Robust fault diagnosis and fault tolerant control for PEMFC system based on an augmented LPV observer

In order to improve the safety and reliability of proton exchange membrane fuel cell system, this paper proposes a novel robust fault observer for the fault diagnosis and reconstruction of the PEMFC air management system. First, considering the complexity and large computation of the nonlinear PEMFC system, a linear parameter-varying (LPV) model is introduced to describe the system behavior and reduce the computation cost. Then, an augmented state observer based on the LPV model is proposed for simultaneously estimating the internal states and component faults. The robustness is guaranteed by taking the system disturbances and measurement noises into consideration when designing the observer gain. The observer design is transformed into a process of solving a set of linear inequality matrices. According to the results, the augmented robust observer can accurately estimate the system states and faults under different conditions. Moreover, to realize the fault tolerant control of the air supply, the oxygen stoichiometry estimator is designed taking consideration of system fault information and a corresponding controller is employed for air compressor voltage following the net power maximization strategy.     

Dynamic characteristics of local current densities and temperatures in proton exchange membrane fuel cells during reactant starvations

Reactant starvation during proton exchange membrane fuel cell (PEMFC) operation can cause serious irreversible damages. In order to study the detailed local characteristics of starvations, simultaneous measurements of the dynamic variation of local current densities and temperatures in an experimental PEMFC with single serpentine flow field have been performed during both air and hydrogen starvations. These studies have been performed under both current controlled and cell voltage controlled operations. It is found that under current controlled operations cell voltage can decrease very quickly during reactant starvation. Besides, even though the average current is kept constant, local current densities as well as local temperatures can change dramatically. Furthermore, the variation characteristics of local current density and temperature strongly depend on the locations along the flow channel. Local current densities and temperatures near the channel inlet can become very high, especially during hydrogen starvation, posing serious threats for the membrane and catalyst layers near the inlet. When operating in a constant voltage mode, no obvious damaging phenomena were observed except very low and unstable current densities and unstable temperatures near the channel outlet during hydrogen starvation. It is demonstrated that measuring local temperatures can be effective in exploring local dynamic performance of PEMFC and the thermal failure mechanism of MEA during reactants starvations.     

A Bayesian network fault diagnostic system for proton exchange membrane fuel cells

This paper considers the effects of different types of faults on a proton exchange membrane fuel cell model (PEMFC). Using databases (which record the fault effects) and probabilistic methods (such as the Bayesian-Score and Markov Chain Monte Carlo), a graphical–probabilistic structure for fault diagnosis is constructed. The graphical model defines the cause-effect relationship among the variables, and the probabilistic method captures the numerical dependence among these variables. Finally, the Bayesian network (i.e. the graphical–probabilistic structure) is used to execute the diagnosis of fault causes in the PEMFC model based on the effects observed.     

Dynamic modeling and dynamic responses of grid-connected fuel cell

The active distribution network (ADN) is a new effective approach to facilitate connecting distributed generation (DG) to the network, where the DG is controlled to support the system stability during various kinds of disturbances. Fuel cell is one of the most important DGs, however there are still many issues left to be solved in order to meet the requirements of the ADN, such as dynamic modeling, dynamic responses to power systems, especially during voltage dip, system fault, etc. In the existing grid-connected fuel cell researches, most of the dynamic models did not consider air compressor and its parasitic power consumption. Hence, a dynamic model of grid-connected proton exchange membrane fuel cell (PEMFC) is presented by considering dynamic modeling of the air compressor and its parasitic power consumption. Based on the model, the mutual influences between power system and fuel cell are analyzed when the fuel cell is synchronously grid-connected. The dynamic responses of the fuel cell and its low voltage and fault ride-through capability are studied when the power system fault or voltage dip occurs. Finally, based on the dynamic simulation of the typical power systems with a PEMFC, the theoretical basis and guiding suggestions are presented for grid-connection, dynamic operation, and off-grid of fuel cells.     

