Intelligent energy management strategy based on hierarchical approximate global optimization for plug-in fuel cell hybrid electric vehicles

The energy management strategy (EMS) is a key to reduce the equivalent hydrogen consumption and slow down fuel cell performance degradation of the plug-in fuel cell hybrid electric vehicles. Global optimal EMS based on the whole trip information can achieve the minimum hydrogen consumption, but it is difficult to apply in real driving. This paper tries to solve this problem with a novel hierarchical EMS proposed to realize the real-time application and approximate global optimization. The long-term average speed in each future trip segment is predicted by KNN, and the short-term speed series is predicted by a new model averaging method. The approximate global optimization is realized by introducing hierarchical reinforcement learning (HRL), and the strategy within the speed forecast window is optimized by introducing upper confidence tree search (UCTS). The vehicle speed prediction and the proposed EMS have been verified using the collected real driving cycles. The results show that the proposed strategy can adapt to driving style changes through self-learning. Compared with the widely used rule-based strategy, it can evidently reduce hydrogen consumption by 6.14% and fuel cell start-stop times by 21.7% on average to suppress the aging of fuel cell. Moreover, its computation time is less than 0.447 s at each step, and combined with rolling optimization, it can be used for real-time application.     

A robust online energy management strategy for fuel cell/battery hybrid electric vehicles

Traditional optimization-based energy management strategies (EMSs) do not consider the uncertainty of driving cycle induced by the change of traffic conditions, this paper proposes a robust online EMS (ROEMS) for fuel cell hybrid electric vehicles (FCHEV) to handle the uncertain driving cycles. The energy consumption model of the FCHEV is built by considering the power loss of fuel cell, battery, electric motor, and brake. An offline linear programming-based method is proposed to produce the benchmark solution. The ROEMS instantaneously minimizes the equivalent power of fuel cell and battery, where an equivalent efficiency of battery is defined as the efficiency of hydrogen energy transforming to battery energy. To control the state of charge of battery, two control coefficients are introduced to adjust the power of battery in objective function. Another penalty coefficient is used to amend the power of fuel cell, which reduces the load change of fuel cell so as to slow the degradation of fuel cell. The simulation results indicate that ROEMS has good performance in both fuel economy and load change control of fuel cell. The most important advantage of ROEMS is its robustness and adaptivity, because it almost produces the optimal solution without changing the control parameters when driving cycles are changed.     

A comprehensive review on energy management strategies of hybrid energy storage system for electric vehicles

The attention on green and clean technology innovations is highly demanded of a modern era. Transportation has seen a high rate of growth in today's cities. The conventional internal combustion engine‐operated vehicle liberates gasses like carbon dioxide, carbon monoxide, nitrogen oxides, hydrocarbons, and water, which result in the increased surface temperature of the earth. One of the optimum solutions to overcome fossil fuel degrading and global warming is electric vehicle. The challenging aspect in electric vehicle is its energy storage system. Many of the researchers mainly concentrate on the field of storage device cost reduction, its age increment, and energy densities' improvement. This paper explores an overview of an electric propulsion system composed of energy storage devices, power electronic converters, and electronic control unit. The battery with high‐energy density and ultracapacitor with high‐power density combination paves a way to overcome the challenges in energy storage system. This study aims at highlighting the various hybrid energy storage system configurations such as parallel passive, active, battery–UC, and UC–battery topologies. Finally, energy management control strategies, which are categorized in global optimization, are reviewed. Copyright © 2017 John Wiley & Sons, Ltd.     

An online prognostics-based health management strategy for fuel cell hybrid electric vehicles

As the energy transformation in the transportation sector is taking place driven by the development of fuel cell technologies, fuel cell hybrid electric vehicles become promising solutions owing to their long driving duration and zero emissions. However, the unsatisfied lifespan of fuel cells is an inevitable obstacle for their massive commercialization. This paper aims to propose an online adaptive prognostics-based health management strategy for fuel cell hybrid electric vehicles, which can improve the durability of the fuel cell thanks to online health monitoring. Here, particle filtering method is adapted for online fuel cell prognostics and the uncertainty of the predicted results is calculated based on the distribution of particles. A health management strategy is developed based on prognostics and a decision-making process is designed by considering the prognostics uncertainty through a decision fusion method. The obtained results show that the developed strategy has effectively improved the durability of the on-board fuel cell by up to 95.4%. Moreover, a sensitivity analysis of the prognostics occurrence frequency and probability calculation has also been conducted in this paper.     

