Search

Energy management strategies for hydrogen fuel cell hybrid electric vehicles (FCHEVs) are a key factor in achieving real-time vehicle energy optimization control, vehicle driving economy, and fuel cell durability. In this paper, for an FCHEV equipped with a fuel cell and supercapacitor, the quantitative information, logic rules, and operational constraints are transformed into linear integer inequalities according to its different operating modes, and the Hysdel language is used to establish its mixed logic dynamic model (MLD). Then, the energy management strategy based on model predictive control (MPC) is developed using the MLD model as the prediction model and the equivalent hydrogen consumption and the performance degradation of the fuel cell as the optimization performance indexes. Finally, under the World Light Vehicle Test Cycle, a joint simulation was carried out with Advisor and Simulink to verify the proposed strategy's superiority by comparing it with the power following control strategy (PFCS) and the compound fuzzy control strategy (CFCS). The results show that the strategy not only ensures real-time FCHEV energy control, but also reduces hydrogen consumption by 10.98% and 1.98% and the number of start/stop times of a fuel cell by six and four, compared to PFCS and CFCS, respectively, which improves the economy of the whole vehicle as well as the durability of the fuel cell. [ABSTRACT FROM AUTHOR]

Fuel cell hybrid electric trucks have become a cutting-edge field in understanding urban traffic emissions due to their enormous potential in low-carbon areas. In order to improve the economy of fuel cell hybrid electric trucks and reduce the decline of fuel cell lifespan, this paper proposes a multi-objective energy management strategy that optimizes weight coefficients. On the basis of establishing a fuel cell battery hybrid system model, three modes of uniform speed, acceleration, and deceleration were identified through clustering analysis of vehicle speed. Reinforcement learning algorithms were used to learn the corresponding weights for different modes, which reduced the decline in fuel cell life while improving the economic efficiency. The simulation results indicate that, under the conditions of no load, half load, and full load, the truck only sacrificed 0.9–5.6%, 1.7–2.6%, and 1.2–1.6% SOC, saving 5.7–6.45%, 5.9–6.67%, and 6.1–6.67% in lifespan loss, and reducing hydrogen consumption by 3.0–7.1%, 2.8–4.4%, and 1.0–3.0%, respectively. [ABSTRACT FROM AUTHOR]

To address the limitations of battery-powered unmanned surface vehicles (USVs) in terms of endurance mileage, this study introduces proton exchange membrane fuel cells (PEMFCs) into the power system of USVs. This paper focuses on the design and testing of a hybrid power system and its energy management strategy for a lightweight USV. The test results demonstrate that the hybrid power system effectively fulfills the power requirements of the USV across various operational conditions. Specifically, the amplitudes of bus voltage overshoot and undershoot remain below 0.31 V even during sudden changes in working conditions. The energy management strategy, in conjunction with an auxiliary battery, successfully limits the PEMFC power fluctuation to 200 W/s, thereby enhancing the lifespan of the PEMFC. Moreover, the study reveals that replacing Li-ion batteries with the PEMFC system as the primary power source can significantly enhance the USV's endurance mileage by 1.33–1.70 times carrying the same weight and 1.07–1.36 times carrying the same volume, respectively. And with increased hydrogen storage, the PEMFC system's energy density advantage over Li-ion batteries becomes more pronounced. These findings contribute to the exploration of PEMFCs as a promising solution for addressing the endurance limitations of battery-powered USVs, leading to their improved performance and extended operational range. • A whole vessel model including electrical, dynamic and control system is established. • A strategy based on bus voltage and PEMFC operating stability is proposed. • The energy management strategy has good adaptability to operating conditions. • Replacing Li-ion batteries with PEMFCs effectively increases the range of USVs. [ABSTRACT FROM AUTHOR]

Fuel-cell hybrid trucks (FCHTs), as primary force in fuel-cell vehicles, currently lack comprehensive development of rule-based energy management strategies (EMSs). The current optimization rule of the dynamic programming (DP) algorithm exhibits poor adaptability to changes in operating conditions and battery state of charge (SOC). Therefore, the work proposed real-time rule EMS of DP-optimized FCHTs. First, DP was taken offline to determine the optimal relationship between fuel cell power and demand power under driving conditions and SOCs. Secondly, real-time online recognition was achieved through driving pattern recognition (DPR) controller. A backpropagation neural network, optimized by the northern goshawk algorithm, was used for constructing DPR. Finally, the MATLAB/Simulink simulation showed that the proposed strategy exhibited superior DPR accuracy. Compared to rule-based strategies, significantly lower hydrogen consumption reduced vehicle-operating costs. • A DP-optimized real-time energy management strategy was designed. • The multivariate DP offline of the optimal rule control sequence library was constructed. • Driving conditions and the initial SOC were defined as multivariates. • A driving pattern recognizer was constructed using the northern goshawk optimization and back-propagation neural network. [ABSTRACT FROM AUTHOR]

To optimize the hydrogen consumption, lifespan of the fuel cell (FC), and durability of the lithium-ion battery in fuel cell electric vehicles (FCEVs), energy management strategies (EMSs) have been developed and implemented in the vehicle control units (VCUs) by engineers. Recently, with the rapid development of artificial intelligence, reinforcement learning (RL)-based EMS have shown great promise among various strategies. However, RL-based EMS tends to exhibit relatively poorer performance when faced with novel environments owing to the requirement for learning. This study proposes an enhanced EMS, Scalable Learning in Novel Environment (SLNE)-based EMS. This EMS performs well in unknown and dynamic environments by integrating a memory library (ML) composed of the Dirichlet process (DRP) clustering algorithm combined with the Chinese restaurant process (CRP) using the expectation-maximization (EM) algorithm for updates and the deep Q-network (DQN). Simulation and comparison are conducted under two novel driving cycles to evaluate the performance of the dynamic programming (DP)-based EMS, rule-based EMS, DQN-based EMS, and SLNE-based EMS. By comparing reward, power, and degradation, the results indicate that the proposed SLNE-based EMS demonstrates excellent convergence and adaptability when facing a novel and dynamic environment. Additionally, the proposed SLNE-based EMS achieves approximately 5% improvement in fuel economy, approximately 4.5% reduction in fuel cell degradation rate, and improved durability of the lithium-ion battery, compared with DQN-based EMS. [Display omitted] • The scalable learning in novel environment-based EMS is proposed for an FCEV. • The SLNE-based EMS performs well from the start when facing novel driving cycles. • The SLNE-based EMS demonstrates a higher reward ceiling and lower fluctuations. • Considering the fuel cell degradation, proposed EMS can better enhance the lifespan. • The fuel consumption of the SLNE-based EMS is 5% lower than that of the DQN-based EMS. [ABSTRACT FROM AUTHOR]

