, where the model gives good agreement with the measured emission response and cell voltage behavior. Further comparisons with test data from a second and third 10-cell commercial short stack models operated with stack inlet hydrogen injection show good agreement with measured emissions onset versus current, where the observed threshold of starvation and emissions occurs a few percent sooner in the third model than the simulation, but the overall behavior is well predicted.     

Computational modeling of microfluidic fuel cells with flow-through porous electrodes

In the current work, a computational model of a microfluidic fuel cell with flow-through porous electrodes is developed and validated with experimental data based on vanadium redox electrolyte as fuel and oxidant. The model is the first of its kind for this innovative fuel cell design. The coupled problem of fluid flow, mass transport and electrochemical kinetics is solved from first principles using a commercial multiphysics code. The performance characteristics of the fuel cell based on polarization curves, single pass efficiency, fuel utilization and power density are predicted and theoretical maxima are established. Fuel and oxidant flow rate and its effect on cell performance is considered and an optimal operating point with respect to both efficiency and power output is identified for a given flow rate. The results help elucidate the interplay of kinetics and mass transport effects in influencing porous electrode polarization characteristics. The performance and electrode polarization at the mass transfer limit are also detailed. The results form a basis for determining parameter variations and design modifications to improve performance and fuel utilization. The validated model is expected to become a useful design tool for development and optimization of fuel cells and electrochemical sensors incorporating microfluidic flow-through porous electrodes.     

A high efficient assembly technique for large PEMFC stacks: Part I. Theory

A high efficient assembly technique for large proton exchange membrane fuel cell (PEMFC) stacks is proposed to obtain the optimal clamping load. The stack system is considered as a mechanical equivalent stiffness model consisting of numerous elastic elements (springs) in either series or parallel connections. We first propose an equivalent stiffness model for a single PEM fuel cell, and then develop an equivalent stiffness model for a large PEMFC stack. Based on the equivalent stiffness model, we discuss the effects of the structural parameters and temperature on the internal stress of the components and the contact resistance at the contact interfaces, and show how to determine the assembly parameters of a large fuel cell stack using the equivalent stiffness model. Finally, a three-dimensional finite element analysis (FEA) for a single PEMFC is compared with what the equivalent stiffness model predicts. It is found that the presented model gives very good prediction accuracy for the component stiffness and the clamping load.     

Dynamic electrochemical model of an alkaline fuel cell stack

The Institute for Energy and Environment (IEE) at the University of Strathclyde has developed various fuel cell (FC) systems for stationary and vehicular applications. In particular the author is involved in the development of alkaline fuel cell (AFC) systems. To understand the dynamic behaviour of the system's key element, the alkaline fuel cell stack, a dynamic model was developed allowing the characterisation of the electrochemical parameters. The model is used to forecast the behaviour of the fuel cell stack under various dynamic operating conditions. The so-called Nernst potential, which describes the open circuit voltage of the stack, is calculated using thermodynamic theory. Electrochemistry theory has been used to model the sources of the electric losses within the FC, such as activation, ohmic and concentration losses. The achievable value of this paper is the first publication of a detailed dynamic AFC based on mass balance, thermodynamics and electrochemical theory. The effects of the load changes on various fuel cell parameters, such as electrolyte concentration and concentrations of dissolved hydrogen and oxygen were covered in this investigation using the author's model. The model allows a detailed understanding of the dynamic effects within the AFC during load change events, which lead to the experienced electric response of the overall FC stack.