Search

A 1+1-dimensional(1+1D) multiphase model of proton exchange membrane fuel cell (PEMFC) is developed to simulate the dynamic behaviors of the fuel cell under various operating conditions. Electrochemical, fluidic, and thermal physical phenomena are taken into account, and the model can accurately describe the multi-physical processes inside the PEMFC. Meanwhile, the water phase change and nitrogen crossover are also considered in this model. The developed model can simulate the fuel cell behaviors in both normal temperature and cold start conditions. Selection of the time step size is discussed, and the solution method of the real-time model is proposed. Computational efficiency is greatly improved by simplifying the multicomponent diffusion inside the membrane electrode assembly (MEA), which results in the shorter calculation time than the simulated physical time. The proposed model is suitable for embedded applications, such as real-time simulation or online diagnostic control. The comprehensive model validation is carried out by comparing the simulation results, including polarization curves, ohmic resistance, local current density distribution, and voltage evolution, under various working conditions of steady state, load change, and cold start, and a good agreement is achieved. Finally, some simulation cases are studied to further demonstrate the simulation ability of the model.

Fault diagnosis is essential for the stable and efficient operation of the proton exchange membrane fuel cell (PEMFC) system. However, the manifold balance of plant (BOP) components and the coupling phenomenon involving multiple physical fields will significantly increase the probability of system fault, which makes it difficult to realize a timely and effective diagnosis. In this study, a novel online diagnosis method for an open-cathode PEMFC system is proposed which is only based on output voltage measurements, and both the normal state and fault states caused by abnormal BOP components operation are taken into consideration. Specifically, the fault identification is realized based on the fusion of t-Distributed Stochastic Neighbor Embedding (t-SNE) and eXtreme Gradient Boosting (XGBoost), where the t-SNE is adopted to extract the diagnostic features from the individual cell output voltages and the XGBoost is adopted to identify the fault type based on the extracted diagnostic features. A facile method based on Grey Relational Analysis (GRA) is also proposed to quantify the fault degree, which can contribute to the condition-based maintenance of the system. The results validated by the fuel cell system diagnostic experiments reveal that the novel method can effectively identify the five health states and the fault degree. The overall accuracy is 99.31% and the diagnosis period is shortened from 0.3375s to 0.1416s after processing by t-SNE, which indicates that the proposed method can have a better performance compared with the traditional methods.

Considering the fact that various features can be used in proton exchange membrane fuel cell (PEMFC) fault diagnosis, while the lack of feature evaluation method brings great difficulty in selecting appropriate features at practical PEMFC applications, a generalized feature evaluation and selection method is urgently required in PEMFC fault diagnosis. This paper proposes a novel feature evaluation method, where feature discrimination capacity and robustness are evaluated. With the proposed method, features providing accurate and consistent diagnostic performance can be determined. In the study, features widely used in existing PEMFC fault diagnosis are utilized, which are extracted from either PEMFC voltage or multi-sensor signals, and their effectiveness in identifying faults at different PEMFC systems is investigated. Results demonstrate that with the proposed evaluation method, available features from various PEMFC test data can be ranked based on their diagnostic results. From the findings, appropriate features for PEMFC fault diagnosis can be determined. Moreover, early stage PEMFC faults can also be distinguished with high ranking features. This will be beneficial in practical PEMFC systems, where mitigation strategies can be taken to remove the effect due to early stage faults.

Data-driven prognostic methods aim at estimating the remaining useful life (RUL) of the proton exchange membrane fuel cell (PEMFC) system and contribute to its lifespan extension and reliability improvement. Lack of dynamic health indicator (HI) and low prediction accuracy are the weaknesses for current RUL prediction methods, especially when the PEMFC system works at the variable load profiles. To overcome the drawbacks of static HIs (e.g., voltage, power), a novel dynamic HI of relative power-loss rate (RPLR) is put forward to represent the degradation state under the variable load profiles. Besides, the discrete wavelet transform and ensemble echo state network (DWT-EESN) approach is proposed to deal with the multi-timescale features of RPLR and enhance the prediction performance. Firstly, the decomposition method of discrete wavelet transform (DWT) is applied to decompose the RPLR into several sub-waveforms. Secondly, several independent echo state networks (ESNs) are utilized to predict the sub-waveforms separately. Finally, the prediction results in different timescales are integrated to achieve the overall RUL prediction. Three micro-combined heat and power (μ-CHP) experiments with different dynamic profiles are carried out, and results show that the DWT-EESN has a higher long-term prediction accuracy than the traditional ESN structure.

Durability is considered as one of the main technical obstacles to the large-scale commercialization of proton exchange membrane fuel cells (PEMFCs), which can be e.ectively improved through prognostics prediction techniques. This paper proposes a stacked echo state network (ESN) based on the genetic algorithm (GA) to predict the future degradation trend of PEMFCs. By alternately using the projection layer and the encoding layer, the proposed method can make full use of the temporal kernel property of the ESN to encode the multi-scale and multi-level dynamics of the stack voltage, thereby obtaining more robust generalization performance and higher accuracy than existing methods. Specifically, a stack voltage time series of PEMFCs is projected into the high-dimensional echo state space of the reservoir. Then, an auto-encoder projects the echo state representation into the low-dimensional feature space. After that, the genetic algorithm is utilized to optimize the hyperparameters of the developed model. Based on two open-source datasets of PEMFCs with di.erent accelerated test conditions, this paper systematically tested the proposed degradation prediction methods based on di.erent model structures. Test results demonstrate that the proposed method is superior to traditional prediction methods in terms of accuracy and generalization performance.

Clean energy and reduction in carbon footprint have motivated the adoption of Fuel Cells as an alternative source of energy, merely having any detrimental byproducts. In this work, the control of the Proton-exchange membrane fuel cell (PEMFC) integrated boost converter has been carried out. State-feedback with integral-based controllers has been designed using the classical pole placement method and optimal linear quadratic regulator approach. The first method aims at achieving the desired performance. The second method also minimizes the error while optimizing the control effort. In this approach, the control energy required for attaining the time and frequency domain objective at steady state operation is also optimized. The same avoids the limitation of existing schemes by avoiding sub-optimal solutions. Both control techniques have been verified in terms of transient performance during the load disturbance using numerical simulations and experimentation. In addition, comparative state trajectories and overall efficiency analysis of the system are presented.