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.     

Preliminary experimental study of the performances for a print circuit board based planar PEMFC stack

This paper presents a novel planar proton exchange membrane fuel cell (PEMFC) stack designed for portable electronic devices, consisting of twenty homemade membrane electrode assemblies (MEAs) arranged on a planar surface and three printed circuit boards (PCBs, including anode, interlayer and cathode PCBs) used to load these MEAs. The current collectors and electrical connectors are manufactured using printed circuit technology. The inlet holes of reaction gases are also machined on PCB substrates. The output performance tests are performed on the MEAs and the assembled planar PEMFC stack. The results show that the power densities of the MEAs and the planar PEMFC stack are 0.6 W/cm² and 0.361 W/cm² at rated voltage under ambient temperature and forced convection air conditions, respectively. The stability tests are also conducted on the planar PEMFC stack, and the results show no significant fluctuations in output current. The feasibility of the application of planar PEMFC stacks in portable electronic devices is preliminarily demonstrated, and the improvement directions for further improving the output performance are proposed accordingly.     

Online humidification diagnosis of a PEMFC using a static DC–DC converter

This paper deals with the online checking of the humidification of a Proton Exchange Membrane Fuel Cell (PEMFC). Indeed, drying or flooding can decrease the performance of the PEMFC and even lead to its destruction. An online humidification diagnosis can allow a real-time control. A good indicator of the membrane humidification state is its internal resistance. As known, the membrane ionic conductivity increases with the membrane water content. This resistance can be calculated at high frequency by dividing the voltage variation by the current variation. The proposed scheme makes use of measurements of current and voltage ripples coming from the association of a static DC–DC converter and the fuel cell. The experiment thus consists in computing the internal resistance in wet and dry conditions.     

Experimental study of dynamic performance of defective cell within a PEMFC stack

Defective cell in a PEMFC stack may reduce durability and reliability of the stack and even damage the stack. However, the dynamic performance of defective cell within a PEMFC stack is not clear. In this paper, the dynamic characteristics of the defective cell under different load conditions are analyzed. The results reveal that the defective cell has slower dynamic response rate than other single fuel cells, and the defective cell causes a poor voltage uniformity of the stack. The increased frequency of load change makes the voltage change rate of defective cell higher. The increased amplitude of load change has a more negative impact than the increased frequency of load change, and makes the defective cell more prone to flooding. Furthermore, impedance spectrum shows that these load conditions have greater negative effect for the defective cell than other cells. Finally, according to the experimental results and practical application, recommends related to control strategy of PEMFC stack are proposed to extend lifetime.     

Simultaneous fault diagnosis of proton exchange membrane fuel cell systems based on an Incremental Multi-label Classification Network

Fault diagnosis plays an important role in the operation of proton exchange membrane fuel cell (PEMFC) systems. In some certain working conditions, multiple faults can occur simultaneously. And, to the best of our knowledge, very few studies have yet to design an algorithm specifically for simultaneous fault diagnosis in PEMFC systems. Therefore, a novel simultaneous fault diagnosis algorithm, based on multi-label classifier chain named Incremental Multi-label Classification Network (IMCN), is proposed. To develop and optimize IMCN, a PEMFC model is constructed based on the commercial software AVL CURISE M to simulate data when simultaneous multiple faults occur. To further verify the generalization performance and practical effect of IMCN, a bench experiment using a high-power PEMFC system is conducted, which has similar boundary conditions as the boundary conditions embedded in simulation model. And, whether in experiment or simulation, corresponding verification methods are adopted to verify the success of simultaneous multiple faults embedding. Experimental data testing shows that, the subset accuracy, Hamming loss, Jaccard index, precision and recall of IMCN reaches 0.973, 0.029, 0.921, 0.961 and 0.956 respectively (better than Multi-Label MLP classifier, Label powerset MLP classifier, etc.), and the proposed simultaneous fault diagnosis method has achieved excellent results.     