The hydrogen combustion engine (H 2 ICE) is known to be able to burn H 2 , producing no CO 2 emissions and extremely low engine-out NO x eo emissions. In this work, the potential to reduce the NO x eo emissions through the implementation of electric hybridization of an H 2 ICE-equipped passenger car (H 2 -HEV), combined with a dedicated energy management system (EMS) is discussed. Achieving a low H 2 consumption and low NO x eo emissions are conflicting objectives, the trade-off of which depends on the EMS and can be represented as a Pareto front. The dynamic programming algorithm is used to calculate the Pareto-optimal EMS calibrations for various driving missions. Through the utilization of a dedicated energy management calibration, H 2 -HEVs exhibit the potential to decrease the NO x eo emissions by more than 90%, while, decreasing the H 2 consumption by over 16%, compared to a comparable non-hybridized H 2 -vehicle. The present paper represents the initial potential analysis, suggesting that H 2 -HEVs are a viable option towards a CO 2 -free mobility with extremely low NO x eo emissions. • H 2 -HEVs with a dedicated energy management can achieve extremely low NO x eo • Mixed H 2 -HEVs have a superior H 2 -NO x eo trade-off than series and parallel H 2 -HEVs • Mixed H 2 -HEVs lower the NO x eo emissions by 90% and decrease the H 2 consumption by 16% • H 2 -HEV's optimal EMS calibrations for the entire H 2 - NO x eo Pareto front [ABSTRACT FROM AUTHOR]

The traditional rule-based energy management strategy for plug-in hybrid vehicles has issues, such as difficulty in online correction and limited online optimization capabilities. In addition, the global optimization energy management strategy cannot be applied online or in real-time. Considering the above difficulties, this study proposes a real-time optimization energy management strategy based on the Markov chain for driving condition prediction and online optimization with the minimum principle. To verify the proposed control strategy, the plug-in hybrid vehicle dynamics model, driving condition prediction model, and online optimization control model were first established. The initial value of the battery state of charge was set to 0.4 under the UDDS (Urban Dynamometer Driving Schedule) standard cycle. The simulation results showed that the comprehensive fuel consumption cost was 1.66 yuan, which was 8.28% better than the energy economy of the traditional rule-based energy management strategy. At the same time, a complete vehicle test was also conducted based on a sample vehicle test platform. The experimental results indicated that the energy management strategy proposed herein exhibits better fuel economy compared to that exhibited by the traditional rule-based energy management strategy. Simulations and experiments have verified the effectiveness of the proposed control strategy in this study. [ABSTRACT FROM AUTHOR]

For a fuel cell hybrid electric vehicle (FCHEV) powered by a fuel cell (FC), a battery (BAT) and an ultracapacitor (UC), an improved convex-optimization-based energy management strategy (EMS) is proposed in this article. To protect the fuel cell and the battery from peak power, an adaptive fuzzy filter is used to complete the frequency decoupling of the power demand. Subsequently, an adaptive equivalent consumption minimization strategy (A-ECMS) is introduced to improve fuel economy. To improve the optimality of the EMS obtained, an improved convex optimization method is utilized by introducing a slack variable and a barrier function. Finally, based on experimental data and an improved convex optimization algorithm, the optimal EMS is calculated and verified by a series of simulations under different driving cycles. Simulation results confirm that, compared with the traditional ECMS-based EMS, the proposed EMS can improve fuel economy and achieve lower power fluctuation and optimal FC efficiency for the FCHEV. [ABSTRACT FROM AUTHOR]

Reinforcement learning has shown success in solving complex control problems, yet safety remains paramount in engineering applications like energy management systems (EMS), particularly in hybrid electric vehicles (HEVs). An effective EMS is crucial for coordinating power flow while ensuring safety, such as maintaining the battery state of charge within safe limits, which presents a challenging task. Traditional reinforcement learning struggles with safety constraints, and the penalty method often leads to suboptimal performance. This study introduces Lagrangian-based parameterized soft actor–critic (PASACLag), a novel safe hybrid-action reinforcement learning algorithm for HEV energy management. PASACLag utilizes a unique composite action representation to handle continuous actions (e.g., engine torque) and discrete actions (e.g., gear shift and clutch engagement) concurrently. It integrates a Lagrangian method to separately address control objectives and constraints, simplifying the reward function and enhancing safety. We evaluate PASACLag's performance using the World Harmonized Vehicle Cycle (901 s), with a generalization analysis of four different cycles. The results indicate that PASACLag achieves a less than 10% increase in fuel consumption compared to dynamic programming. Moreover, PASACLag surpasses PASAC, an unsafe counterpart using penalty methods, in fuel economy and constraint satisfaction metrics during generalization. These findings highlight PASACLag's effectiveness in acquiring complex EMS for control within a hybrid action space while prioritizing safety. [ABSTRACT FROM AUTHOR]

In electric vehicles, the battery is a key component that calculates vehicle performance. Due to their greater efficiency and the lower cost of power, charging an electric vehicle is more affordable than purchasing gasoline or diesel for travel needs. To increase the battery's lifespan, the accuracy of the battery model for electric vehicles must be enhanced. To operate at their peak efficiency, batteries must be managed properly by a battery management system. This research illustrates the functioning of a rechargeable electric vehicle battery's charging system. There are several types of rechargeable batteries used, including lead acid, lithium‐ion, and nickel‐cadmium batteries. In recent trends, are used in the majority of cars use rechargeable lithium‐ion batteries. In general, accumulated heat, rapid utilization, and total energy throughput have an impact on the battery life of electric vehicles. In this study, 50 papers were analyzed about battery charging in an electric vehicle, which utilized different measures, as well as achievements attained by various methods. This survey reviewed the information from a different journal, along with their advantage, disadvantages, and challenges. The review lays the groundwork for future researchers to gain a deeper understanding of electric vehicles by offering a thorough interpretation of the methods currently in use. [ABSTRACT FROM AUTHOR]

In order to reduce the equivalent hydrogen consumption of the hybrid system and delay the aging of the fuel cell, an Energy management strategy (EMS) was proposed based on multi-objective optimization and road condition classification. Firstly, the electrical model of the fuel cell and lithium battery hybrid system power was constructed, and the equivalent hydrogen consumption model and fuel cell aging model were introduced. Then, a rule-based multi-mode EMS was designed; on this basis, in order to further reduce the equivalent hydrogen consumption of the system and prolong its service life, the multi-objective beluga whale optimization algorithm (MOBWO) was proposed to optimize the control parameters. Furthermore, in order to make the designed EMS suitable for different road conditions, a real-time classification method of driving road conditions based on long short-term memory (LSTM) network was proposed, aiming to switch the control parameters of EMS according to the classification results to achieve the optimal effect. Finally, the proposed algorithm was analyzed on the simulation platform. The results showed that the hydrogen consumption of the hybrid system with the proposed method was reduced by 2.3% and the aging degree of the fuel cell was reduced by 1.02% compared with the rule-based method, The proposed EMS could effectively reduce the equivalent hydrogen consumption of the hybrid system and delay the aging of the fuel cell. [ABSTRACT FROM AUTHOR]