The degradation seriously affects the durability and cost of the proton exchange membrane fuel cell (PEMFC). This article presents a novel model-driven method based on the frequency-domain Kalman filter (FDKF) and voltage degradation model to predict the degradation of PEMFC in the frequency domain. The advantage of the proposed FDKF method is that it can process the data in groups; thus, the computation time can be greatly reduced with high accuracy. Two degradation experiments under constant and quasi-dynamic currents have been used to demonstrate its prognosis performances under different conditions and different training times. Compared with the traditional time-domain extended Kalman filter method and literature, it has been demonstrated that the proposed one has higher accuracy and requires much less calculation time.

Prognostic of the proton-exchange membrane fuel cell can effectively extend the fuel cell lifespan, which can contribute to its large-scale commercialization. In this article, a hybrid prognostic approach is proposed to predict the fuel cell output voltage and other aging parameters that can reflect the stack’s internal degradation. During the training stage, the prognostic parameters are obtained by using the extended Kalman filter (EKF). Besides, the fuel cell output voltage is used to train the long short-term memory (LSTM) recurrent neural network. During the prediction stage, the hybrid EKF and LSTM method will predict the output voltage and aging parameters, and the degradation can be predicted under dynamic conditions. The proposed method is validated by experimental tests under static, quasi-dynamic, and dynamic conditions. Results indicate that the hybrid method can accurately predict the degradation trend of fuel cell voltage and aging parameters. The RMSE of the method is less than 0.0110, 0.0262, and 0.0317 under static, quasi-dynamic, and dynamic conditions, respectively, which are smaller than the conventional model-based methods or data-driven methods. Furthermore, the hybrid method can provide more detailed information for prognostic decision-making and better prolong the fuel cell lifespan.

In this article, the improved chaotic electromagnetic field optimization (ICEFO) algorithm is adopted to generate the optimal values of unknown parameters of fuel cells (FCs). The mathematical model of polymer electrolyte membrane FC (PEMFC) considers nonlinear and complex optimization problems with different control variables. The sum of squared error between the measured and computed stack voltages is considered as the main objective function. The performance of the ICEFO algorithm is tested on three PEMFC stacks. Moreover, sensitivity and statistical measures are presented to confirm the reliability and accuracy of ICEFO. In addition, the effect of changing the cell temperature and reactants pressures is studied for more validation of ICEFO. Furthermore, the results obtained by ICEFO are competitive compared with other optimization methods. These results confirm the effectiveness of ICEFO in solving the optimization problem of PEMFC parameter estimation. Finally, based on the optimization results a Simulink model for PEMFC is developed to examine the dynamic performance of the PEMFCs.

The traction power of electrical multiple unit (EMU) trains can even reach megawatt level so that in hydrogen EMU trains, it is necessary to adopt the multistack proton exchange membrane fuel cells (PEMFC) generation system (MFCS), which can provide higher power. MFCS is composed of multiple parallel-connected PEMFC. Different PEMFCs often have different durability. In general, it is hoped that all the PEMFCs in an MFCS do not have large performance differences, which often occurs under traditional strategies. And it is also hoped that PEMFCs have longer and uniform lifetimes. To meet this demand, first, this article conducted a feasibility study on the EMU hybrid system and obtained the configuration scheme. Then, this article proposed a distributed performance consensus control strategy for MFCS. Moreover, considering fault and fault removal conditions, the strategy was further designed for high robustness. And based on stability analysis of iterative matrix, key parameters of the algorithm were set. Finally, based on hardware-in-the-loop experiments, this article conducted experiments in real-time and showed the effectiveness and superiority of strategy through comparison with the traditional strategy. Besides, the high-robustness characteristic of the proposed strategy was also verified through experiments under communication fault, electrical fault, and electrical fault removal conditions.

All-electric ships (AES) are regarded as a promising solution for decreasing greenhouse gas emissions since they are able to utilize clean technologies like fuel cells instead of fossil fuel. A zero-emission hybrid energy system comprising the Proton Exchange Membrane (PEM) fuel cell, battery, cold-ironing, and Recuperative organic Rankine cycle (RORC) is scrutinized in this paper. To use the waste heat produced by PEM fuel cells, a hybrid system which is composed of PEM fuel cells and RORC is suggested. In order to analyze this zero-emission all-electric ship, the real data of a ferry boat, containing the load profiles and routes is used to appraise the possibility of the suggested hybrid system. The structure of the boat and energy sources, along with mathematical models, are represented and examined. Eventually, the hourly energy management of the boat for one specific day is analyzed, and also, to optimize the power dispatch, the Deep Deterministic Policy Gradient (DDPG) is applied in actor-critic architecture. To corroborate the proposed models, the MATLAB software is employed. According to obtained results, the proposed models could ensure effective and efficient ways in marine vessels due to not only their high performances but also permissible energy cost to be a zero-emission ship.

This article presents a real-time parameter estimation of a proton exchange membrane fuel cell (PEMFC). The proposed strategy estimates online the PEMFC's resistance, since it is directly correlated to its remaining useful life assessment. The estimation of the PEMFC's parameters is a difficult task to undertake due to various uncertainties, like temperature and aging, that lead to a drift in parameters and limit the performance of the overall energy system. Therefore, online system identification is essential to track online the PEMFC's time-varying parameters. Unlike other identification techniques, the proposed strategy is based on a simple yet accurate PEMFC's model and adjusts its parameters in real-time using a Lyapunov-based adaptation law, which yields guaranteed stability. Experiments are conducted on a 500-W Horizon PEMFC and results along with a comparison against the well-known Kalman filter highlight the effectiveness of the proposed approach, which is instrumental for its numerous applications, such as the energy management of hybrid fuel cell vehicles.

