Green Energy and Intelligent Transportation最新文献

The water content of proton exchange membrane fuel cells (PEMFCs) affects the transport of reactants and the conductivity of the membrane. Effective water management measures can improve the performance and extend the lifespan of the fuel cell. The water management state of the stack is influenced by various external operating conditions, and optimizing the combination of these conditions can improve the water management state within the stack. Considering that the stack's internal resistance can reflect its water management state, this study first establishes an internal resistance-operating condition model that considers the coupling effect of temperature and humidity to determine the variation trend of total resistance and stack humidity with single-factor operating conditions. Subsequently, the water management state optimization method based on the ANN-HGPSO algorithm is proposed, which not only quantitatively evaluates the influence weights of different operating conditions on the stack's internal resistance but also efficiently and accurately obtains the optimal combination of five operating conditions: working temperature, anode gas pressure, cathode gas pressure, anode gas humidity, and cathode gas humidity to achieve the optimal water management state in the stack, within the entire range of current densities. Finally, the response surface experimental results of the stack also validate the effectiveness and accuracy of the ANN-HGPSO algorithm. The method mentioned in this article can provide effective strategies for efficient water management and output performance optimization control of PEMFC stacks.

This paper aims to answer how to use traffic information to design energy management strategies for fuel cell buses in a networked environment. For the buses entering the bus stops scenario, this paper proposes a hierarchical energy management strategy for fuel cell buses, which considers the traffic information near the bus stops. In the upper-level trajectory planning stage, the optimal SOC trajectory under various historical traffic conditions is solved through dynamic planning. The traffic information and the best SOC trajectory are mapped through BiLSTM, which can achieve fast, real-time long-term SOC reference. In the lower-level real-time predictive energy management strategy, the optimal SOC is used as the state reference to guide the predictive energy management of fuel cell buses when entering the bus stops. Simulation results show that compared with the strategy without SOC trajectory reference, the life cost of the proposed strategy is reduced by 13.8%, and the total cost is reduced by 3.61%. The SOC of the proposed strategy is closer to the DP optimal solution.

The brake-by-wire (BBW) system is an essential part of the intelligent electric vehicle, which is determination of the braking safety and recovery efficiency. To design a safe and efficient booster motor, the design of booster motor for BBW system is discussed in this paper. Through comparative analysis, experimental simulation and assessment argument, the scheme of designing a booster motor for brake-by-wire system is completely described. First, the mainstream structure of the BBW system and the main challenges it faces in the assisted motor are discussed. Second, comparing the motors of different types and structures, the motor body and control system scheme suitable for the characteristics of the booster motor system are determined. Then, through the simulation analysis of the ansoft and matlab, the optimization scheme of the motor and performance improvement are proposed. Further, through the actual design of a set of the booster motor system, the safe and efficient motor designing are verified, and the problems involving functional safety are discussed. Finally, focus on the problem while simulation and experiment, some important countermeasures to improve current technology and prospect of in-depth study are pointed out.

Due to the less stringent emission technology requirement, motorized two and three-wheelers (2&3W) generate more pollutants than cars. About 20% of the world's registered motorcycles are known to be in Africa. Vehicle pollution is one of the major causes of death and health problems in Africa. The electrification of transportation provides an opportunity for E2&3W in Africa. To assess this transition, this study quantifies the number of E2&3W present in some African countries. Surveys of electric vehicle start-ups, drivers, and owner experiences are used to determine the E2&3W's technical feasibility and ability to compete with petrol scooters (p-scooters). SimaPro 9.4 software together with Ecoinvent 3.8 database was used to conduct a cradle-to-the-grave analysis of the environmental impact of using electric scooters (e-scooters). The research found that Africa's E2&3W's have a 0.2% market share compared to gasoline versions. The main disadvantage of e-scooters is their limited range and battery life. The average range and speed are 50 ​km and 50 ​km/h, respectively. Overloading of E2&3W caused damage to traction motors and was of major concern to distributors. The main advantages of E2&3W are their low operating costs and low environmental impact. In South Africa, the total environmental impact of e-scooters outweighed that of p-scooters. Emissions that have a direct impact on human health, were significantly lower for e-scooters than for p-scooters. The lack of battery performance standards, battery swapping station standards, and charging station standards negatively affects the quality of imported e-scooters. African countries need to implement electric vehicle standards, and battery recycling policies, and establish electric vehicle training and research centers.

Unmanned aerial vehicles (UAVs) have gained much attention from academic and industrial areas due to the significant number of potential applications in urban airspace. A traffic management system for these UAVs is needed to manage this future traffic. Tactical conflict resolution for unmanned aerial systems (UASs) is an essential piece of the puzzle for the future UAS Traffic Management (UTM), especially in very low-level (VLL) urban airspace. Unlike conflict resolution in higher altitude airspace, the dense high-rise buildings are an essential source of potential conflict to be considered in VLL urban airspace. In this paper, we propose an attention-based deep reinforcement learning approach to solve the tactical conflict resolution problem. Specifically, we formulate this task as a sequential decision-making problem using Markov Decision Process (MDP). The double deep Q network (DDQN) framework is used as a learning framework for the host drone to learn to output conflict-free maneuvers at each time step. We use the attention mechanism to model the individual neighbor's effect on the host drone, endowing the learned conflict resolution policy to be adapted to an arbitrary number of neighboring drones. Lastly, we build a simulation environment with various scenarios covering different types of encounters to evaluate the proposed approach. The simulation results demonstrate that our proposed algorithm provides a reliable solution to minimize secondary conflict counts compared to learning and non-learning-based approaches under different traffic density scenarios.