The traditional rule-based energy management strategy for plug-in hybrid vehicles has issues, such as difficulty in online correction and limited online optimization capabilities. In addition, the global optimization energy management strategy cannot be applied online or in real-time. Considering the above difficulties, this study proposes a real-time optimization energy management strategy based on the Markov chain for driving condition prediction and online optimization with the minimum principle. To verify the proposed control strategy, the plug-in hybrid vehicle dynamics model, driving condition prediction model, and online optimization control model were first established. The initial value of the battery state of charge was set to 0.4 under the UDDS (Urban Dynamometer Driving Schedule) standard cycle. The simulation results showed that the comprehensive fuel consumption cost was 1.66 yuan, which was 8.28% better than the energy economy of the traditional rule-based energy management strategy. At the same time, a complete vehicle test was also conducted based on a sample vehicle test platform. The experimental results indicated that the energy management strategy proposed herein exhibits better fuel economy compared to that exhibited by the traditional rule-based energy management strategy. Simulations and experiments have verified the effectiveness of the proposed control strategy in this study. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The plug-in hybrid vehicles (PHEV) technology can effectively address the issues of poor dynamics and higher energy consumption commonly found in traditional mining dump trucks. Meanwhile, plug-in hybrid electric trucks can achieve excellent fuel economy through efficient energy management strategies (EMS). Therefore, a series hybrid system is constructed based on a 100-ton mining dump truck in this paper. And inspired by the dynamic programming (DP) algorithm, a predictive equivalent consumption minimization strategy (P-ECMS) based on the DP optimization result is proposed. Based on the optimal control manifold and the SOC reference trajectory obtained by the DP algorithm, the P-ECMS strategy performs real-time stage parameter optimization to obtain the optimal equivalent factor (EF). Finally, applying the equivalent consumption minimization strategy (ECMS) realizes real-time control. The simulation results show that the equivalent fuel consumption of the PECMS strategy under the experimentally collected mining cycle conditions is 150.8 L/100 km, which is 10.9% less than that of the common CDCS strategy (169.3 L/100 km), and achieves 99.47% of the fuel saving effect of the DP strategy (150 L/100 km). [ABSTRACT FROM AUTHOR]

This paper describes a decentralised smart grid system containing renewable energies, storage systems and distributed generation with human control and intervention. The importance of each element and the interaction between them leads to think about a decision-making strategy. In fact, the integration of a Photovoltaic Panel (PVP) is used due to its availability and its participation in the carbon emissions reduction. Also, a battery is required to fill a power gap or absorb extra generated energy. Moreover, an optimal sizing is needed to get an efficient system with minimum cost. Also, an energy management strategy (EMS) is essential to ensure the power resources scheduling in order to keep a continuous equilibrium supply-demand of electricity and avoid instabilities in the grid, with guaranteeing a minimum cost of electricity. In the first part, the proposed smart grid optimal sizing is determined under real weather data (solar radiation) of the city of Sousse, Tunisia, using the Hybrid Optimization of Multiple Energy Resources (HOMER) software technique. This approach is chosen thanks to its simplicity, effectiveness, and high precision compared to traditional techniques. In this paper, several configurations (Grid, (Grid-battery), (Grid-PVP), (Grid-PVP-battery)) are studied. The obtained results prove that the (Grid-PVP-battery) system configuration is the most efficient and economical solution. In the second part, a robust energy management strategy (EMS) is proposed for two smart grid configurations (grid-battery, grid-PVP-battery). This strategy is based on Fuzzy Logic Control (FLC) thanks to its non-linear modelling and its ability to make decisions relating to energy management. The primary goal of the suggested (EMS) is to ensure the energy resources scheduling in order to keep a continuous equilibrium among the production and consumption of electricity and avoid instabilities in the grid, with guaranteeing a minimum cost of electricity. As input data, (FLC) used time-varying price electricity (Price (t)) to solve an instant decision problem by choosing, at each instant, the optimal energy source (which provide electricity at the cheapest price possible). The obtained results, carrying out Matlab simulation, prove the efficacy of the proposed strategy, not only, in the energy resources scheduling to meet the load, but also, for the system cost reduction since the PVP has been used as much as possible since it is inexpensive relative to the costs of battery capacity and the grid. [ABSTRACT FROM AUTHOR]

To enhance the fuel economy of parallel hybrid commercial vehicles equipped with automatic transmissions and optimize the efficiency of the drive system, a new method for dividing driving mode boundaries and gear boundaries was proposed. A control strategy for mode switching and gear shifting was developed based on optimal efficiency and simulated under the driving conditions of Chinese heavy commercial vehicles. The results demonstrate that the proposed strategy maintains the balance of the battery state of charge, and achieves a 11.2% reduction in fuel consumption per 100 kilometers compared to the electric assist control strategy, which improves the fuel economy. [ABSTRACT FROM AUTHOR]

This paper proposes a novel energy management strategy satisfying real-time and highly efficient energy management strategies for fuel cell hybrid electric vehicles (FCHEVs). The strategy is based on model predictive control (MPC), which integrates long short-term memory (LSTM) and dynamic programming (DP). A high-precision powertrain model of the investigated FCHEV is established for subsequent simulations. After training under several typical working conditions, LSTM is designed to forecast future power demands of the entire vehicle. Using the prediction results, the DP algorithm calculates the control scheme based on model predictive control. Considering the economy and durability of power sources, the results of four different control strategies are compared: thermostat, power following, traditional DP, and MPC. The MPC proposed in this paper reduces the total usage cost per 100 km on the test set by 9%, 33.5%, and −4.6%. • The economy and durability of vehicular fuel cell system are both considered. • The LSTM neural network is imported into MPC theory for vehicular power prediction. • The key parameters of MPC and LSTM are determined by referring to the greedy algorithm. • The computational load in MPC optimisation is reduced by simplifying DP algorithm. • The real-time performance of the supposed EMS on-board is validated. [ABSTRACT FROM AUTHOR]

Continuous efforts to preserve the environment and to reduce gaseous emissions due to the massive growth of urban economic development and heightened concerns over crude oil depletion have accelerated researchers to find long‐term solutions, particularly in the transportation sector with the focus on powertrain electrification. This article delivers a comprehensive overview of electric vehicle architectures, energy storage systems, and motor traction power. Subsequently, it emphasizes different charge equalization methodologies of the energy storage system. This work's contribution can be identified in two points: first, providing an overview of different energy management methods to researchers and scholars. Second, to highlight the state‐of‐the‐art leanings in major components and to highlight promising approaches to hybrid electric vehicle future development. [ABSTRACT FROM AUTHOR]

