With the development of electric vehicles and microgrids, the demand for energy storage is growing rapidly. Sodium-ion batteries, due to their abundant reserves, high energy density, and good safety, are beginning to be used in electric vehicles and energy storage power stations. High-precision modeling is the basis for state estimation and energy management of sodium-ion batteries. Fractional-order equivalent circuit model is favored for its balance between computational complexity and accuracy. In this study, electrochemical impedance spectroscopy tests were conducted on sodium-ion batteries, and a fractional-order equivalent circuit model in a wide temperature range considering aging, was established. The model parameters can be identified online using the global optimization algorithm based on dynamic cycling condition. The model's accuracy was verified under different temperatures and dynamic working conditions. The results show that, compared to the Thevenin model and second-order equivalent circuit model, the fractional-order equivalent circuit model can better fit the terminal voltage of sodium-ion batteries, with a mean relative error of less than 4%.

In transportation and portable applications, prognostic health management is essential to achieve long life and good performance of proton exchange membrane fuel cell (PEMFC). While the performance degradation mechanism of fuel cells (FCs) is complex and affected by multiple factors, achieving highly accurate health prediction remains a challenging problem. In this article, a long-term performance prediction method for FCs combining degradation mechanisms and machine-learning methods is proposed. First, the aging parameters characterizing the degradation of the catalyst, diffusion layer, and proton exchange membrane are estimated using the extended Kalman filter (EKF). Besides, considering the complexity of aging influences, sufficient correlation analysis, and variable selection are performed. Second, the relationship between external operating conditions and internal health characteristics is constructed by a multiobjective Gaussian process regression (MOGPR) algorithm. Finally, the aging path and remaining useful life (RUL) of the PEMFC are predicted under three operating conditions. The root mean square error is less than 0.024 V and 12.43 h. The results indicate that the proposed method can provide accurate PEMFC predictions.

This paper presents a novel approach to the capacity allocation problem in fuel cell hybrid vehicles. It introduces a multi-objective evolutionary algorithm nested Dynamic Programming (DP) strategy aimed at minimizing both manufacturing and operating costs. The outer loop employs a fast-converging Multi-Objective Particle Swarm Optimization (MOPSO) algorithm based on competitive mechanisms for parameter matching, while the inner loop employs DP for energy management. The effectiveness of the proposed method is validated through simulation under specific operating conditions. Comparative analysis with traditional MOPSO demonstrates superior performance in terms of solution set diversity and convergence, affirming the efficacy of the proposed approach.

Fuel cells have been studied for use in stationary power generation and vehicle propulsion systems. The fuel cell thermal management subsystem is coupled and nonlinear, posing challenges for modeling and temperature control. This paper aims to integrate the physical models of the fuel cell stack, pump, thermostat, and other components combined with intelligent algorithms into an efficient system-level thermal management model framework and develop a model predictive controller to solve the temperature control problem. First, a physics-based nonlinear model of the fuel cell system is developed and used as a basis to identify the linearized model for different operating points. Then, the global model is obtained by fusing the local models with Gaussian validity functions using the local linear model tree method. Third, a multi-step prediction model is derived based on the local model networks, and a parameterized linear state space form is obtained and used for controller design. Furthermore, an online correction method is developed to reduce the model discrepancy. Finally, the accuracy of the system model and the performance of the proposed controller are verified by open-loop experimental data and a series of closed-loop simulation cases.

In recent years, supervised deep learning-based methods have achieved significant results in fuel cell system fault diagnosis. However, most existing deep learning-based fault prediction methods suffer from missing fault labels and data limitations due to the difficulty in obtaining fault and degradation data in real fuel cell systems. To address the above challenges, this paper proposes a fault diagnosis method based on digital twin and unsupervised domain adaptive learning. The method has two key features: First, a maximum-relevance minimum-redundancy algorithm is used to select the input signals. Then a high-order fuel cell system model is developed to obtain a large amount of digital domain fault data at low cost by simulating fault injection. Second, domain-invariant features are extracted using a domain-adaptive adversarial learning approach to reduce the distribution differences between the digital and real domains. The method successfully diagnosed nine typical faults in the fuel cell air, hydrogen, and thermal subsystems without real data fault labels. Under dynamic load conditions, the diagnostic accuracy reached 92.5 %. In addition, the method achieves a diagnostic accuracy of over 90 % under domain adversarial training using only normal real data. The experimental results show that the proposed method can achieve fuel cell system fault diagnosis without fault labels and significantly reduce the dependence on fault data.

