Search

In this paper, we focus on addressing the air supply problem for fuel cells. The air supply system faces a challenge: operating at maximum load consumes a significant amount of power, while insufficient air can lead to oxygen starvation problems in fuel cells. An important metric, the oxygen excess ratio, indicates whether the fuel cell is receiving the appropriate amount of air. Unfortunately, directly measuring this ratio is generally impractical. To overcome this limitation, we propose a fixed-time observer that reconstructs the oxygen excess ratio within a short predetermined period. By utilizing this reconstructed index, we introduce a cascaded double-loop controller. Specifically, both the external and internal loops are regulated using a modified prescribed time control strategy. This approach enables the regulation of the oxygen excess ratio to the optimal value within a prescribed short time. The advantages of our proposed method are validated through hardware in-loop experiments, showcasing its superiority over conventional finite-time control techniques. • The controller ensures the oxygen excess ratio is regulated in a prescribed time. • The oxygen excess ratio is unmeasurable, so we estimate it by a Fixed-time observer. • A comparison with finite-time control is presented in a hardware-in-loop experiment. • The proposed method shows robustness against disturbance and parameter uncertainties. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

In this paper, the design of a nonlinear observer-based fault diagnosis approach for polymer electrolyte membrane (PEM) fuel cell air-feed systems is presented, taking into account a fault scenario of sudden air leak in the air supply manifold. Based on a simplified nonlinear model proposed in the literature, a modified super-twisting (ST) sliding mode algorithm is employed to the observer design. The proposed ST observer can estimate not only the system states, but also the fault signal. Then, the residual signal is computed online from comparisons between the oxygen excess ratio obtained from the system model and the observer system, respectively. Equivalent output error injection using the residual signal is able to reconstruct the fault signal, which is critical in both fuel cell control design and fault detection. Finally, the proposed observer-based fault diagnosis approach is implemented on the MATLAB/Simulink environment in order to verify its effectiveness and robustness in the presence of load variation. [ABSTRACT FROM PUBLISHER]

In this paper, a nonlinear observer is proposed for a PEMFC system, based on Second Order Sliding Mode (SOSM) techniques. The goal is to estimate the hydrogen partial pressure in the anode channel of the PEMFC, using the measurements of stack voltage, stack current, anode pressure and anode inlet pressure. The proposed observer employs a nonlinear error injection term, where the error is obtained from the difference between the system voltage output obtained from an experimental validated nonlinear model and estimated voltage output obtained from the designed observer. The robustness of this observer against parametric uncertainties and load variations is studied, and the finite time convergence property is proved via Lyapunov analysis. Simulation results illustrate the effectiveness and robustness of the proposed approach. [ABSTRACT FROM AUTHOR]

This paper presents an observer-based fault reconstruction method for PEM fuel cells. This method extends the results of a class of nonlinear uncertain systems with Lipschitz nonlinearities. An adaptive-gain second-order sliding mode (SOSM) observer is developed for observing the system states, where the adaptive law estimates the uncertain parameters. The inherent equivalent output error injection feature of SOSM algorithm is then used to reconstruct the fault signal. The performance of the proposed observer is validated through a hardware-in-loop emulator. The experimental results illustrate the feasibility and effectiveness of the proposed approach for application to fuel cell air-feed systems. [ABSTRACT FROM PUBLISHER]