Aiming to solve the problems of insufficient dynamic responses, the large loss of energy storage life of a single power cell, and the large fluctuation in DC (direct current) bus voltage in fuel cell vessels, this study takes a certain type of fuel cell ferry as the research object and proposes an improved equivalent minimum hydrogen consumption energy management strategy, based on fuzzy logic control. First, a hybrid power system including a fuel cell, a lithium–iron–phosphate battery, and a supercapacitor is proposed, with the simulation of the power system of the modified mother ship. Second, a power system simulation model and a double-closed-loop PI (proportion integration) control model are established in MATLAB/Simulink to design the equivalent hydrogen consumption model and fuzzy logic control strategy. The simulation results show that, under the premise of meeting the load requirements, the control strategy designed in this paper improves the Li-ion battery's power, the Li-ion battery's SOC (state of charge), the bus voltage stability, and the equivalent hydrogen consumption significantly, compared with those before optimization, which improves the stability and economy of the power system and has certain practical engineering value. [ABSTRACT FROM AUTHOR]

The increasing adoption of electric vehicles (EVs) presents a promising solution for achieving sustainable transportation and reducing carbon emissions. To keep pace with technological advancements in the vehicular industry, this paper proposes the development of a hybrid energy storage system (HESS) and an energy management strategy (EMS) for EVs, implemented using Proteus Spice Ver 8. The HESS consists of a proton exchange membrane fuel cell (PEMFC) as the primary source and a supercapacitor (SC) as the secondary source. The EMS, integrated into an electronic board based on the STM32, utilizes a low-pass filter algorithm to distribute energy between the sources. The accuracy of the proposed PEMFC and SC models is validated by comparing Proteus simulation results with experimental tests conducted on the Bahia didactic bench and Maxwell SC bench, respectively. To optimize energy efficiency, simulations of the HESS system involve adjusting the hybridization rate through changes in the cutoff frequency. The analysis compares the state-of-charge (SOC) of the SC and the voltage efficiency of the fuel cell (FC), across different frequencies to optimize overall system performance. The results highlight that the chosen strategy satisfies the energy demand while preserving the FC's dynamic performance and optimizing its utilization to the maximum. [ABSTRACT FROM AUTHOR]

Under net-zero objectives, the development of electric vehicle (EV) charging infrastructure on a densely populated island can be achieved by repurposing existing facilities, such as rooftops of wholesale stores and parking areas, into charging stations to accelerate transport electrification. For facility owners, this transformation could enable the showcasing of carbon reduction efforts through the self-use of renewable energy while simultaneously gaining charging revenue. In this paper, we propose a dynamic energy management system (EMS) for a solar-and-energy storage-integrated charging station, taking into consideration EV charging demand, solar power generation, status of energy storage system (ESS), contract capacity, and the electricity price of EV charging in real-time to optimize economic efficiency, based on a real-world situation in Taiwan. This study confirms the benefits of ESS in contracted capacity management, peak shaving, valley filling, and price arbitrage. The result shows that the incorporation of dynamic EMS with solar-and-energy storage-integrated charging stations effectively reduces electricity costs and the required electricity contract capacity. Moreover, it leads to an augmentation in the overall operational profitability of the charging station. This increase contains not only the revenue generated from electricity sales at the charging station but also the additional income from surplus solar energy sales. From a comprehensive cost–benefit perspective, introducing this solar-and-energy storage-integrated EMS can increase facility owners' net income by 1.25 times compared to merely installing charging infrastructure. [ABSTRACT FROM AUTHOR]

A charging station that integrates renewable energy sources is a promising solution to address the increasing demand for electric vehicle (EV) charging without expanding the distribution network. An efficient and flexible energy management strategy is essential for effectively integrating various energy sources and EVs. This research work aims to develop an Energy Management System (EMS) for an EV charging station (EVCS) that minimizes the operating cost of the EVCS operator while meeting the energy demands of connected EVs. The proposed approach employs a model-free method leveraging Deep Reinforcement Learning (DRL) to identify optimal schedules of connected EVs in real time. A Markov Decision Process (MDP) model is constructed from the perspective of the EVCS operator. The real-world scenarios are formulated by considering the stochastic nature of renewable energy and the commuting behavior of EVs. Various DRL algorithms for addressing MDPs are examined, and their performances are empirically compared. Notably, the Truncated Quantile Critics (TQC) algorithm emerges as the superior choice, yielding enhanced model performance. The simulation findings show that the proposed EMS can offer an enhanced control strategy, reducing the charging cost for EVCS operators compared to other benchmark methods.

Energy management strategies (EMSs) for hybrid vehicles have been extensively studied to achieve high system efficiency. EMSs usually focus on the torque split between the electric motor and the main power source. Other powertrain components, such as the gearbox or battery management system, are optimized individually. However, the cooperation between different powertrain components has been studied for specific hybrid architectures and demonstrated to be highly beneficial. A modular EMS that ensures the cooperation of multiple components with different characteristics, shared constraints and objectives, while taking advantage of predictive information will be highly beneficial. To address this research gap, a modular cooperative EMS is proposed using parametric controllers with parameter updates realized in the background using available predictive information. The strategy emphasizes modularity, feasibility, and systematically takes advantage of any available predictive information to improve the overall vehicle objectives, hence considering all the components playing a role in the EMS. The proposed cooperative strategy is first detailed for a generic EMS and then demonstrated for the control of the torque split and gear selection of a hybrid electric vehicle. A numerical study is presented to compare the proposed method with the optimal strategy derived from dynamic programming. The results are detailed for different available predictive information, both in terms of quantity and quality. The proposed method is revealed to be robust against incomplete predictive information and guarantees feasibility with low computational effort, making it real-time capable.

The automobile industry is regarded as one of the primary producers of greenhouse gas emissions. Hence, one major approach for promoting global sustainability is vehicle electrification. Energy source hybridization is imperative in vehicle electrification because no alternative clean energy source can match the performance of vehicles with internal combustion engines. For a compact energy source system with minimal source degradation and low operational costs, it is crucial to determine the optimal sizing of multiple sources in a hybrid electric vehicle (HEV). The objective of this article is to conduct a thorough assessment of the optimal energy source sizing methodology for HEV alongside an analysis of energy management systems. The importance of dynamic energy source characteristics in the optimal source design is explained and the dynamic modelling of these sources is investigated in detail. Moreover, this paper discusses the dynamic source degradation models used in the literature. This analysis on HEV component sizing provides a comprehensive picture of the current state-of-the-art and highlights several shortcomings, difficulties, and knowledge gaps. The findings indicate that the establishment of an energy management system and energy source sizing are interdependent activities that can prolong the usable life of the energy sources and reduce energy consumption. The aging, temperature, depth of discharge, and charging state are found to be essential characteristics of vehicle energy sources, yet these dynamic aspects have largely been neglected in previous papers. Additionally, if the source deterioration and associated factors are considered throughout the design phase, the HEV system can be built with long-life characteristics. The assessment conclusions highlight the significance of continued analysis to overcome obstacles and improve the hybrid automobile sector.