Towards health-aware energy management strategies in fuel cell hybrid electric vehicles: A review

An energy management strategy (EMS) is responsible for distributing the power between the electrochemical power sources of a fuel cell hybrid electric vehicle (FCHEV) with a view to minimizing the hydrogen consumption and maximizing the lifetime of the system. However, the energetic characteristics of the electrochemical devices (fuel cell, battery, and supercapacitor) are time-varying due to the influence of ageing, and different ambient and operating conditions. Any drift in the characteristics of the power sources can lead to the mismanagement of an EMS. According to the literature, ignorance of health adaptation can increase the hydrogen consumption from almost 6.5%–24% depending on the EMS. Therefore, it is necessary to develop a strategy which is aware of the actual state of the components while conducting the power split. Health monitoring techniques are potential candidates to deal with the uncertainties arising from the mentioned factors. In this respect, this paper first puts forward a concise review of the general modeling techniques which are essential for developing precise health monitoring techniques and in turn EMSs. Subsequently, the utilized methods for prognosis, diagnosis, and health state tracking of each of the mentioned power sources in a FCHEV are introduced. Then, a new taxonomy for the classification of the EMSs based on their health-awareness is proposed based on which three categories of prognostic-based, diagnostic-based, and systemic EMSs are formed. Each category is thoroughly explained, and a state-of-the-art review of these health-aware EMSs is presented. Finally, future perspectives of this new line of research and development are discussed before drawing a conclusion.     

A comprehensive review on choice of hybrid vehicles and power converters,control strategies for hybrid electric vehicles

A worldwide shift headed for a greener and low emissions will necessitate remarkable advancement in the way in which the energy is being produced and used. The factors such as climate changes induced by pollution, progressively more strict emissions norms for vehicles, depletion of petrol/diesel along with instability in their prices for transportation systems, play a vital role in the improvisation of technology involved in conventional vehicles. The hybrid electric vehicles (HEVs) are on the peak of the list of choices available for clean vehicle technologies. The various architectures of HEV, different methodologies of hybrid vehicle, are focused in this paper. The design criteria and optimization techniques with reference to the driving cycle is also elucidated. The various electric drives used for HEV are discussed in this paper. Also, the different electric propulsion systems are explained. To improve the fuel economy and emission of hybrid power system, control strategies are very significant. Researchers concentrate in optimizing the performance of HEV.     

Energy storage devices for future hybrid electric vehicles

Powertrain hybridization as well as electrical energy management are imposing new requirements on electrical storage systems in vehicles. This paper characterizes the associated vehicle attributes and, in particular, the various levels of hybrids. New requirements for the electrical storage system are derived, including: shallow-cycle life, high dynamic charge acceptance particularly for regenerative braking and robust service life in sustained partial-state-of-charge usage. Lead/acid, either with liquid or absorptive glass-fibre mat electrolyte, is expected to remain the predominant battery technology for 14 V systems, including micro-hybrids, and with a cost-effective battery monitoring system for demanding applications. Advanced AGM batteries may be considered for mild or even medium hybrids once they have proven robustness under real-world conditions, particularly with respect to cycle life at partial-states-of-charge and dynamic charge acceptance. For the foreseeable future, NiMH and Li-ion are the dominating current and potential battery technologies for higher-functionality HEVs. Li-ion, currently at development and demonstration stages, offers attractive opportunities for improvements in performance and cost. Supercapacitors may be considered for pulse power applications. Aside from cell technologies, attention to the issue of system integration of the battery into the powertrain and vehicle is growing. Opportunities and challenges for potential “battery pack” system suppliers are discussed.     

An improved energy management strategy for FC/UC hybrid electric vehicles propelled by motor-wheels

The hybridization of the fuel-cell electric-vehicle (FCEV) by a second energy source has the advantage of improving the system's dynamic response and efficiency. Indeed, an ultra-capacitor (UC) system used as an energy storage device fulfills the FC slowest dynamics during fast power transitions and recovers the braking energy. In FC/UC hybrid vehicles, the search for a suitable power management approach is one of the main objectives. In this paper, an improved control strategy managing the active power distribution between the two energy sources is proposed. The UC reference power is calculated through the DC link voltage regulation. For the FC power demand, an algorithm with five operating modes is developed. This algorithm, depending on the UC state of charge (SOC) and the vehicle speed level, minimizes the FC power demand transitions and therefore ameliorates its durability. The traction power is provided using two permanent magnetic synchronous motor-wheels to free more space in the vehicle. The models of the FC/UC vehicle system parts and the control strategy are developed using MATLAB software. Simulation results show the effectiveness of the proposed energy management strategy.     