In this article, an approach for boosting the efficiency of energy management strategies (EMSs) in fuel cell hybrid electric vehicles using an online systemic management of the fuel cell system (FCS) is put forward. Unlike other similar works which solely determine the requested current from the FCS, this article capitalizes on simultaneous regulation of current and temperature, which have different dynamic behavior. In this regard, first, an online systemic management scheme is developed to guarantee the supply of the requested power from the stack with the highest efficiency. This scheme is based on an updatable three-dimensional map which relates the requested power from the stack to its optimal temperature and current. Second, two different EMSs are used to distribute the power between the FCS and battery. The EMSs’ constraints are constantly updated by the online model to embrace the stack performance drifts owing to degradation and operating conditions variation. Finally, the effect of integrating the developed online systemic management into the EMSs’ design is experimentally scrutinized under two standard driving cycles and indicated that up to 3.7% efficiency enhancement can be reached by employing such a systemic approach. Moreover, FCS's health adaptation unawareness can increase the hydrogen consumption up to 6.6%.

This article proposes an energy management system (EMS) for a fuel cell (FC) hybrid electric vehicle. The EMS is based on nonlinear model predictive control (NMPC) and employs a recurrent neural network (RNN) for modeling a proton exchange membrane FC. The NMPC makes possible the formulation of control objectives not allowed by a linear model predictive control (MPC), such as maximum efficiency point tracking of the FC, while the RNN can accurately predict the FC nonlinear dynamics. The EMS was implemented on a low-cost development board, and the experiments were performed in real time on a hardware-in-the-loop test bench equipped with a real 3-kW FC stack. The experimental results demonstrate that the NMPC EMS is able to meet the vehicle's energy demand, as well as to operate the FC in its most efficient region. Moreover, a comparative study is performed between the proposed NMPC, a linear MPC, and hysteresis band control. The results of this comparative study demonstrate that the NMPC provides a better fuel economy and can reduce FC degradation.

Health management can effectively extend the service life of proton exchange membrane fuel cells and reduce the maintenance cost. This paper proposes a health management method for the proton exchange membrane fuel cells based on an active fault tolerant control method. With the advantages of low cost and high speed, a stack voltage model is developed for the condition monitoring. The fast electrochemical impedance spectroscopy measurement is performed when the condition monitoring module detects faults. Then, the distribution of relaxation time is used to extract the characteristics of electrochemical impedance spectroscopy for fault diagnosis. Thereafter, based on the diagnosis results, the performance recovery strategies are incorporated to cope with the faults. This paper adopts three typical fuel cell faults, namely flooding, membrane drying, and air starvation, to demonstrate the effectiveness of the proposed health management. Experimental results show that the proposed health management can realize real-time health monitoring and rapid fault diagnosis, and achieve effective recovery of performance under faulty conditions, thereby significantly improving the reliability of the proton exchange membrane fuel cell system.

The output power of the fuel cell (FC) is mainly depending on the membrane water content, temperature, the hydrogen and oxygen partial pressures. The polarization curve has one global maximum power to be tracked. Therefore, a robust maximum power point tracking (MPPT) is highly required to follow the optimal operating point under any operating conditions. In this article, a recent approach of forensic-based investigation (FBI) algorithm is proposed to identify the optimal parameters of fractional order PID-based MPPT with proton exchange membrane (PEM) fuel cell. FBI is selected due to its high accuracy and requirement of less computational efforts. The considered objective function to be minimized is the error between the voltage at maximum power (VMP) and the actual one at FC terminals. To prove the robustness of the proposed methodology, four cases of operating conditions are analyzed which are constant membrane water content and temperature, constant membrane water content with variable temperature, variable membrane water content with constant temperature, and variable membrane water content with variable temperature. The obtained results are compared to other approaches such as incremental resistance (INCR), particle swarm optimizer (PSO), invasive weed optimizer (IWO), sin-cosine algorithm (SCA), and artificial ecosystem optimizer (AEO). In case (1), the proposed FBI-FOPID succeeded in achieving maximum power of 5185.101 W. While the minimum objective functions in the second, third, and fourth cases are 2.5736 V, 1.4436 V, and 1.1568 V respectively obtained via the proposed approach. The comparison confirmed the superiority of the proposed FBI-based MPPT compared with other methods.

Electrification in the transportation industry is becoming more important to face global warming and replace fossil fuels in the future. Among the available energy sources Li-ion battery and proton exchange membrane fuel cell (PEMFC) are the most promising energy sources. Therefore, employing them in fuel cell hybrid electric vehicles (FCHEVs) to combine their advantages is one of the favorable solutions. However, they still face a major challenge residing in their aging that cause the drop of system performance. On one hand, the degradation is the result of the interaction between several aging mechanisms that react differently with various operating conditions. On the other hand, a hybrid system requires an essential energy management strategy (EMS) for fuel economy and optimal power share. At the end, this EMS has an important impact on the lifetime of sources in term of reducing or favorizing the degradation. Therefore, it is important to consider the degradation in the objectives of the designed EMS. Since the degradation is usually neglected when designing an EMS, this paper tends to review the possible methods for designing a health-conscious EMS. Hence, this paper presents a summary of the main fuel cell (FC) and Li-ion battery aging mechanisms as well as the useful degradation models for state of health estimation. In addition, the existing works that consider the degradation of on-board energy sources in their approaches for increasing their durability are classified and analysed. Remaining challenges are detailed along with a discussion and outlooks about current and future trends of health-conscious EMS.

In recent years, with wide application of proton exchange membrane fuel cell (PEMFC) in vehicles and portable applications, researches regarding PEMFC lifetime behavior and associated prognostic techniques receive more interest. In this article, a least absolute shrinkage and selection operator-echo state network (LASSO-ESN)-based prognostic strategy is proposed for the optimization of input parameters and long-term PEMFC behavior prediction. In the analysis, ESN is selected to predict PEMFC long-term behavior iteratively, while input parameters to ESN are optimized using LASSO. With LASSO, the contribution of input parameters to PEMFC prediction can be evaluated, and those with the minimum weight are eliminated iteratively during the prediction. From the findings, the most accurate predictions and corresponding optimized input parameters can be determined. Furthermore, effectiveness of proposed strategy is investigated using PEMFC data at different operating conditions. Results demonstrate that with proposed strategy, optimized input parameters at different operating conditions can be determined, and accurate PEMFC predictions can be provided.