The rotary motion field of heavy equipment is a large energy-consuming field, characterized by frequent cyclical start-stop, significant load inertia, and braking energy is usually dissipated as thermal energy, for energy regeneration, no good solution has been found. This paper proposes a new energy-regenerative hybrid drive (ERHD) system and defines three operating modes. Taking the reversible rolling mill’s roll as load, and taking the energy consumption of electric motor (EM) and peak power as evaluation indexes, the influence law of key component parameters on the driving characteristics of the system is studied. Simulation models for the pure electric motor drive (PEMD) system and ERHD system were established by AMESim, along with a rule-based energy management strategy (EMS). The results show that the hydraulic pump/motor displacement has the greatest influence on braking time, peak power, and energy consumption. Under the optimal parameters, the proposed ERHD system can reduce the peak power of EM by 45.75% and energy consumption by 48.33% compared with the PEMD system. Starting and braking times were reduced by 44.54% and 1.21%, respectively. Based on the test results, the ERHD system reduces start-up time by 22.70% and peak power by 23.72%. The proposed system will significantly contribute to developing the rotary motion field of heavy equipment in terms of energy efficiency, low carbon and green.

This paper presented an optimal design of a grid-independent hybrid renewable energy system (HRES) that comprises Photovoltaic, Biomass, Hydrogen Fuel Cell, and battery storage. Renewable energy-based system have been endorsed for remote off-grid communities electrification. However, it is difficult to design an optimal hybrid energy system due to the stochastic resource nature, load variation, and high cost of renewable components. The sizing of components for the proposed HRES is determined through the application of an innovative metaheuristic optimization technique called salp swarm algorithm (SSA). Addressing the limitations of the salp swarm algorithm, which include low precision, optimization dimension and convergence rate, a modified version of the salp swarm algorithm (SSA), known as the Levy and sine cosine operator-based (LSC-SSA), was introduced. The proposed algorithm is compared with standard SSA and Genetic Algorithm (GA). The primary goal of the research is to reduce the annualized cost of the hybrid system, whilst taking into account the reliability constraint. The novelty of this research lies in its approach to enhance the performance of a HRES by optimizing its size and energy management strategy (EMS). It is achieved by employing a combined framework that integrate the proposed LSC-SSA into the supervisory EMS. The potential benefits of this approach include reducing the cost of energy and the annualized system cost. The comparative results validate that the LSC-SSA surpasses the standard SSA, and GA algorithms examined, by realizing significant cost reductions amounting to ${\$}$ 82,023, and ${\$}$ 202,127 respectively. Additionally, the outcome indicates that, the LSC-SSA offers the least cost of energy (COE) of ${\$}$ 0.927/kWh, in comparison with the COE values of ${\$}$ 0.931/kWh for SSA and ${\$}$ 0.949/kWh for GA, which are higher. Furthermore, the results indicate that the applied supervisory EMS has effectively assisted the establishing an eco-friendly and economical energy system.

In addressing challenges associated with the constrained enhancement of range performance in pure electric tractors, the difficulty in achieving genuinely eco-friendly agricultural machinery with hybrid powertrains, and the outdated approaches to energy optimization in hydrogen fuel cell tractors, a comprehensive methodology covering the entire spectrum of system design, optimization, and validation is presented. This method constructs an integrated electromechanical and hydraulic power bond graph model for an agricultural tractor, encompassing energy systems, drive systems, and lifting systems. It achieves rapid interaction between 20-sim software and Matlab/Simulink software through a script toolbox. In order to tackle the real-time applicability challenges of dynamic programming, a hierarchical dynamic programming is proposed. The dynamic programming strategy results serve as the upper-level output. At the lower layer, preprocessing of impact value variables is carried out to filter the input variables for the general regression neural network. This enables the real-time application of the dynamic programming algorithm and significantly reduces training time. Finally, validation is conducted through both model-in-the-loop and hardware-in-the-loop. The results demonstrate the correctness and superiority of the designed tractor simulation model and energy management strategy model compared to the power-following strategy. Specifically, in plowing conditions, the dynamic programming and hierarchical dynamic programming strategies exhibited reductions of 10.278% and 6.728%, respectively, in equivalent hydrogen consumption compared to power-following strategy. In transportation conditions, the reductions are 16.02% for dynamic programming strategy and 4.87% for hierarchical dynamic programming strategy, both relative to power-following strategy. This study lays the theoretical groundwork for modeling dynamic systems of tractors and optimizing energy management.

In campus facilities, classrooms and labs often use a large amount of energy due to their variable consumption pattern and lack of use management. Installing solar photovoltaic (PV) rooftop in the campus building through net-energy-metering (NEM) scheme has recently increased to reduce energy usage as well as generate income from the sales of excess solar energy to the grid. Meanwhile, the Malaysian government has introduced the Enhanced Time of Use (ETOU) tariff to encourage consumers to shift their electricity usage to reduce their bills through demand response. Despite offering different rates at various times of the day, the ETOU tariff may lead to an increase in electricity expenses if consumers do not effectively shift their consumption to lower rate hours and eventually using more during peak hours. Additionally, there has been lack of quantitative analysis conducted to determine how effective the compensation scheme provided by NEM. Therefore, considering a university building that holds a commercial electricity tariff, this study aims to develop an optimum energy management strategy integrating demand response and solar energy rooftop using improved Evolutionary- Particle Swarm Optimisation (EPSO). To determine the best load shifting strategy, the model was used to evaluate two Universiti Teknologi MARA (UiTM) campuses where NEM solar PV rooftop systems were installed. The analysis involved testing various weightage factors for controlling the loads, ranging from 5% to 20% under 2 different electricity tariffs offered in Malaysia. Results show the electricity cost under EPSO provides a significant cost reduction compared to PSO for both tariffs with a lesser computational time. Furthermore, EToU tariff with a weightage factor of 20% gives a higher energy and cost saving compared to fixed tariff. The findings from this research will assist the energy users in managing the load and generation from solar, whilst supporting the policymakers in designing effective compensation schemes.

The growing use of proton-exchange membrane fuel cells (PEMFCs) in hybrid propulsion systems is aimed at replacing traditional internal combustion engines and reducing greenhouse gas emissions. Effective power distribution between the fuel cell and the energy storage system (ESS) is crucial and has led to a growing emphasis on developing energy management systems (EMSs) to efficiently implement this integration. To address this goal, this study examines the performance of a fuzzy logic rule-based strategy for a hybrid fuel cell propulsion system in a small hydrogen-powered passenger vessel. The primary objective is to optimize fuel efficiency, with particular attention on reducing hydrogen consumption. The analysis is carried out under typical operating conditions encountered during a river trip. Comparisons between the proposed strategy with other approaches—control based, optimization based, and deterministic rule based—are conducted to verify the effectiveness of the proposed strategy. Simulation results indicated that the EMS based on fuzzy logic mechanisms was the most successful in reducing fuel consumption. The superior performance of this method stems from its ability to adaptively manage power distribution between the fuel cell and energy storage systems.