Lifespan-consciousness and minimum-consumption coupled energy management strategy for fuel cell hybrid vehicles via deep reinforcement learning

Energy management strategy (EMS) based on optimized deep reinforcement learning plays a critical role in minimizing fuel consumption and prolonging the fuel cell stack lifespan for fuel cell hybrid vehicles. The deep Q-learning (DQL) and deep deterministic policy gradient (DDPG) algorithms with priority experience replay are proposed in this research. The factors of fuel economy and power fluctuation are incorporated into the multi-objective reward functions to decline the fuel consumption and extend the lifetime of fuel cell stack. In addition, the degradation rate is introduced to reflect the lifetime of fuel cell stack. Furthermore, compared to the referenced optimally energy management strategy (dynamic planning), the DQL-based and DDPG-based EMS with prioritized experience replay (DQL-PER, DDPG-PER) are evaluated in hydrogen consumption and cumulative degradation of fuel cell stack under four driving cycles, FTP75, US06-2, NEDC and LA92-2, respectively. The training results reveal that the DQL-PER-based EMS performances better under FTP75 and US06-2 driving cycles, whereas DDPG-PER-based EMS has better performance under NEDC driving cycle, which provide a potential for applying the proposed algorithm into multi-cycles.     

Comparative study of energy management systems for a hybrid fuel cell electric vehicle - A novel mutative fuzzy logic controller to prolong fuel cell lifetime

Hybrid fuel cell battery electric vehicles require complex energy management systems (EMS) in order to operate effectively. Poor EMS can result in a hybrid system that has low efficiency and a high rate of degradation of the fuel cell and battery pack. Many different types of EMS have been reported in the literature, such as equivalent consumption minimisation strategy and fuzzy logic controllers, which typically focus on a single objective optimisations, such as minimisation of H₂ usage. Different vehicle and system specifications make the comparison of EMSs difficult and can often lead to misleading claims about system performance. This paper aims to compare different EMSs, against a range of performance metrics such as charge sustaining ability and fuel cell degradation, using a common modelling framework developed in MATLAB/Simulink - the Electric Vehicle Simulation tool-Kit (EV-SimKit). A novel fuzzy logic controller is also presented which mutates the output membership function depending on fuel cell degradation to prolong fuel cell lifetime – the Mutative Fuzzy Logic Controller (MFLC). It was found that while certain EMSs may perform well at reducing H₂ consumption, this may have a significant impact on fuel cell degradation, dramatically reducing the fuel cell lifetime. How the behaviour of common EMS results in fuel cell degradation is also explored. Finally, by mutating the fuzzy logic membership functions, the MFLC was predicted to extend fuel cell lifetime by up to 32.8%.     

A hierarchical energy management strategy for fuel cell/battery/supercapacitor hybrid electric vehicles

In this paper, a hierarchical energy management strategy (EMS) based on low-pass filter and equivalent consumption minimization strategy (ECMS) is proposed in order to lift energy sources lifespan, power performance and fuel economy for hybrid electrical vehicles equipped with fuel cell, battery and supercapacitor. As for the considered powertrain configuration, fuel cell serves as main energy source, and battery and supercapacitor are regarded as energy support and storage system. Supercapacitor with high power density and dynamic response acts during great power fluctuations, which relives stress on fuel cell and battery. Meanwhile, battery is used to lift the economy of hydrogen fuel. In higher layer strategy of the proposed EMS, supercapacitor is employed to supply peak power and recycle braking energy by using the adaptive low-pass filter method. Meantime, an ECMS is designed to allocate power of fuel cell and battery such that fuel cell can work in a high efficient range to minimize hydrogen consumption in lower layer. The proposed EMS for hybrid electrical vehicles is modeled and verified by advisor-simulink and experiment bench. Simulation and experiment results are given to confirm effectiveness of the proposed EMS of this paper.     