This paper puts forward an adaptive cold start strategy for a proton exchange membrane fuel cell (PEMFC) based on maximum power mode. The proposed strategy consists of a water evacuation process after PEMFC shutdown and a self-heating process at PEMFC cold startup. To maximize the performance of the suggested strategy, an optimal operating condition for the cold start procedure is sought first. In this respect, an experimental parametric study is performed to explore the impact of fan velocity, micro-short circuit, anode pressure, and purge procedure on the PEMFC cold start performance. After laying down the proper conditions, the proposed cold start procedure is implemented on a test bench for experimental validations. The self-heating process is based on an online adaptive algorithm that maximizes the PEMFC's internal heat depending on its operating parameters’ variation. In fact, this algorithm attempts to keep the current density at high levels, leading to PEMFC's performance improvement achieved by membrane hydration and temperature increase. The experimental results confirm the effectiveness of the proposed strategy, which presents a fast and cost-effective PEMFC's cold start.

In this article, a model predictive control (MPC) energy management strategy is proposed to distribute power flows of proton exchange membrane fuel cell (PEMFC)-based hybrid power systems consisting of PEMFC, battery, and waste heat recovery system such as TEG and CHP. To optimally meet the demand of load power balancing as well as protect PEMFC from lifetime degradation, a novel objective function by considering fuel consumption, state-of-charge (SOC) of battery, as well as power slope and temperature of PEMFC is constructed and solved in the states prediction horizon within the defined lifetime constraints and SOC limitations. In particular, temperature effects are newly introduced by adding a state-variable to the energy management model and formulating a penalty function. Simulations with mobility and stationary application scenarios are presented. In the automobile case, the hydrogen consumption of the constraints MPC is reduced by 9.98% compared with the rule-based strategy, and the same results can be achieved in the household application. A hardware in the loop experiment was carried out to verify the real-time performance of the MPC strategy which occupied a 2.21% average CPU load rate. The proposed MPC strategy has a promising fuel consumption optimization, lifetime extension, and real-time capability.

Proton exchange membrane fuel cell (PEMFC) is a rich source of renewable energy. A non-destructive prediction method is needed to determine the content of water in the PEMFC. In the gas channel of a transparent PEMFC, water is detected with image processing. This method has a high computational cost and is sensitive to the initial position of the camera and ambient lighting. In this paper, the deep neural network (DNN) has been trained to learn the transparent PEMFC’s labeled images as a way to determine the content of water, limit human interference and employed in a real-time process. This DNN model is a virtual sensor for measuring the water coverage ratio. To produce the label of images, all data are divided into 6 classes based on the percentage of water coverage ratio. Through analyzing the number of each class, the imbalance data is unfolded. To overcome this problem, random oversampling and undersampling techniques are used. The images and the classes are considered as the input and output of the DNN, respectively. Also, the region of water accumulation in the gas channel can be recognized with robustness to the environmental conditions. Final results of 4-41-64-120-99-6 nodes for DNN layers were derived due to GA optimization. Accuracy of 96.77% and 94.23% in train and test data have been achieved. This DNN, processes the images up to 10 times faster than image processing. Also, the region of water accumulation in the gas channel can be recognized.

Maintaining the cathode pressure stable and avoiding oxygen starvation are crucial for the air supply of proton exchange membrane fuel cell (PEMFC). In most applications, the cathode pressure and oxygen excess ratio (OER) are unmeasurable parameters, which makes it difficult to precisely control the air supply system. This article proposes a fractional order PID (FOPID) controller based on an unknown input nonlinear observer for the fuel cell air supply system. The proposed nonlinear observer is able to estimate internal states including the cathode pressure of the PEMFC system. Then, the OER is obtained based on the observed system states. A fractional-order PID controller with a parameter optimization algorithm is developed to regulate as fast the OER and the cathode pressure to their desired values. Both the steady and transient performances of the proposed control method are simulated and experimentally validated compared with supertwisting sliding mode controller and traditional PID controller.

Proton exchange membrane fuel cells (PEMFCs) are considered as one of the most promising power sources for transportation in the near future. Proper and robust thermal management is a key issue in fuel cell applications. This paper mainly studies the sensor fault detection and isolation (FDI) and fault tolerant control (FTC) for the thermal management of PEMFC systems. The thermal model of fuel cell is established and analyzed by structure analysis, and the residual generator of sensor faults are designed by Dulmage–Mendelsohn decomposition to rearrange the biadjacency matrix of the thermal model. A sliding-mode-based active FTC (AFTC) strategy is proposed for the thermal management of fuel cell systems. The effectivenesses of the proposed FDI method and AFTC strategy are verified on a fuel cell test bench. The experimental results show that the temperature of the PEMFC stack can be maintained at the reference value with high accuracy even when sensor fails.

Polymer electrolyte membrane fuel cell (PEMFC), because of faster response, portability and the low operating temperature has found wide usage in applications requiring regulated output voltage. Alongwith voltage regulation, optimum stack efficiency is important for reliable operation. Overall, the maximum efficiency point (MEP) operation and voltage regulation need to be achieved while restricting the PEMFC operation till maximum power point (MPP). This demands operational adaptability of PEMFC over a wider range, to meet the desired levels of voltage regulation, maximum efficiency and MPP operation. However, achieving all the objectives simultaneously is challenging since operating points corresponding to the objectives differ. This paper proposes a control strategy that achieves operation dependent adaptability of PEMFC between the objectives as per the demand. The adaptability in controller tuning for MPP and voltage regulation has been formulated as multi-objective optimization (MOO) problem with a constraint on controller parameters, for allowing the PEMFC operation closer to MEP. The solution of MOO problem provides a set of controller configurations, each achieving different operating scenarios/objectives of the PEMFC system. Compared to the existing works aiming at either of the objectives, the effectiveness of the proposed approach is reflected in terms of simultaneous attainment of all the objectives.