Energy management strategies typically employ reinforcement learning algorithms in a static state. However, during vehicle operation, the environment is dynamic and laden with uncertainties and unforeseen disruptions. This study proposes an adaptive learning strategy in dynamic environments that adapts actions to changing circumstances, drawing on past experience to enhance future real-world learning. We developed a memory library for dynamic environments, employed Dirichlet clustering for driving conditions, and incorporated the expectation maximization algorithm for timely model updating to fully absorb prior knowledge. The agent swiftly adapts to the dynamic environment and converges quickly, improving hybrid electric vehicle fuel economy by 5–10% while maintaining the final state of charge (SOC). Our algorithm’s engine operating point fluctuates less, and the working state is compact compared with Deep Q-Network (DQN) and Deterministic Policy Gradient (DDPG) algorithms. This study provides a solution for vehicle agents in dynamic environmental conditions, enabling them to logically evaluate past experiences and carry out situationally appropriate actions.

The energy management strategy plays an essential role in improving the fuel economy and extending the energy source lifetime for fuel cell hybrid electric vehicles (FCHEVs). However, the traditional energy management strategy ignores the lifetime of the energy sources for good fuel economy. In this work, an adaptive equivalent consumption minimization strategy considering performance degradation (DA-ECMS) is proposed by incorporating fuel cell and battery performance degradation models and establishing an optimal covariate predictor based on a long short-term memory (LSTM) neural network. The comparative simulations show that, compared with the adaptive equivalent consumption minimization strategy (A-ECMS), the DA-ECMS reduces the fuel cell stack voltage degradation by 17.1%, 23.2%, and 16.6% for the Worldwide Harmonized Light Vehicle Test Procedure (WLTP), the China Light-Duty Vehicle Test Cycle (CLTC), and the New European Driving Cycle (NEDC), respectively, and the corresponding battery capacity degradation is reduced by 5.1%, 11.1%, and 11.2%. The average relative error between the hardware-in-the-loop (HIL) test and simulation results of the DA-ECMS is 5%. In conclusion, the proposed DA-ECMS can effectively extend the lifetime of the fuel cell and battery compared to the A-ECMS.

This paper investigates microgrid systems characterized by the coexistence of discrete events and continuous events, a typical hybrid system. By selecting the charging and discharging processes of the energy storage unit as logical variables, a mixed logical dynamic (MLD) model for the microgrid in islanded mode is established. Based on this model, model predictive control (MPC) theory is employed to optimize the energy management strategy, aiming to stabilize the DC bus voltage of the photovoltaic (PV) unit and minimize the switching frequency of the energy storage unit’s charging and discharging processes during system operation.

To further improve the fuel economy of hybrid tractors, an energy management strategy based on model predictive control (MPC) solved by dynamic programming (DP) is proposed, taking into account the various typical operating conditions of tractors. A coupled dynamics model was constructed for a series diesel–electric hybrid tractor under three typical working conditions: plowing, rotary tillage, and transportation. Using DP to solve for the globally optimal SOC change trajectory under each operating condition of the tractor as the SOC constraint for MPC, we designed an energy management strategy based on DP-MPC. Finally, a hardware-in-the-loop (HIL) test platform was built using components such as Matlab/Simulink, NI-Veristand, PowerCal, HIL test cabinet, and vehicle controller. The designed energy management strategy was then tested using the HIL test platform. The test results show that, compared with the energy management strategy based on power following, the DP-MPC-based energy management strategy reduces fuel consumption by approximately 7.97%, 13.06%, and 11.03%, respectively, under the three operating conditions of plowing, rotary tillage, and transportation. This achieves fuel-saving performances of approximately 91.34%, 94.87%, and 96.69% compared to global dynamic programming. The test results verify the effectiveness of the proposed strategy. This research can provide an important reference for the design of energy management strategies for hybrid tractors.

Nowadays, due to climate change and disappearance of fossil fuels, hybrid electric UAVs using renewable energy sources are being developed. In addition, although research on UAVs with a large wingspan and high weight is common due to their long endurance, research on mini UAVs has remained limited. This study aims to increase the energy capacity of solar-powered mini UAVs and thus extend their endurance by developing a fixed-wing hybrid UAV that can fly with solar energy as much as possible, especially during the cruise phase. In this study, a solar-powered mini VTOL (vertical take-off and landing) UAV with a wingspan of 1.8 m and weight of 3.3 kg is developed and a model of the system consisting of solar cells, a battery, a super capacitor, and a DC/DC converter is created in MATLAB/Simulink software (R2023b). Additionally, state machine control (SMC), a rule-based (RB) energy management strategy (EMS), has been applied to this model. While the power obtained from the sun is divided among the other energy components, the durability of the UAV is increased, and the excess energy is stored as altitude energy to be used when necessary. As a result, in this study, an energy management algorithm including altitude energy has been successfully applied to a solar-powered UAV, achieving an 11.11% energy saving.

Multi-rotor drones, a kind of unmanned equipment which is widely used in the military, commercial consumption and other fields, have been developed very rapidly in recent years. However, their short flight time has hindered the expansion of their application range. This can be addressed by utilizing hydrogen fuel cells, which exhibit high energy density, strong adaptability to ambient temperature, and no pollution emissions, as the power source. Accordingly, the application of hydrogen fuel cells as the power source in multi-rotor drones is a promising technology that has attracted significant research attention. This paper summarizes the development process of hydrogen fuel cell multi-rotor drones and analyzes the key obstacles that need to be addressed for the further development of hydrogen fuel cell multi-rotor drones, including structural light weight, hydrogen storage methods, energy management strategies, thermal management, etc. Additionally, prospects for the future development of hydrogen fuel cell multi-rotor drones are presented.

The key to improving the fuel economy of plug-in hybrid electric vehicles (PHEVs) lies in the energy management strategy (EMS). Existing EMS often neglects engine operating conditions, leading to frequent start–stop events, which affect fuel economy and engine lifespan. This paper proposes an Integrated Engine Start–Stop Dynamic Programming (IESS-DP) energy management strategy, aiming to optimize energy consumption. An enhanced rule-based strategy is designed for the engine’s operating conditions, significantly reducing fuel consumption during idling through engine start–stop control. Furthermore, the IESS-DP energy management strategy is designed. This strategy comprehensively considers engine start–stop control states and introduces weighting coefficients to balance fuel consumption and engine start–stop costs. Precise control of energy flow is achieved through a global optimization framework to improve fuel economy. Simulation results show that under the World Light Vehicle Test Cycle (WLTC), the IESS-DP EMS achieves a fuel consumption of 3.36 L/100 km. This represents a reduction of 6.15% compared to the traditional DP strategy and 5.35% compared to the deep reinforcement learning-based EMS combined with engine start–stop (DDRL/SS) strategy. Additionally, the number of engine start–stop events is reduced by 43% compared to the DP strategy and 16% compared to the DDRL/SS strategy.