A comparison of rule-based and model predictive controller-based power management strategies for fuel cell/battery hybrid vehicles considering degradation

Traditional power management systems for hybrid vehicles often focus on the optimization of one particular cost factor, such as fuel consumption, under specific driving scenarios. The cost factor is usually based on the beginning-of-life performance of system components. Typically, such strategies do not account for the degradation of the different components of the system over their lifetimes. This study incorporates the effect of fuel cell and battery degradation within their cost factors and investigates the impact of different power management strategies on fuel cell/battery loads and thus on the operating cost over the vehicle's lifetime. A simple rule-based power management system was compared with a model predictive controller (MPC) based system under a connected vehicle scenario (where the future vehicle speed is known a priori within a short time horizon). The combined cost factor consists of hydrogen consumption and the degradation of both the fuel cell stack and the battery. The results show that the rule-based power management system actually performs better and achieves lower lifetime cost compared to the MPC system even though the latter contains more information about the drive cycle. This result is explained by examining the changing dynamics of the three cost factors over the vehicle's lifetime. These findings reveal that a limited knowledge of traffic information might not be as useful for the power management of certain fuel cell/battery hybrid vehicles when degradation is taken into consideration, and a simple tuned rule-based controller is adequate to minimize the lifetime cost.     

Power management system for a fuel cell/battery hybrid vehicle incorporating fuel cell and battery degradation

Optimization of fuel cell/battery hybrid vehicle systems has primarily focused on reducing fuel consumption. However, it is also necessary to focus on fuel cell and battery durability as inadequate lifespan is still a major barrier to the commercialization of fuel cell vehicles. Here, we introduce a power management strategy which concurrently accounts for fuel consumption as well as fuel cell and battery degradation. Fuel cell degradation is quantified using a simplified electrochemical model which provides an analytical solution for the decay of the electrochemical surface area (ECSA) in the fuel cell by accounting for the performance loss due to transient power load, start/stop cycles, idling and high power load. The results show that the performance loss based on remaining ECSA matches well with test data in the literature. A validated empirical model is used to relate Lithium-ion battery capacity decay to C-rate. Simulations are then conducted using a typical bus drive cycle to optimize the fuel cell/battery hybrid system. We demonstrate that including these degradation models in the objective function can effectively extend the lifetime of the fuel cell at the expense of higher battery capacity decay resulting in a lower average running cost over the lifetime of the vehicle.     

An innovative optimal power allocation strategy for fuel cell, battery and supercapacitor hybrid electric vehicle

An optimal design of a three-component hybrid fuel cell electric vehicle comprised of fuel cells, battery, and supercapacitors is presented. First, the benefits of using this hybrid combination are analyzed, and then the article describes an active power-flow control strategy from each energy source based on optimal control theory to meet the demand of different vehicle loads while optimizing total energy cost, battery life and other possible objectives at the same time. A cost function that minimizes the square error between the desired variable settings and the current sensed values is developed. A gain sequence developed compels the choice of power drawn from all devices to follow an optimal path, which makes trade-offs among different targets and minimizes the total energy spent. A new method is introduced to make the global optimization into a real-time based control. A model is also presented to simulate the individual energy storage systems and compare this invention to existing control strategies, the simulation results show that the total energy spent is well saved over the long driving cycles, also the fuel cell and batteries are kept operating in a healthy way.     

Economic energy management strategy design and simulation for a dual-stack fuel cell electric vehicle

This paper presents the design and simulation validation of two energy management strategies for dual-stack fuel cell electric vehicles. With growing concerns about environmental issues and the fossil energy crisis, finding alternative methods for vehicle propulsion is necessary. Proton exchange membrane (PEM) fuel cell systems are now considered to be one of the most promising alternative energy sources. In this work, the challenge of further improving the fuel economy and extending the driving range of a fuel cell vehicle is addressed by a dual-stack fuel cell system with specific energy management strategies. An efficiency optimization strategy and an instantaneous optimization strategy are proposed. Simulation validation for each strategy is conducted based on a dual-stack fuel cell electric vehicle model which follows the new European driving cycle (NEDC). Simulation results show that a dual-stack fuel cell system with proposed energy management strategies can significantly improve the fuel economy of a fuel cell vehicle and thus lengthen the driving range while being able to keep the start-stop frequency of the fuel cell stack within a reasonable range.     

II. A combined model for determining capacity usage and battery size for hybrid and plug-in hybrid electric vehicles

We combine a detailed battery model with a simple vehicle model to examine the battery size and capacity usage of a Li_xC₆/Li_y+0.16Mn_1.84O₄ cell (with a normal and artificially flat equilibrium potential) and a Li_4+3xTi₅O₁₂/Li_yFePO₄ cell. The features of cell chemistry we are concerned with are the magnitude and shape of the cell equilibrium potential and internal resistance. Our key findings include that a battery for a hybrid electric vehicle application has a capacity usage from 15 to 25% (for a minimum separator area size), and as one moves from a HEV battery to a plug-in hybrid electric vehicle battery there is a change in the slope of the separator area vs. equivalent-electric range curve due to the shape of the pulse-power capability. We also find that defining the resistance using the HPPC protocol has limitations because in general the pulse resistance depends on the applied current and pulse duration. Our detailed, combined model also shows that the benefits of a flat-potential system may be limited because of the relative positions of a flat and sloped equilibrium potential, and the lack of a driving force for the relaxation of solid-phase concentration gradients throughout the electrode. That latter effect is shown to be more significant for electrodes with a non-uniform current distribution.     