Proton exchange membrane fuel cell vehicles using hydrogen as fuel has become one of the key development directions in the field of new energy vehicles. However, hydrogen is flammable, it is easy to trigger serious safety accidents once hydrogen leak occurs. Therefore, the application of hydrogen leakage diagnosis methods is essential for the safe operation of proton exchange membrane fuel cell system. This paper reviews the existing methods of diagnosing hydrogen leakage for proton exchange membrane fuel cell system. The principles, research status and application scopes of different methods are elaborated, and these methods are analyzed based on three aspects of on-line diagnosis, real-time performance and calculation complexity. Furthermore, suggestions are provided for the selection of on-line hydrogen leakage diagnosis methods for fuel cell vehicles. Based on this review, readers can easily understand the current status of hydrogen leakage diagnosis methods for proton exchange membrane fuel cell system, and it can provide references for the application selection of the hydrogen leakage diagnosis methods for fuel cell vehicles.

Proton Exchange Membrane Fuel Cells (PEMFC) is considered a propitious solution for an environmentally friendly energy source. A precise model of PEMFC for accurate identification of its polarization curve and an in-depth understanding of all its operating characteristics attracted the interest of many researchers. In this paper, recent meta-heuristic optimization methods have been successfully applied to evaluate the unknown parameters of PEMFC models, particularly Marine Predators Algorithm (MPA) and Political Optimizer (PO) techniques. The proposed optimization algorithms have been tested on three different commercial PEMFC stacks, namely BCS 500-W, SR-12PEM 500 W, and 250 W stack under various operating conditions. The sum of square errors (SSE) between the results obtained by the application of the estimated parameters and the experimentally measured results of the fuel cell stacks was considered as the objective function of the optimization problem. In order to validate the effectiveness of the proposed methods, the results are compared with those obtained in the literature. Moreover, the I/V curves obtained by the application of MPA and PO showed a clear matching with datasheet curves for all the studied cases. Statistical analysis has been performed to evaluate the robustness of the MPA and PO techniques. Finally, the PEMFC model based on the MPA technique surpasses all compared algorithms in terms of the solution accuracy and the convergence speed. The obtained results confirmed the superiority and reliability of the applied approach of the MPA algorithm. The results prove that the MPA algorithm has a superior performance based on its reliability.

This article assesses the energy management of reconfigurable residential smart hybrid AC/DC microgrids considering the combined heat and power (CHP) loads as well as the electric vehicles charging/discharging behaviors. A holistic model is developed for the proton exchange membrane fuel cell to retrieve the unwanted thermal energy generated at the operation time. The proposed model makes use of the unoccupied capacity of the fuel cell for producing/storing hydrogen for the later usage and increasing its efficiency. A stochastic framework is designed using point estimate method (PEM) to capture the uncertainties of the photovoltaic and wind turbine forecast error, power company price, the operating temperature of the proton exchange membrane fuel cell, the price for natural gas, price for selling hydrogen, and the pressure of the H2 and O2 in the fuel cell stack. The PEM approach has shown superior advantages in terms of accuracy and running time. Considering the complex and nonlinear structure of the proposed framework, a proficient optimization technique based on the teacher learning algorithm (TLA) is devised. A two-phase modification method is proposed to increase the algorithm variety and help its convergence characteristics. The performance of the proposed algorithm is compared with the TLA, particle swarm optimization (PSO) algorithm and genetic algorithm (GA). For enhancing the security of the energy and data transaction within the system, a directed acyclic graph (DAG)-based security framework is introduced to guarantee the performance of the system against the subversive accesses. By using this scheme, the essential data of the units are recorded and secured in the form of public, private and transaction blockchains. The economic characteristics of the proposed method are assessed on a residential hybrid AC-DC microgrid test system.

In this paper, an efficient optimization technique called Chaotic Harris Hawks optimization (CHHO) is proposed and applied for estimating the accurate operating parameters of proton exchange membrane fuel cell (PEMFC), which simulate and mimic its electrical performance. The conventional Harris Hawks optimization (HHO) is a recent optimization technique that is based on the hunting approach of Harris hawks. In this proposed optimization technique, ten chaotic functions are applied for tackling with the studied optimization problem. The CHHO is proposed to enhance the search capability of conventional HHO and avoid its trapping into local optima. The sum of squared errors (SSE) between the experimentally measured output voltage and the corresponding simulated ones is adopted as the objective function. The developed CHHO technique is tested on four various commercial PEMFC stacks to assess and validate its effectiveness compared with other well-known optimization techniques. A statistical study is performed to appreciate the stability and reliability of the proposed CHHO technique. However, the results show the effectiveness and superiority of proposed CHHO compared with the conventional HHO and other competitive metaheuristic optimization algorithms under the same study cases.

Hydrogen economy is one of the recently opened alternatives in the field of non-polluting energy. Hydrogen fuel cells show high performance, high reliability in stationary applications and minimal environmental impact. To increase the efficiency of the hydrogen fuel cell it is very important to have a good model to predict its dynamic behavior. In addition, this model must be able to adapt iteratively to the changes that occur in its performance due to operating conditions and even to the degradation through its lifespan. This paper presents the application of an iterative fuzzy modeling methodology based on the extended Kalman filter applied to a real hydrogen fuel cell. Two algorithms based on the Kalman filter will be compared with the well-known backpropagation algorithm from three different initializations: by uniform partitioning, subtractive clustering and CMeans clustering. The used data have been collected during the actual operation of a real 3.4 kW proton exchange membrane fuel cell. As the article experimentally shows, the Takagi-Sugeno type fuzzy model allows to create a very accurate nonlinear dynamic model of the fuel cell, which can be very useful to design an efficient fuel cell control system.

The efficiency and durability of a Proton Exchange Membrane Fuel Cell (PEMFC) can be improved with proper controller design to regulate the flow of reactants, cell stack temperature and humidity of the membrane. In this paper, sliding mode controllers (SMC) are proposed for a polymer electrolyte membrane fuel cell PEMFC. In particular, first order SMC and second order SMC based on super twisting algorithm are designed and investigated. The actual process has been formulated in simulation by Pukurushpan’s ninth order model. Performance of both control laws has been compared in simulation in MATLAB/Simulink environment in terms of oxygen excess ratio, net power generated, stack voltage/power produced and compressor motor voltage. Simulation results dictate that second order SMC demonstrates superior performance in terms of set-point tracking and disturbance rejection. The designed controller makes the interaction of various subsystems in a smooth manner and consequently improves the overall efficiency of the system and prolongs the stack life of the fuel cells.