The energy management system of a fuel cell electric robot should be highly responsive to provide the required power for various tactical operations, navigation of different routes, and acceleration. This paper presents a new multi-level online energy management strategy for a fuel cell electric robot based on the proposed functions of equivalent hydrogen fuel value evaluation, classification of the battery state of charge via the squared combined efficiency function, identification of the robot maneuver condition based on the proposed operation state of robot function, improvement of the overall energy efficiency based on the proposed function of the battery overcharge control, and separation of the functional points of the fuel cell based on the operational mode control strategy. The simulation study of the proposed online multi-level energy management strategy was carried out with MATLAB R2018b software to verify its superiority by comparing with other strategies. The results indicate a reduction in hydrogen consumption, reduction in fuel cell power fluctuations, prevention of battery overcharging, and incrementation in the total energy efficiency of energy storage systems compared to other energy management strategies.

Energy management strategies (EMS) for the flexible traction power supply system (FTPSS) typically depend on the accurate predictive model or probabilistic estimation of traction load and renewable energy generation. However, it can be challenging due to the ultra-short-term dramatic fluctuation in traction load profile. To address the issue, a model-free EMS is proposed to achieve the power dispatch in real time based on the current state. Firstly, a sequential stochastic optimization model is built to optimize the long-term operating cost and load fluctuation. Through the relaxation of time-coupling constraints and incorporation of the Lyapunov optimization technique, the problem is decomposed into individual optimization problems at each time slot. Considering the complementary characteristic of hybrid energy storage system, a bi-level optimization framework is constructed to separately control powers of the supercapacitor and battery with the hierarchical sequence method. More importantly, a fully informative control strategy with the known future load profile and renewable energy generation is adopted as the evaluation benchmark. The gap between the proposed method and the benchmark can be demonstrated to fall within a certain range of below 10% by mathematical derivation and extensive cases.

Environmental working conditions have a great impact on the power demand and fuel consumption of vehicles, and the rational use of road terrain information plays an important role in the improvement of vehicle economy and energy sources durability. In this paper, a fuel cell hybrid electric bus (FCHEB) energy management strategy (EMS) based on deep deterministic policy gradient (DDPG) algorithm taking into account future terrain information is proposed based on cyber-physical system (CPS) to reduce the economic cost of FCHEB. First, this paper implements the information exchange between the vehicle system and the network layer through CPS to obtain the environmental working conditions of the vehicle operation. Second, future terrain information is introduced into the framework for the first time with hydrogen consumption, battery degradation and fuel cell durability constraints to rationally allocate the power of the FCHEB. The results show that the proposed strategy improves the power battery durability by 7.39% and reduces the total operating cost by 5.76% compared to the EMS that ignores the future terrain information. • An energy management strategy that considers future terrain information is proposed. • The proposed strategy achieves an effective combination with cyber physical system. • A trade-off between hydrogen consumption and energy sources durability is achieved. • The proposed strategy reduces the total cost by 7.81% compared to NTI EMS. [ABSTRACT FROM AUTHOR]

This paper provides a cost-effective energy management method for the microgrid's standalone and on-grid operational modes. The considered microgrid based on Green-to-Green systems such as a photovoltaic array (PV), wind turbine (WT) as renewable generators, hydrogen fuel cell (FC) system, microturbine (MT), and battery storage system. The suggested technique is based on the marine predator algorithm (MPA) that and created for a scheduling horizon of one day. The main objective of this paper is to reduce operating costs while satisfying the demand power. To approve the performance of the suggested management strategy, the simulation results are compared with other recent optimization algorithms. These algorithms include particle swarm optimization (PSO), salp swarm algorithm (SSA), and coot optimization algorithm (COOT). To approve the performance of the proposed EMS, the system will be evaluated for three cases: free renewable generation, restricted generation mode, and unlimited main grid power mode. For the first case, the proposed EMS reduces the operating costs by 0.8732%. For case 2, the economic benefits have been raised by 1.0815% and by 0% for the last case because of the reduced problem complexity. • A cost-effective energy management strategy for the microgrid based PEM fuel cells is proposed. • Implementation of marine predator algorithm to minimize the operating costs. • The performance has been investigated under various operating conditions. [ABSTRACT FROM AUTHOR]

With the prosperity of artificial intelligence in recent years, energy management strategies (EMSs) based on deep reinforcement learning (DRL) have become the mainstream approach to ensure efficient energy distribution of hybrid electric vehicles (HEVs). Moreover, in terms of developing sustainable urban public transportation systems, zero-emission fuel cell hybrid electric buses (FCHEBs) are more promising than hybrid electric buses (HEBs). Given that, this article proposes a novel data-driven EMS based on DRL to enhance the training efficiency of the proposed EMS while improving the fuel economy of an FCHEB. In this article, to optimize the power allocation of the FCHEB, an improved twin delayed deep deterministic policy gradient (TD3) algorithm combined with prioritized experience replay is innovatively formulated, and then a promising EMS based on it is proposed. Furthermore, to enhance the adaptability and improve the training efficiency of the proposed EMS, a stochastic training environment is established with massive real-world velocity data, and a pre-training method using the global optimal experience is designed. Simulation results show that the proposed EMS improves fuel economy by 5.87% compared with the EMS based on original TD3, reaching 97.15% of the global optimal dynamic programming method. • TD3 algorithm combined with prioritized experience replay is innovatively designed. • A stochastic training environment is designed based on massive real driving data. • A pre-training method is proposed to provide a heuristic effect for the TD3 agent. • The proposed strategy improves fuel economy by 8.03% than the DDPG-based strategy. • The robustness and computational efficiency of the proposed strategy are verified. [ABSTRACT FROM AUTHOR]

Fuel cell hybrid electric vehicles (FCHEV) are one of the most promising new energy vehicles. The cost and lifetime of its powertrain have limited its commercial development. This paper proposed an energy management strategy based on nonlinear model predictive control (NMPC) technology to solve the economy and durability problem of FCHEVs. Based on Markov Monte Carlo(MCMC) method, a prediction model of multi-scale operating conditions is established, and dynamic programming(DP) is used to realize the optimal control in the predicted time domain. The "constant speed prediction" is innovatively adopted in the transition stage to improve the prediction accuracy and enable the model to be realized online. The ways to reduce calculating amount of NMPC are also discussed in this paper. This simplification leads to suboptimal fuel economy and durability of control system but can have obvious reduction in calculating time. The simulation results show that, compared with the thermostat strategy and the power following strategy, the degradation cost decrease of 11.1% and 23.9% and the total operation cost of NMPC decrease of 11.0% and 23.5% respectively. The NMPC strategy has better economy and durability than the rule-based energy management strategy, is close to the global optimal result obtained by dynamic programming and can meet the requirements of real-time control. • The economy and durability of vehicular fuel cell system are both considered. • Markov Chain Monte Carlo is imported into MPC theory for vehicular power prediction. • Adaptability to changing conditions is strengthened via "constant speed prediction". • The computational load in MPC optimization is reduced by simplifying DP algorithm. [ABSTRACT FROM AUTHOR]