A well-designed hybrid powertrain is crucial for ensuring the safe, efficient, and durable operation of fuel cell hybrid vehicles. This paper introduces a modular design approach for powertrains, utilizing a Competitive mechanism-based Multi-Objective Particle Swarm Optimization (CMOPSO) algorithm integrated with nested dynamic programming. In this approach, the upper layer employs the CMOPSO algorithm to design the powertrain system, while the lower layer optimizes power coordination for each proposed design. This two-layer optimization framework considers factors such as vehicle economy and durability. Under WLTP conditions, the capacity configuration results are a fuel cell with a rated power of 22 kW, 100 batteries in series, and 7 batteries in parallel. Furthermore, the modular approach outperforms three other algorithms in terms of solution count, diversity, and overall performance metrics. The study also highlights that the vehicle’s power demand characteristics, influenced by different driving cycles, significantly affect capacity configuration results. Sensitivity analysis reveals that both the total operating cost and manufacturing cost of the vehicle are most sensitive to variations in the fuel cell rated power.

Proton exchange membrane fuel cells (PEMFCs) vehicles are regarded as the most promising green transportation option, but their widespread adoption is hindered by cost and longevity, and temperature of PEMFCs stack is a crucial factor affecting both efficiency and longevity. Current researches on temperature control mainly focus on the iterative updates of control methods and performance optimization, while there is relatively little research on the detailed analysis of control objectives. Therefore this paper developed an active optimal control strategy for stack temperature with adaptive control objective to enhance the output performance of PEMFCs in hybrid systems. To this end, firstly, a quantitative mapping relationship between operating temperature and current was established through experimental calibration, identifying the optimal temperature path for maximizing output voltage at different current levels. Secondly, a control-oriented voltage model was developed to describe the phenomenon observed experimentally, where the output voltage initially increased and then decreased with the monotonically increasing stack temperature, provided that other parameters remain constant. Finally, an active optimal control strategy is proposed, which actively adjusts the temperature control objective in real-time according to the prevailing operating current and the predetermined optimal temperature path. The comparative validations under both static and dynamic conditions, utilizing three different control methods, demonstrated that the proposed active optimal control strategy clearly outperforms normal control strategy. The maximum performance enhancements achieved were 1.15%, 1.21%, and 1.30%, respectively.

Proton exchange membrane fuel cells (PEMFCs) require an appropriate operating temperature to achieve high performance and longevity. In addressing the critical need for effective thermal management in PEMFCs for vehicle propulsion systems, this study has developed and introduced a novel thermal management system model equipped with dual‐cooling loops. Addressing the issues of slow response and poor dynamic performance inherent in traditional control strategies, as well as the computational complexity that hinders the practical application of existing advanced control strategies, this research proposes a fuzzy proportional‐integral‐derivative (PID) controller optimizing the improved whale optimization algorithm (IWOA‐FPID) aimed at enhancing fan side control. By simulating step changes in current load and designing dynamic operating conditions based on the most basic and simple energy management system, the performance of IWOA‐FPID in temperature control is validated. The final results indicate that the IWOA‐FPID strategy significantly outperforms existing control methods, notably reducing adjustment time and minimizing temperature overshoot to ≈0.5 K. The proposed framework achieves efficient temperature control, highlighting its potential for broader application in vehicular fuel cells and offering a promising solution to the challenges of PEMFC thermal management.

An effective energy coordination strategy is pivotal for fuel cell hybrid vehicles (FCHVs), aiming to optimize the energy synergy between lithium-ion batteries and fuel cells. This serves as the foundation for the sustainable progress in clean energy transportation. This article introduces an energy management strategy designed for real-time applications, with a focus on ensuring the security, efficiency, and prolonged operation of FCHVs. Precisely, leveraging precise system modeling, this article integrates considerations for efficiency awareness, system health, and battery thermal penalties into a structured model predictive control framework. The designed framework utilizes sequential quadratic programming to derive optimal control sequences while operating within multiphysical constraints. Moreover, a deep learning algorithm is employed for velocity prediction, and the article explores the effects of network structure and input-output feature size on prediction accuracy. Ultimately, the proposed strategy is implemented under diverse operating conditions to validate its robustness and to demonstrate its effectiveness in comparison with existing real-time optimization method. In addition, contrasting experiments are conducted to examine the impact of different weights in the multiobjective function.