This paper investigates the oxygen starvation and parasitic loss prevention problem of the adaptive oxygen excess ratio (OER) control system of nonlinear proton exchange membrane fuel cells (PEMFCs). Asymmetric OER constraints are considered to avoid oxygen starvation and parasitic loss in the air supply system of PEMFCs. An approximation-based adaptive control strategy is established to ensure robust regulation of the OER while not violating the OER constraints, regardless of unknown system parameters, nonlinearities, and the abrupt changes of the load current. A dynamic surface design technique using an asymmetric barrier Lyapunov function is employed for a recursive control design. Compared with existing control approaches for uncertain nonlinear air supply systems of PEMFCs, this paper first considers the oxygen starvation and parasitic loss prevention problem for the regulation of optimal OER in the control field of nonlinear PEMFCs. Using the Lyapunov stability theorem, the boundedness of all closed-loop signals and the convergence of the output tracking error to the vicinity of zero are proved.

This paper addresses the design of a systemic management to improve the energetic efficiency of an open cathode proton exchange membrane fuel cell (PEMFC) in a hybrid system. Unlike the other similar works, the proposed approach capitalizes on the usage of both thermal management strategy and current control to meet the requested power from the system by the minimum fuel consumption. To do so, firstly, an experimentally based 3D mapping is performed to relate the requested power form the PEMFC to its operating temperature and current. Secondly, the reference temperature which leads to gaining the demanded power by the minimum current level is determined to minimize the hydrogen consumption. Finally, the temperature control is formulated by an optimized fuzzy logic scheme to reach the determined reference temperature by acting on the cooling fan of the PEMFC system, whilst the current is being regulated by its controller. The inputs of the fuzzy controller are the PEMFC current and temperature error and the sole output is the duty factor of the fan. The proposed methodology is tested on an experimental test bench to be better evaluated in a real condition. The obtained results from the proposed systemic management indicate promising enhancement of the system efficiency compared to a commercial controller. The proposed method of this work is extendable and applicable in fuel cell hybrid electric vehicles.

In order to optimise the performance of Proton Exchange Membrane Fuel Cells (PEMFCs) and to maximise their life cycle, water content has to be properly controlled. This paper presents a model-based method to determine the effect of load on PEMFC water content in PEMFCs using Acoustic Emission (AE) measurements. The developed model was implemented in COMSOL and verified using a single proton exchange membrane fuel cell (FC) operated under various loads. Acoustical events originating from water bubble formation have been identified and assessed using statistical parameters determined in the time and frequency domains. The feasibility of using AE techniques to detect and monitor the impact of a cell’s load variation on water content is assessed. As the model results were in good agreement with experimental data, it was concluded that an AE based method could serve as an effective monitoring and control tool of water content in PEMFCs. Statically, the root mean square for acoustic emission activity has a significant relation with load characteristics and can, potentially, be a candidate for determining the AE behavior in a PEMFC.

This paper introduces a novel controller design for pressure control in the proton exchange membrane (PEM) fuel cells. The proposed controller can control the system under the fault/failure of the actuators. The introduced design uses an artificial neural network for online fault detection and isolation in the pressure valves of the PEM fuel cell (PEMFC). We designed a nonlinear controller based on feedback linearization technique to compensate for the fault effects in real time. We also investigated the stability of the proposed design based on the Lyapunov theory. The simulation and the hardware in the loop results clearly show that the proposed active fault-tolerant control design is able to detect, estimate, and track the PEMFC actuators faults and failure accurately, and to compensate for their negative impacts while keeping the desired control performances in real time.

International audience; During the lifespan of a Polymer Electrolyte Membrane Fuel Cell (PEMFC) system, some heterogeneities between the cells constituting the stack can appear. The voltage of one particular cell in a stack may decrease because of specific aging or local malfunctioning such as drying. As a result, more heat is generated in this cell leading to an increase in its temperature and thus an additional voltage loss. This snowball effect can result in the failure of the cell. Therefore, the lifetime of a PEMFC stack can be increased by applying energy management to its cells. Notable that the output voltage of a cell is lower than a stack. Hence, a high conversion ratio converter is necessary to implement such energy management. An efficient way to increase the output voltage is to connect the output capacitors of the converters such as the boosts in series. Ensuring the converters' controllability is a key point to implement energy management. In this paper, an equalizer system is proposed to ensure the controllability of the boost converters. The balancing speed and the low number of switches are the main advantages of this system. The validity of the proposed system is verified through simulation and experiments.

The aviation industry pursues the integration of fuel cells (FCs) to reduce pollutant emissions. Their connection to the on-board power supply leads to new requirements for electrical grid protection. The limited short-circuit current of a weight-optimized FC system cannot trip a standard fuse. Hence, in this paper, a new protection device is developed as an under/overvoltage primary protection. The proposed device consists of three basic elements: relay; differential amplifier; and current source. This paper includes a detailed description of the protections design process, which includes a requirement analysis, a detailed robustness consideration, and an experimental validation of a developed prototype.

International audience; Proton exchange membrane fuel cell (PEMFC) degradation prediction is essential especially in transportation applications, since one of the major issues that hinder its worldwide commercialization is represented by its durability. However, due to the complex physical phenomena inside the fuel cell, which are usually strongly inter-coupled, the conventional semi-empirical model-based prognostics approach may fail to predict the aging phenomena under various fuel cell operating conditions. In order to improve prognostics accuracy, this paper proposed a data-fusion approach to forecast the fuel cell performance based on long short-term memory (LSTM) recurrent neuron network (RNN) and auto-regressive integrated moving average (ARIMA) method. LSTM can efficiently make a prediction regarding long-term physical degradation, whereas the fusion with ARIMA can effectively track the degradation tendency. In order to validate the performance of the proposed data-fusion approach, two different PEMFCs are tested for recording the aging experimental datasets. The forecasting results indicate that the proposed LSTM-ARIMA approach can accurately predict PEMFC degradation, which can be then used directly to optimize fuel cell performance implemented in transportation applications.