I. A simplified model for determining capacity usage and battery size for hybrid and plug-in hybrid electric vehicles

We develop a simplified model to examine the effect of the shape and magnitude of the battery pulse-power capability on capacity usage and battery size. The simplified model expresses the capacity usage and a dimensionless battery area in terms of a dimensionless energy-to-power ratio and a parameter that characterizes the shape of the pulse-power capability. We also present dimensional results that show how the capacity usage depends on the equivalent-electric range and separator area, and how the battery area depends on the equivalent-electric range. Key results include the presence of a Langmuir-like relationship between the capacity usage and the dimensionless energy-to-power ratio, and a linear relationship between the dimensionless energy-to-power ratio and a dimensionless area, with a slope and offset that depend on the shape of the pulse-power capability. We also found that a flat pulse-power capability curve increases capacity usage and decreases battery size, and that two important parameters for battery design are (U − V_min)V_min/R, which reflects the maximum power capability, and Q〈V〉, which reflects the battery energy. The results and analysis contained herein are used to help interpret the results from a combined battery and vehicle model, presented in a companion paper.     

Near-optimal energy management for plug-in hybrid fuel cell and battery propulsion using deep reinforcement learning

Plug-in hybrid fuel cell and battery propulsion systems appear promising for decarbonising transportation applications such as road vehicles and coastal ships. However, it is challenging to develop optimal or near-optimal energy management for these systems without exact knowledge of future load profiles. Although efforts have been made to develop strategies in a stochastic environment with discrete state space using Q-learning and Double Q-learning, such tabular reinforcement learning agents’ effectiveness is limited due to the state space resolution. This article aims to develop an improved energy management system using deep reinforcement learning to achieve enhanced cost-saving by extending discrete state parameters to be continuous. The improved energy management system is based upon the Double Deep Q-Network. Real-world collected stochastic load profiles are applied to train the Double Deep Q-Network for a coastal ferry. The results suggest that the Double Deep Q-Network acquired energy management strategy has achieved a further 5.5% cost reduction with a 93.8% decrease in training time, compared to that produced by the Double Q-learning agent in discrete state space without function approximations. In addition, this article also proposes an adaptive deep reinforcement learning energy management scheme for practical hybrid-electric propulsion systems operating in changing environments.     

Lithium polymer batteries and proton exchange membrane fuel cells as energy sources in hydrogen electric vehicles

This paper deals with the application of lithium ion polymer batteries as electric energy storage systems for hydrogen fuel cell power trains. The experimental study was firstly effected in steady state conditions, to evidence the basic features of these systems in view of their application in the automotive field, in particular charge-discharge experiments were carried at different rates (varying the current between 8 and 100 A). A comparison with conventional lead acid batteries evidenced the superior features of lithium systems in terms of both higher discharge rate capability and minor resistance in charge mode. Dynamic experiments were carried out on the overall power train equipped with PEM fuel cell stack (2 kW) and lithium batteries (47.5 V, 40 Ah) on the European R47 driving cycle. The usage of lithium ion polymer batteries permitted to follow the high dynamic requirement of this cycle in hard hybrid configuration, with a hydrogen consumption reduction of about 6% with respect to the same power train equipped with lead acid batteries.     

Development of new energy management strategy for a household fuel cell/battery hybrid system

This work aims to construct an efficient and robust fuel cell/battery hybrid operating system for a household application. The ability to dispatch the power demands, sustain the state of charge (SOC) of battery, optimize the power consumption, and more importantly, ensure the durability as well as extend the lifetime of a fuel cell system is the basic requirements of the hybrid operating system. New power management strategy based on fuzzy logical combined state machine control is developed, and its effectiveness is compared with various strategies such as dynamic programming (DP), state machine control, and fuzzy logical control with simulation. Experimental results are also presented, except for DP because of difficulties in achieving real‐time implementation and much faster response to load variation. The given current from the energy management system (EMS) as a reference of the fuel cell output current is determined by filtering out various harmful signals. The new power management strategy is applied to a 1‐kW stationary fuel cell/battery hybrid system. Results show that the fuel cell hybrid system can run much smoothly with prolonged lifetime.