Proton Exchange Membrane Fuel Cell (PEMFC) vehicles have been widely studied. However, PEMFCs are constrained to large-scale commercialization for safety and durability. Under real working conditions, the humidity of the PEMFC changes with drastically fluctuated load current, which seriously affects the electrochemical reaction, and may even causes serious faults-membrane drying or flooding. Therefore, it is necessary to develop accurate model on crucial internal states and simulate the dynamic characteristics of PEMFC, so that accurate estimation of the internal state can be the vital foundation for feedback control, ultimately to optimize the performance of PEMFC. In this paper, a one-dimension model of water transport across the Nafion® membrane for observer is presented. The analytical model is proposed with two main water transport mechanisms: back diffusion and electro-osmotic drag. The relationship between membrane water content and the easily measurable variables is foundation of observer subsequently. The simulated results show that the MAPE of stack voltage is 8%, which is precise enough to apply convergence algorithm.

Accurately predicting the degradation of fuel cells and then extending their lifespan through reasonable management measures is crucial. This paper proposes a novel method that combines random forest regression with grey wolf optimization algorithm to predict the degradation of fuel cells. First, the measurement data is reconstructed using a Gaussian average weighted smoothing method to reduce the measurement noise. Then, a degradation model of fuel cells is established using random forest regression. Finally, the hyperparameters of the random forest are optimized using the grey wolf optimization algorithm to improve the accuracy of degradation prediction. The effectiveness of this method is verified through degradation experiments conducted at two different load currents. The test results demonstrate that proposed method can significantly improve the accuracy of degradation prediction and outperform other methods in terms of precision.

The proton exchange membrane fuel cell (PEMFC) is a “green” energy conversion device that is widely considered to be one of the best power sources for future electric vehicles and static energy systems. The task of fault diagnosis for PEMFC often faces the dilemma of data shortage, especially in terms of internal faults of the fuel cell. To solve these problems, We proposed a method for model transfer based on hybrid transfer learning to solve the problem of insufficient data sets in the target domain. The key point of this approach is to use the TrAdaBoost algorithm for transfer learning. In order to meet the algorithm’s requirements for initial diagnosis accuracy in practical applications, we combine a fine-tuning model transfer strategy with this algorithm. Compared with other methods, this method has significant improvement in water fault diagnosis accuracy.

Accurate air supply and stable temperature control are important factors to ensure fuel cell safety and high efficiency. In automotive applications, frequent load changes challenge the air supply and thermal management systems of fuel cells. In this paper, a coordination model predictive control strategy based on velocity prediction is proposed to regulate the oxygen excess ratio and stack temperature to improve the fuel cell system efficiency. First, the impact of load current, temperature and oxygen excess ratio on the efficiency is analyzed to obtain the optimal control reference. Then, the future velocity information is predicted by the long short term memory algorithm and integrated into the disturbance sequences. Optimal control trajectory obtained by collaborative optimization of the global objective function for sub-controllers. Finally, the impact of parameters on control performance is analyzed, and the effectiveness of the coordination control strategy is verified under the combined driving condition. The results show that the proposed method can reduce the oxygen excess ratio and temperature control errors by 13.8% and 4.5% compared to the control algorithm without velocity prediction. In addition, the system efficiency is increased by 1.15% due to the introduction of the optimal control reference.

In a proton exchange membrane fuel cell (PEMFC) system, the flow of air and hydrogen is the main factor affecting the output characteristics of the PEMFC, and there is a coordination problem in the flow control of both. To ensure real-time gas supply in the fuel cell and improve the output power and economic benefits of the system, a deep reinforcement learning controller with continuous state based on fusion optimization (FO-DDPG) and a control optimization strategy based on net power optimization are proposed in this paper, and the effects of whether the two gas controls are decoupled or not are compared. The experimental results show that the undecoupled FO-DDPG algorithm has a faster dynamic response and more stable static performance compared to the fuzzy PID, DQN, traditional DRL algorithm, and decoupled controllers, demonstrated by a dynamic response time of 0.15 s, an overshoot of less than 5%, and a steady-state error of 0.00003.