PEMFC stack voltage singularity measurement and fault classification

The study summarized in this paper deals with non-intrusive fault diagnosis of Polymer Electrolyte Membrane Fuel Cell (PEMFC) stack. In the proposed approach, the diagnosis operation is based on the stack voltage singularity measurement and classification. To this aim, wavelet transform-based multifractal formalism, named WTMM (Wavelet Transform Modulus Maxima), and pattern recognition methods are combined to realize the identification of the PEMFC faults. The proposed method takes advantage of the non-linearities associated with discontinuities introduced in the dynamic response data resulting from various failure modes. Indeed, the singularities signature of poor operating conditions (faults) of the PEMFC is revealed through the computing of multifractal spectra. The obtained good classification rates demonstrate that the multifractal spectrum based on WTMM is effective to extract the incipient fault features during the PEMFC operation. The proposed method leads to a promising non-intrusive and low cost diagnostic tool to achieve on-line characterizations of dynamical FC behaviors.     

Investigation of PEMFC fault diagnosis with consideration of sensor reliability

Despite the wide range of applications for the polymer electrolyte membrane fuel cell (PEMFC), its reliability and durability are still major barriers for further commercialization. As a possible solution, PEMFC fault diagnosis has received much more attention in the last few decades. Due to the difficulty of developing an accurate PEMFC model incorporating various failure mode effects, data-driven approaches are widely used for diagnosis purposes. These methods depend largely on the quality of sensor measurements from the PEMFC. Therefore, it is necessary to investigate sensor reliability when performing PEMFC fault diagnosis.In this study, sensor reliability is investigated by proposing an identification technique to detect abnormal sensors during PEMFC operation. The identified abnormal sensors will be removed from the analysis in order to guarantee reliable diagnostic performance. Moreover, the effectiveness of the proposed technique is investigated using test data from a PEMFC system, where fuel cell flooding is observed. During the test, due to accumulation of liquid water inside the PEMFC, the humidity sensors will give misleading readings, and flooding cannot be identified correctly with inclusion of these humidity sensors in the analysis. With the proposed technique, the abnormal humidity measurements can be detected at an early stage. Results demonstrate that by removing the abnormal sensors, flooding can be identified with the remaining sensors, thus reliable health monitoring can be guaranteed during the PEMFC operation.     

Fault diagnosis of PEMFC systems based on an auxiliary transfer network

Data-driven fault diagnosis methods require huge amounts of expensive experimental data. Due to the irreversible damage of severe fault embedding experiments to proton exchange membrane fuel cell (PEMFC) systems, rare available data can be obtained. In view of this issue, a fault diagnosis method based on an auxiliary transfer network (ATN) is proposed. This method uses two parallel neural networks (main and auxiliary neural network) and a prediction fusion module to realize fault diagnosis. The auxiliary neural network is a fault diagnosis classifier pretrained based on both slight and severe fault simulative data, and its weights are transmitted into the ATN structure and frozen. After that, the main neural network is trained based on a large number of slight fault experimental data and a small number of severe fault experimental data. Through ATN, the main neural network learns the abstract features of severe faults under the guidance of auxiliary neural network, and realizes the transfer learning from simulation-based fault diagnosis classifier to experiment-based fault diagnosis classifier. Through testing, the accuracy and precision of ATN-based fault diagnosis classifier with LSTM as both main and auxiliary neural network reaches 0.993 and 1.0 respectively, which is higher than the common data-driven methods.     

A novel approach for modeling the internal behavior of a PEMFC by using electrical circuits

This paper presents a method for modeling a PEMFC by using electrical circuits. In particular, it focuses on temperature and voltage distribution of fuel cell. The current distribution is calculated by using the Newton-Raphson method in order to estimate the physical parameters (connection resistances) of the model. Several test on a single PEMFC cell have been carried out during this study. In order to validate the model, temperature and voltage sensors have been installed in different segments of a single cell. A distinguishing advantage of the developed model is its ability to detect and localize the faults within the PEMFC cell, as well as simulate different faults in all of the three directions of the PEMFC cell.     