The efficiency of a proton exchange membrane fuel cell system (PEMFCS), which includes a PEMFC stack and a dc/dc converter, depends on the applied voltage and there exists an efficiency extreme point (EEP) in PEMFCS. Therefore, the EEP of PEMFCS changes with varying load, because the system parameters are also varying. It makes EEP tracking (EEPT) a challenging assignment. In order to achieve the EEP operation of PEMFCS under varying load conditions without oscillation, this paper proposes a novel EEPT method based on a forgetting factor recursive least square (FFRLS) online identification. The FFRLS algorithm is based on data-driven and uses real-time data of the system to improve the estimation accuracy of PEMFCS parameters under the changing load. On the test bench of PEMFCS-battery system consists of 300-W PEMFCS, lithium-ion battery, PEMFC controller, and DSP controller, a multi-index performance test and comparative analysis were carried out. The results showed that the proposed method is not sensitive to load conditions. The performance of the proposed EEPT method for PEMFCS has been successfully validated. In addition, compared with the “perturb and observe” and “incremental conductance” online tracking algorithms, the proposed online identification method can get more satisfactory results. Such as, reducing the tracking time and hydrogen consumption, making the output power of PEMFCS smoother, which means its operation stress is smaller, and thus, it lasts longer.

In this paper, a model-based robust control is proposed for the polymer electrolyte membrane fuel cell air-feed system, based on the second-order sliding mode algorithm. The control objective is to maximize the fuel cell net power and avoid the oxygen starvation by regulating the oxygen excess ratio to its desired value during fast load variations. The oxygen excess ratio is estimated via an extended state observer (ESO) from the measurements of the compressor flow rate, the load current, and the supply manifold pressure. A hardware-in-loop test bench, which consists of a commercial twin screw air compressor and a real-time fuel cell emulation system, is used to validate the performance of the proposed ESO-based controller. The experimental results show that the controller is robust and has a good transient performance in the presence of load variations and parametric uncertainties.

Trabajo presentado en el 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ), celebrado en Västerås (Suecia), del 7 al 10 de septiembre de 2021, Recently, new alternatives to conventional energy sources such as fossil fuels are arising due to global problems related to climate change effect and energy shortage. In this context, fuel cells and combined heat and power technologies appear as a possible solution due to their ability to provide both electrical and thermal energy more efficiently compared to traditional methods. Related to this, high-temperature proton exchange membrane fuel cells offer the possibility of implementing combined heat and power systems, and they are also considered an efficient technology that emits less greenhouse gases. In this article a model predictive control based energy management system for a specific house is presented. Simulation and control models of the system are presented, together with dimensions and energy profiles used. Finally, control objectives and the proposed control algorithm are detailed, and the results when trying to match residential heat and power demands are discussed., This work has been partially funded by the Spanish national project DOVELAR (ref. RTI2018-096001-B-C32). This work is partially funded by AGAUR of Generalitat de Catalunya through the Advanced Control Systems (SAC) group grant (2017 SGR 482)

A four-module PEM fuel cell stack was electrochemically characterized prior to its incorporation to a hybrid power plant of an electrical utility vehicle. The 3 kW fuel cell stack, comprised of 4 units of 100 membrane electrode assemblies (MEAs) in an open-cathode and air-cooled configuration, was characterized in order to identify its optimum operational parameters. The open cathode configuration is a common approach to reduce parasitic loads and increase energy efficiency in fuel cells; however, the forced convection derives frequently to internal dehydration. Voltage reversal caused by lack of reactants, many times due to dehydration at the reaction sites (membrane-electrode interface) is a common failure source for this kind of configuration especially at high current demands. Therefore, water management becomes crucial for preventing fuel cell’s performance decrease and permanent failure. Subsequently, a smart water management strategy had to be established prior to the power plant integration into the vehicle for the fuel cell’s performance to be guaranteed during the vehicle duty cycle. For this purpose, a testing protocol was established for testing each module based on linear voltammetries, electrochemical impedance spectroscopy and thermal images in order to observe cell’s voltage and resistance as indicators of internal hydration, reactants concentration, and heat distribution during the stack operation. Polarization curves were obtained for each module and from them, the point (voltage, current, temperature and air vent) for steady operation was identified as the recommended condition for nominal performance during the fuel cell operation in the hybrid power plant of the electrical vehicle.

In this paper, a feedback linearization controller is proposed for the van compressor in the air supply system of a proton exchange membrane fuel cell. The control goal is to avoid oxygen starvation and reduce power consumption by tracking an optimal reference oxygen excess ratio. Specifically, an improved control-oriented third-order model of the air supply system is proposed with the model identification of the air compressor. The optimal reference oxygen excess ratio is obtained from experiments to maintain a maximum net power. Based on the air supply system model, a nonlinear controller is designed to track the optimal oxygen excess ratio using feedback linearization. Lyapunov-based technique is utilized to analyze the stability of the closed-loop system. Effectiveness of the proposed approach is illustrated by experimental results.

The monitoring of engineering systems is becoming more common place because of the increasing demands on reliability and safety. Being able to diagnose a fault has been facilitated by technology developments. This has resulted in the application of methods yielding an earlier detection and thus prompted mitigation of corrective measures. The level of maturity of monitoring systems varies across domain areas, with more nascent systems in newly emerging technologies, such as fuel cells. With the increasing complexity of systems comes the inclusion of more sensors, and for expedient on-line diagnosis utilizing the information from the most appropriate sensors is key to enabling excellent diagnostic resolution. In this paper, a novel sensor selection algorithm is proposed and its performance in polymer electrolyte membrane (PEM) fuel cell on-line diagnosis is investigated. In the selection procedure, both sensor sensitivities to various failure modes and corresponding fuel cell degradation rates are considered. The optimal sensors determined from the proposed algorithm are compared with previous sensor selection techniques, where results show that the proposed algorithm can provide more efficient sensor selection results using less computational time, which makes this method better applied in practical PEM fuel cell systems for on-line diagnostic tasks.