An effective energy management strategy (EMS) is essential to ensure the safe and efficient operation of the fuel cell hybrid vehicles. In this paper, an online adaptive EMS is proposed for the fuel cell hybrid vehicles to minimize hydrogen consumption and adjust the strategy according to the driving conditions. Driving pattern recognition is realized by the improved k-means cluster approach which combines multiple k-means clusters with specific distances to serve as the classifier. In each driving pattern, separate machine learning (ML) models are trained to obtain the energy management regression learner. Comparison experiments are performed to determine the optimal ML model and input parameters. The effectiveness of the proposed EMS is evaluated using two compound test driving cycles. Results show that the proposed method achieves the lowest fuel consumption compared to the other five algorithms considered. Remarkably, it reduces hydrogen consumption by up to 5.66% when compared to commonly used methods.

The hybrid system containing the fuel cell and energy storage sources contributes to realizing hydrogen energy in road traffic applications. It is meaningful to evaluate the different forms of system topology. In this work, the quantitative comparison of topologies and sensitivity analysis of system parameters are conducted. First, the output characteristics of the fuel cell, battery, and ultracapacitor (UC) are modeled by experimental data. Second, the dimensions of four hybrid topologies are determined by an iterative constraint method. An energy management strategy based on dynamic programming (DP) is conducted for all topologies. Then the overall economic cost is used as an indicator for quantitative evaluation, considering the initial acquisition, hydrogen consumption, and component aging. The base-case results illustrate that the fuel/cell battery semi-active topology is the least costly one. Finally, seven parameters are analyzed to determine the system cost’s key factors. The relationship between costs and driving conditions is further studied. The rankings of the normalized parameter analysis results inspire us on how to further reduce the cost of fuel cell hybrid vehicles.

Temperature is a key factor affecting the efficiency and safety of proton exchange membrane fuel cells. It is especially important to keep the fuel cell stack temperature stable under the operating conditions where the load current changes frequently. Firstly, a nonlinear model of the stack and cooling system is developed for a 50kW commercial fuel cell system. Then, a series of local models are established at different operating points to accurately describe the nonlinear characteristics of the proton exchange membrane fuel cell (PEMFC) system. Finally, a multi-model predictive control method based on an adaptive switching strategy is proposed. The simulation results show that the temperature overshoot can be controlled within 1K in the operating range of 50-200A. Compared with the PID and model predictive control(MPC) methods, the multi-model predictive control(MMPC) method has better robustness.

This paper performs sizing determination and energy management of four common fuel cell hybrid systems and compares their performance. Control-oriented models of external properties for fuel cells, batteries, and ultracapacitors are developed. Capacity settings for different systems are determined by analyzing the power and energy constraints of the driving conditions. An energy management strategy based on the dynamic programming approach is implemented, with the optimization objective of minimizing hydrogen consumption. Hydrogen consumption and the aging state of power energy devices are used to evaluate the performance of candidates. The results show that there is no topology with optimal fuel economy and aging performance at the same time.

Selection and peer-review under responsibility the scientific committee of the 13 th Int. Conf. on Applied Energy (ICAE2021). ABSTRACT Proton exchange membrane fuel cells(PEMFCs) have the advantages of clean efficiency, long range and fast recharging, with a short life span and harsh operating conditions. To ensure their safe operation, extend the life of PEMFCs and improve the dynamic characteristics of the power system. This paper uses a combination of PEMFC, battery and supercapacitor (SC) to form a PEMFC hybrid power system. A comprehensive dynamic model is developed for the non-linearity and time-varying nature of the system. Based on this, Adaptive Model Predictive Control (AMPC) is used to allocate power to the system. Minimized hydrogen consumption is considered in the rolling optimization function in AMPC. The simulation is validated by two different types of operating conditions and the experimental results show the effectiveness of the system's model and power allocation strategy. The proposed energy management strategy can improve the stability of the PEMFC output and guarantee that the fuel cell, battery and SC work in a safe interval.

The energy management strategy (EMS) plays an important role in the power system of hybrid-powered fuel cell vehicles in order to reduce hydrogen consumption and fuel cell performance degradation.This paper proposes a robust EMS based on the min-max game theory, where the EMS and the driver behavior are set as two virtual game players making decisions for opposite goals.First, a mathematical model of the hybrid-powered fuel cell vehicle is introduced, that include a transmission system, an ultracapacitor system, a fuel cell system, and the DC/DC converter.Then, a minmax game framework is constructed to describe the energy management problem of fuel cell/ultracapacitor hybrid-powered vehicle with uncertain environment.Finally, the high efficiency and robustness of the proposed strategy are validated by comparing it to the PID-based strategy in the dynamic driving condition.