Data-driven fault diagnosis for PEMFC systems of hybrid tram based on deep learning

The running state of the hybrid tram and the service life of fuel cell stacks are related to the fault diagnosis strategy of the proton exchange membrane fuel cell (PEMFC) system. In order to accurately detect various fault types, a novel method is proposed to classify the different health states, which is composed of simulated annealing genetic algorithm fuzzy c-means clustering (SAGAFCM) and deep belief network (DBN) combined with synthetic minority over-sampling technique (SMOTE). Operation data generated by the tram are clustered by SAGAFCM algorithm, and valid data are selected as fault diagnosis samples which include the training sample and the test sample. However, the fault samples are usually unbalanced data. To reduce the influence of unbalanced data on the fault diagnosis accuracy, SMOTE is employed to form a new training sample by supplementing the data of the small sample. Then DBN is trained by the new training sample to obtain the fault diagnosis model. In this paper, the proposed method can well distinguish the four health states, which are high deionized water inlet temperature fault, hydrogen leakage fault, low air pressure fault and the normal state, with an accuracy of 99.97% for the training sample and 100% for the test sample.     

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.     

Behavior of current distribution evolution under reactant starvation conditions based on a single polymer electrolyte membrane fuel cell (PEMFC) with triple-serpentine flow field: An experimental study

Reactant starvation is unfavorable to the durability and life extension of PEMFC engines. In this paper, a 25 cm² segmented PEMFC is assembled to investigate starvation phenomenon, and the contour maps of current distribution are given to analyze the reactant starvation mechanism.The experimental results prove the high-quality homogeneity of current with triple-serpentine configuration even under starvation conditions. The air starvation experiments suggest the migration of lowest current region and the variation trend of standard deviation with the increasing of stoichiometry. The survival time increases with the anode stoichiometry, and the current density of anode downstream constantly increases with the reversal of cell, reflecting severe hydrogen starvation in these local areas.It is concluded ORR dominates the specific current distribution rather than any other electrochemical reactions. This study sheds the light of improving the lifespan and potential large-scale commercialization realization of PEMFC engines.     

A review on model-based diagnosis methodologies for PEMFCs

The proton exchange membrane fuel cell systems (PEMFC)s are interesting devices for energy conversion. Recent researches are aimed at developing new monitoring and diagnosis techniques; a good management of these systems would allow optimizing the performance and reducing their degradation. The objective of a suitable diagnostic tool is to identify and isolate the different faults that may occur in the system being monitored in real time. Therefore, the main features of computational methods are accuracy, reliability and high computational speed. In order to perform the diagnosis, it is necessary to evaluate different approaches. In this work different model-based approaches are investigated as well as their validation and applications. An overview of different methodologies available in the literature is proposed, which is oriented to help in developing suitable diagnostic tool for PEMFC monitoring and fault detection and isolation (FDI).     

Proton-exchange-membrane fuel cells durability evaluated by load-on/off cycling

Load-on/off cycles at 80 °C, with near-saturated H₂ and air at ambient pressure were applied to investigate the durability of several types of membrane-electrode-assemblies (MEAs) for proton-exchange-membrane fuel cells (PEMFC). The ohmic resistance, H₂ cross-over, electrochemically active surface area (ECSA), protonic resistance of the cathode as well as the performances with H₂/air and H₂/O₂ were measured at regular intervals. These data enabled a breakdown of the increase in cell voltage losses upon cycling. Increase of kinetic losses was found in all MEAs but significant differences were obtained for the transport losses in the cathode catalyst layer, which either had a small or a substantial contribution to the overall voltage decay, depending on the carbon type and ionomer loading. Membrane degradation did not contribute significantly in these tests.