Adding battery locomotives to traditional diesel locomotives to form a hybrid consist has the potential to reduce fuel consumption and emissions in freight rail operations. This paper provides route-based estimates of diesel (hpd/ton) and battery (hpb/ton) power requirements and diesel (gal/ton) and battery (hpbhr/ton) energy requirements for hybrid consists. Given a route-specific power profile, the power split between the battery pack and the diesel engine is optimized to minimize fuel consumption by running the diesel engine at maximum efficiency during the entire route. Simulations for 200-mile round trips between Chicago and Harrisburg show that the diesel power is maximum in low-gradient regions at 1.05 (hpd/ton) and battery power is maximum in hilly regions at 2 (hpb/ton) for discharge and 6.5 (hpb/ton) for charge. Maximum fuel efficiency gains of approximately 60% are seen in the mountains, where 2.09 (hpbhr/ton) of battery energy is needed. Minimum fuel economy gains are observed in flat regions, with 20% fuel consumption reduction. With battery current and voltage limits, the battery pack size increases, and fuel savings decrease. [ABSTRACT FROM AUTHOR]

An energy management strategy (EMS) is important in marine hybrid propulsion systems while the global optimal solutions are more significant for the EMS to improve the fuel economy of system. Aiming at finding the more accurate global optimal solutions for EMS, an improved dynamic programing (DP) algorithm was proposed to overcome the basic DP algorithms' weaknesses and improve the fuel economy. Then the model of gas-electric hybrid propulsion system was also established to verify the strategies. What's more, the improved DP algorithm was applied to the minimum natural gas consumption and charge-sustaining strategy. And a bi-level optimization scheme that decoupled the interaction between the EMS and components matching was also studied. The results showed that the improved DP algorithm not only avoided the shortcomings in the basic DP algorithm such as the weak effect of penalty functions and curse of dimensionality but also gave more accurate solutions. Compared to the basic DP, the improved DP algorithm can reduce the gas fuel consumption by 3.67% and the computational complexity decreases 100 times. [ABSTRACT FROM AUTHOR]

To balance the hydrogen consumption of fuel cell vehicle (FCV), the durability of the fuel cell (FC), and the life of the power battery (PB) to further reduce the whole lifecycle costs of FCV. A multi-objective reinforcement learning-based (MORL-based) energy management strategy (EMS) is proposed in this research. First, the composition mechanism of the FCV lifecycle costs is analyzed, and the equivalent hydrogen consumption model, FC durability degradation model, and PB life decay model are established; Then, a three-dimensional reward function is constructed by integrating the objectives of equivalent hydrogen consumption, FC durability degradation, and PB life decay. And the penalty terms coupled with the decay factors are introduced into the reward function to satisfy the mutual constraint characteristics between the PB and the FC system to ensure the stability of the MORL-based EMS; In addition, the prioritized experience replay technology is introduced into the MORL-based EMS to improve the learning efficiency and convergence of traditional deep Q network (DQN) algorithm; After that, the evaluation and target network of the embedded dueling network are introduced to solve the multi-objective overestimation problem encountered in the training process by generalizing the behavior learning in the presence of similar value behaviors; Finally, the performance of MORL-based EMS and DQN-based EMS is compared by numerical simulation under various driving cycles. The results show that the MORL-based EMS proposed in this paper has better convergence ability, adaptability, and lower lifecycle costs than the DQN-based EMS. In addition, the lifecycle costs of the MORL-based EMS can achieve a 99.2% control effect of the dynamic programming-based EMS. • The prioritized dueling double deep Q network-based EMS is proposed for an FCV. • Three objectives are considered in the PD3QN-based EMS. • Considering the battery life decay, EMS can better reduce the life cycle costs. • The PD3QN-based EMS can achieve a 99.2% control effect of DP-based EMS. • The PD3QN-based EMS can achieve good convergence ability and adaptability. [ABSTRACT FROM AUTHOR]

To improve the fuel economy of ships with multi-energy hybrid power systems, we propose an energy management strategy for hybrid power ships based on condition identification and prediction. By constructing a condition identification model based on a support vector machine (SVM), the characteristic parameters of current operation conditions of the ships were analyzed and assessed to determine operation condition types of the ships in real-time. The model predictive control (MPC) method is used to distribute the output power of the main engine, storage battery, and supercapacitor. Using multiple sets of multi-step Markov models with different types of operating conditions as the power prediction model, the optimal prediction time domain length and initial SOC are selected through simulation. Finally, based on the operating condition identification results, the operating condition prediction model for the corresponding type of operating condition is automatically selected to improve the strategy performance.The results show that the proposed strategy can save 4.55% of fuel consumption compared with the strategy using only model predictive control.Using this strategy can effectively improve the fuel economy and energy efficiency, and promote the development of green ships. [ABSTRACT FROM AUTHOR]

A parallel hybrid vehicle was studied to establish the demand power and power system model of the whole vehicle and proposed an energy management strategy based on improved deep reinforcement learning (DRL). The DRB-TD3 algorithm was proposed to improve the sampling efficiency of the original algorithm by improving the twin delayed deep deterministic policy gradient (TD3) algorithm in DRL and introduced dual replay buffers. A rule-based constraint controller was designed and embedded into the algorithm structure to eliminate unreasonable torque allocation. The performance of the dynamic planning (DP)-based energy management strategy was used as a benchmark for simulation experiment under UDDS driving conditions. The experimental results show that the DRB-TD3 algorithm has the best convergence performance compared with the deep deterministic policy gradient (DDPG) algorithm and the conventional TD3 algorithm, with 61.2$ \% $ and 31.6$ \% $ improvement in convergence efficiency, respectively, the proposed energy management strategy reduces the average fuel consumption by 3.3$ \% $ and 2.3$ \% $ compared with the DDPG- and TD3-based energy management strategies, respectively, the fuel performance reaches 95.2$ \% $ of DP-based, which with the best fuel economy, and the battery SOC can be maintained at a better level, which helps to extend the battery life. [ABSTRACT FROM AUTHOR]

Copyright of Nonferrous Metals (Mining Section) is the property of Beijing Research Institute of Mining & Metallurgy Technology Group and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)