The transportation sector is characterized by high emissions of greenhouse gases (GHG) into the atmosphere. Consequently, electric vehicles (EVs) have been proposed as a revolutionary solution to mitigate GHG emissions and the dependence on petroleum products, which are fast depleting. EVs are proliferating in many countries worldwide and the fast adoption of this technology is significantly dependent on the expansion of charging stations. This study proposes the use of the hybrid genetic algorithm and particle swarm optimization (GA-PSO) for the optimal allocation of plug-in EV charging stations (PEVCS) into the distribution network with distributed generation (DG) in high volumes and at selected buses. Photovoltaic (PV) systems with a power factor of 0.95 are used as DGs. The PVs are penetrated into the distribution network at 60% and six penetration cases are considered for the optimal placement of the PEVCSs. The optimization problem is formulated as a multi-objective problem minimizing the active and reactive power losses as well as the voltage deviation index. The IEEE 33 and 69 bus distribution networks are used as test networks. The simulation was performed using MATLAB and the results obtained validate the effectiveness of the hybrid GA-PSO. For example, the integration of PEVCSs results in the minimum bus voltage still within accepted margins. For the IEEE 69 bus network, the resulting minimum voltage is 0.973 p.u in case 1, 0.982 p.u in case 2, 0.96 p.u in case 3, 0.961 p.u in case 4, 0.954 p.u in case 5, and 0.965 p.u in case 6. EVs are a sustainable means of significantly mitigating emissions from the transportation sector and their utilization is essential as the worldwide concern of climate change and a carbon-free society intensifies.

Amidst the rapid urbanization in the country, the importance of urban public transport has been realized by the governments. Public transport is vital to the city's economy and ensures social equity. Bus Rapid Transit System (BRTS) has emerged as an exciting way to decongest the cities, enhancing and increasing mobility and accessibility and promoting transit-oriented development. India's longest BRTS, Janmarg, was created with similar objectives. However, the system faces reduced ridership and inhibited growth because of its hidden inefficiencies. This research aims to identify all the factors affecting ridership, accessibility, and inhibiting the system's growth even after having sufficient infrastructure. It also aims to quantitatively determine whether Janmarg could achieve its establishment's objectives on the city transportation system after thirteen years of the successful implementation of the project. The research methodology used in this work combines primary and secondary research. The factors are responsible for preventing Janmarg from achieving its objectives and utilizing its full potential are determined and recommended ways to utilize adversities effectively. Results show that this study endorses reducing ambiguities and a way forward for making a sustainable transportation system.

This work aims to investigate the factors accelerating electric vehicle (EV) acceptance at the consumer end in Pakistan and analyzes the implications for policymakers for a fast-track EV transition. The study further investigates the high EV penetration scenario resulting from the technology acceptance model (TAM's 80% EV) and its impact on energy demand and CO₂ emissions. The study design used a quantitative analysis method with the survey as an instrument for data collection regarding EV acceptance. The model under investigation was adapted from the famous Technology-Acceptance Models (TAMs) and modified with other significant predictors evidenced in the literature. Correlation and stepwise regression were performed with a multicollinearity check for model hypothesis testing. Out of six predictors, only four factors were significant in accelerating the EV transition. Financial policies were found to be highly significant, followed by environmental concern, facilitating conditions and perceived ease of use. The research then used exponential smoothing forecasts for transport demand and developed an EV penetration scenario based on modified TAM results. The results highlight the significant increase in transport demand and the opportunity for Pakistan to limit passenger transport emissions to 36.6 ​MT instead of 61.6 ​MT by 2040.

Autonomous driving is a promising way to future safe, efficient, and low-carbon transportation. Real-time accurate target detection is an essential precondition for the generation of proper following decision and control signals. However, considering the complex practical scenarios, accurate recognition of occluded targets is a major challenge of target detection for autonomous driving with limited computational capability. To reveal the overlap and difference between various occluded object detection by sharing the same available sensors, this paper presents a review of detection methods for occluded objects in complex real-driving scenarios. Considering the rapid development of autonomous driving technologies, the research analyzed in this study is limited to the recent five years. The study of occluded object detection is divided into three parts, namely occluded vehicles, pedestrians and traffic signs. This paper provided a detailed summary of the target detection methods used in these three parts according to the differences in detection methods and ideas, which is followed by the comparison of advantages and disadvantages of different detection methods for the same object. Finally, the shortcomings and limitations of the existing detection methods are summarized, and the challenges and future development prospects in this field are discussed.