The high costs of fuel cell stacks are often prohibitive for research applications. Instead, researchers tend to either perform tests on individual cells under emulated load conditions, or they use model-based emulated fuel cell stacks to test realistic loads. This paper presents an alternative technique that allows the simultaneous investigation of both cell and hardware. In this technique, an amplifier takes as input the voltage of a reference fuel cell and reproduces the “scaled-up” voltage that would be provided by a stack of similar cells. The output terminals of this simulated stack can be connected to realistic loads, which are series connected with the reference cell to maintain a one-to-one correspondence of cell and load currents. This technique allows the simultaneous investigation of stack/load interactions, stack electrochemical performance characteristics, and stack durability under load. The amplifier electronics are independent of the fuel cell allowing its use with all fuel cell types, e.g., solid oxide fuel cells (SOFCs) or proton exchange membrane fuel cells. We demonstrate the emulator using a single planar SOFC and under several real loads. The data collected reveal good steady-state and dynamic accuracy, and the observed electrical interactions highlight the utility of the emulator in cell and hardware-in-the-loop testing. Ultimately, this technique provides fuel cell system researchers and developers a low-cost, easily implemented tool for rapid assessment of novel fuel cell technologies under real-world loading conditions.

In this paper, an estimator-based nonlinear globally linearizing controller (GLC) is proposed for regulating a multivariable nonlinear proton exchange membrane fuel cell. To represent the actual process, we have adopted a simulated model and then validated it with experimental data. Aiming to formulate a state estimator, the predictor model is derived with a reduced number of model equations with considering only the controlled variables as true states, keeping others as augmented states with no dynamics. Instead of computing all states, which is quite a common phenomenon for most of the estimators, the proposed adaptive state observer (ASO) computes a limited number of states as per the GLC requirement. This, in turn, leads to a large process/model mismatch, the effect of which is attempted to reduce by introducing a variable tuning parameter of ASO. Subsequently, the GLC structure is synthesized with combining a nonlinear transformer (input–output linearizing state feedback), a dual-loop external linear controller, and an adaptive state observer. The superiority of the proposed GLC-ASO scheme is finally shown over a conventional dual-loop proportional–integral controller in terms of set point tracking and disturbance rejection.

Proton exchange membrane fuel cell (PEMFC) is an ideal form of power generator, but its performance is drastically compromised under dynamic loading conditions. For the purpose of correctly understanding and accurately predicting the power performance of PEMFC under dynamic loading conditions so as to facilitate the rational design of PEMFC vehicles, this paper first built a high-fidelity 3D model of a PEMFC, then precisely calculated the dynamic voltage response during the non-steady stages, and finally identified the influential factors that can moderate the dynamic response. Results suggest that avoiding extremely large rate of current density change can keep the PEMFC running in steady state, which is beneficial to the lifetime of the PEMFC. Meanwhile, raising the anode/cathode pressure to 2.0 atm, maintaining the excess H2/O2 coefficients above 2.0/2.5, or keeping the anode/cathode inlet sufficiently humidified to 100% R.H. help the PEMFC to quickly reach new equilibrium in response to dynamic loading. The novelty of this paper is embedded in the detailed modeling of the PEMFC micro structure as well as the systematic parametric analysis of the potential moderating factors and mechanisms of the dynamic response.

Due to the more vigorous regulations on carbon gas emissions and fuel economy, Fuel cell electric vehicles (FCEV) are becoming more popular in the automobile industry. This paper presents a neural network-based maximum power point tracking (MPPT) controller for 1.26-kW proton exchange membrane fuel cell (PEMFC), supplying electric vehicle powertrain through a high voltage-gain dc-dc boost converter. The proposed neural network MPPT controller uses a radial basis function network (RBFN) algorithm for tracking the maximum power point of the PEMFC. High switching-frequency and high voltage-gain dc-dc converters are essential for the propulsion of FCEV. In order to attain high voltage-gain, a three-phase high voltage-gain interleaved boost converter is also designed for FCEV system. The interleaving technique reduces the input current ripple and voltage stress on the power semiconductor devices. The performance analysis of the FCEV system with RBFN-based MPPT controller is compared with the fuzzy logic controller in MATLAB/Simulink platform.

The paper deals with reliability issues of a diesel-powered fuel cell auxiliary power unit (APU). The unit combines an autothermal diesel reformer and a proton exchange membrane fuel cell stack. The focal point is mitigation approaches for increasing the reliability of the complete APU system. These include control strategies on the one side, and electronic hardware solutions on the other. The measures, guarantying safe, reliable, and long-life operation, were developed, implemented and experimentally validated on a 3-kW net electric power APU system targeted for truck on-board applications.

This paper studies a real-time control problem for a hybrid power system consisting of a proton exchange membrane fuel cell (FC), a unidirectional boost converter, and a lithium-ion battery. An adaptive control strategy is proposed to manage the power sharing in this hybrid power system. System constraints, including the slow dynamics of the FC and the state of charge of the battery, are explicitly considered. The controller achieves tracking a dynamically changing load demand while satisfying the system constraints based on parameter estimations. The main contribution is that, compared with the previous control methods, the proposed control design for hybrid power systems has provable stability and convergence closed-loop properties. Simulation and experimental results are provided to validate the control design.

Hydrogen-air proton exchange membrane U+0028 PEM U+0029 fuel cell is a promising clean energy. However, the stack output tracking control is still a challenging problem due to the soft characteristic of the stack. Both over- and less- control will cause the stack flooding or oxygen lacking which dramatically decreases the life of stacks. Traditional control methods rely on the accurate model of the fuel cell system, which is a high-order nonlinear system, and involve a complex controller design process. This paper combines the data-based fuzzy cluster modeling technology with the sliding mode control and the integral actions. The sliding mode controller tracks the dynamic changes of the fuel cell system and the integral controller eliminates the steady-state errors. Simulation results demonstrate good performance of the proposed control method.