In this paper, an adaptive algebraic observer is proposed for a Polymer Electrolyte Membrane Fuel Cell (PEMFC) air-feed system, based on Higher Order Sliding Mode (HOSM) differentiators. The goal is to estimate oxygen and nitrogen partial pressures in the fuel cell cathode side, using measurements of supply manifold pressure and compressor mass flow rate. As the proposed technique requires the time derivatives of the states, Lyapunov-based adaptive HOSM differentiators are synthesized and implemented for estimating these derivatives without a-priori knowledge of the upper bounds of their higher order time derivatives. The performance of the proposed method is validated through experiments on a Hardware-In-Loop (HIL) test bench. These results illustrate the feasibility and effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Prognostics and Health Management (PHM) offer a potential solution to improve the durability of Proton Exchange Membrane Fuel Cells (PEMFCs), where degradation prognostic is the key component of the PHM system. However, limited by the dynamic operating environment, accurate and efficient prognostic algorithms still required for real applications. In this paper, the Seasonal-Trend Disentangle (STD) based prognostic framework is proposed to enhance the Remaining Useful Life (RUL) prediction of PEMFC system. Specifically, a lightweight parameter estimation neural network is introduced to estimate the aging parameters of the FC degradation model directly from PEMFC measurements. Besides, the integral of the FC degradation model at the specified current density range serves as the comprehensive Health Index (HI), which could combine different aging parameters and mitigate the effect of load dynamics. The STD-based prognostic model effectively captures the time-invariant features in the HI sequence from trend and seasonal phases, improving Remaining Useful Life (RUL) prediction performance. The proposed prognostic model is compared with RNN-family, ESN, and Dilated CNN methods using three distinct durability datasets from FCs operating under static, quasi-dynamic, and cyclically varying dynamic current loads. Experimental results demonstrate that the proposed algorithm outperforms the reference methods in terms of RMSE and MAPE metrics in the aging prognostic, and the proposed method could obtain satisfactory RUL prediction results 100–150 h earlier than the reference methods. [Display omitted] • STD-based model extracts time-invariant features of historical sequences. • New health index is proposed to represent state of PEMFC. • Aging parameters of PEMFC are estimated by nonlinear estimation network. • Proposed lightweight model provides competitive prognostic accuracy. [ABSTRACT FROM AUTHOR]

Electrochemical Impedance Spectroscopy (EIS) serves as a valuable tool for analyzing the health of Proton Exchange Membrane Fuel Cell (PEMFC). However, the practical application of EIS-based fault diagnosis algorithms continues to face challenges, including time-consuming EIS measurements, inefficient Equivalent Circuit Model (ECM) parameter estimation, and limited generalization capability of fault diagnosis models. To enhance the utility of the EIS-based fault diagnosis methods, this paper develops a new deep-learning-based PEMFC fault diagnosis framework, along with a frequency selection method. Specifically, a Parameter Estimation Unit (PEU) is introduced to derive the ECM parameters directly from EIS measurements. A Frequency Selection Unit (FSU) based on the Gumbel-Softmax trick is proposed to enable the identification of the optimal frequency solution to maximize fault diagnosis performance with a predetermined number of measured frequency points. Furthermore, a Feature Augmentation Unit (FAU) is proposed to generate robust diagnosis features based on ECM parameters, thus reducing the influence of non-fault operations on fault diagnosis results. Experiments based on real EIS data demonstrate the effectiveness of the proposed algorithm. With these innovations, the proposed framework could significantly improve the efficiency and accuracy of fault diagnosis in PEMFC. [Display omitted] • EIS-based fault diagnosis method is proposed to address the fault diagnosis of PEMFC. • Frequency selection unit is proposed to find redundant frequencies in EIS. • Discrete loss function is used to avoid the duplicate selection of frequencies. [ABSTRACT FROM AUTHOR]

Air compressor which is to used to deliver the air (including about 21% oxygen) to the cathode channel for electrochemical reaction is a crucial component for the polymer electrolyte membrane (PEM) fuel cell. The working characteristics of the compressor greatly influences the fuel cell performance as well as the durability. In this paper a semi-physical modeling method is adopted to analyze the operating property of a centrifugal compressor which is more suitable for automotive fuel cells because of its compactness. This model includes many physical and empirical parameters which are very difficult to determine. Interior-point optimization method based on Newton iteration is used to identify those parameters. The result shows that the modeled compressor map has a good agreement with the experimental data. Meanwhile, the compressor efficiency is analyzed and compared with the measurement to further validate the developed model. This compressor is thus adapted to a validated 10 kW fuel cell model. A dynamic feedforward controller is proposed based on the load torque to control the air mass flow, eliminating the disturbance produced by the compressor load in transient. The simulation results show that this compressor could satisfy requirements of the fuel cell under dynamic load situations while keeping both the fuel cell and compressor with high efficiencies. [ABSTRACT FROM AUTHOR]