Green Energy and Intelligent Transportation最新文献

Electric vehicles (EVs) have gained prominence in the present energy transition scenario. Widespread adoption of EVs necessitates an accurate State of Charge estimation (SoC) algorithm. Integrating predictive SoC estimations with smart charging strategies not only optimizes charging efficiency and grid reliability but also extends battery lifespan while continuously enhancing the accuracy of SoC predictions, marking a crucial milestone in sustainable electric vehicle technology. In this research study, machine learning methods, particularly Artificial Neural Networks (ANN), are employed for SoC estimation of LiFePO₄ batteries, resulting in efficient and accurate estimation algorithms. The investigation first focuses on developing a custom-designed battery pack with 12 ​V, 4 Ah capacity with a facility for real-time data collection through a dedicated hardware setup. The voltage, current and open-circuit voltage of the battery are monitored with computerized battery analyzer. The battery temperature is sensed with a DHT22 temperature sensor interfaced with Raspberry Pi. Principal components are derived for the collected battery data set and analyzed for feature engineering. Three principal components were generated as input parameters for the developed ANN. Early Stopping for the ANN was also implemented to achieve faster convergence of the ANN. While considering eleven combinations for ten different optimizers loss function is minimized. Comparative analysis of hyperparameter tuning and optimizer selection revealed that the Adafactor optimizer with specific settings produced the best results with an RMSE value of 0.4083 and an R2 Score of 0.9998. The proposed algorithm was also implemented for two different types of datasets, a UDDS drive cycle and a standard cell-level dataset. The results obtained were in line with the results obtained with the ANN model developed based on the data collected from the developed experimental setup.

Autonomous driving is an active area of research in artificial intelligence and robotics. Recent advances in deep reinforcement learning (DRL) show promise for training autonomous vehicles to handle complex real-world driving tasks. This paper reviews recent advancement on the application of DRL to highway lane change, ramp merge, and platoon coordination. In particular, similarities, differences, limitations, and best practices regarding the DRL formulations, DRL training algorithms, simulations, and metrics are reviewed and discussed. The paper starts by reviewing different traffic scenarios that are discussed by the literature, followed by a thorough review on the DRL technology such as the state representation methods that capture interactive dynamics critical for safe and efficient merging and the reward formulations that manage key metrics like safety, efficiency, comfort, and adaptability. Insights from this review can guide future research toward realizing the potential of DRL for automated driving in complex traffic under uncertainty.

Many countries are relying on electric vehicles to achieve their future greenhouse gas reduction targets; thus, they are setting regulations to force car manufacturers to a complete shift into producing fully electric vehicles, which will significantly influence the adoption rates of electric vehicles. This research investigates the temporal evolution of battery electric vehicle (BEV) ownership growth in Turkey, drawing insights from both historical and current trends. By employing and optimizing the Gompertz model, we provide a year-by-year projection of BEV ownership rates, aiding in exploring the anticipated timeline for BEV market saturation. Our findings indicate that the introduction of BEVs into the Turkish motorization market is poised to push further market saturation by approximately 15 years, to occur in around 2095 as opposed to 2080s. Furthermore, our analysis underscores the rapid growth pace in BEV ownership compared to the ownership of internal combustion engine vehicles (ICEVs). The main aim of this research is to provide Turkish policymakers and transport planners with solid insights into how the vehicle market will perform in the short and long run, allowing them to prepare a smooth transition from traditional vehicles to BEVs.

It is well acknowledged to all that an active equalization strategy can overcome the inconsistency of lithium-ion cell's voltage and state of charge (SOC) in series-connected lithium-ion battery (LIB) pack in the electric vehicle application. In this regard, a novel dual threshold trigger mechanism based active equalization strategy (DTTM-based AES) is proposed to overcome the inherent inconsistency of cells and to improve the equalization efficiency for a series-connected LIB pack. First, a modified dual-layer inductor equalization circuit is constructed to make it possible for the energy transfer path optimization. Next, based on the designed dual threshold trigger mechanism provoked by battery voltage and SOC, an active equalization strategy is proposed, each single cell's SOC in the battery packs is estimated using the extended Kalman particle filter algorithm. Besides, on the basis of the modified equalization circuit, the improved particle swarm optimization is adopted to optimize the energy transfer path with aiming to reduce the equalization time. Lastly, the simulation and experimental results are provided to validate the proposed DTTM-based AES.

In terms of battery design and evaluation, Electric Vehicles (EVs) are receiving a great deal of attention as a modern, eco-friendly, sustainable transportation method. In this paper, a novel battery pack is designed to maintain a uniform temperature distribution, allowing the battery to operate within its optimal temperature range. The proposed battery design is part of a main channel where a portion of cool air will pass from an inlet then exit from an outlet where a uniform temperature distribution is maintained. First, a 3-D model of a battery cell was created, followed by thermal simulation for 15C, 25C, and 35C ambient temperatures. The simulation results reveal that the temperature distribution is nearly uniform, with slightly higher values in the middle portion of the cell height. Second, using finite element analysis (FEA), it was determined that the heat flux per unit area is nearly uniform with a slight increase at the edges. Third, a machine learning model is proposed by utilizing a neural network (NN). Lastly, the heat flux values were predicted using the NN model that was proposed. The model was assessed based on statistical measures where a root mean square error (RMSE) value of 0.87% was achieved. The NN outperformed FEA in terms of time consumption with a high prediction accuracy, leveraging the potential of adopting machine learning over FEA in related operational assessments.

LoRa technology contributes to green energy by enabling efficient, long-range communication for the Internet of Things (IoT). This paper addresses the challenges related to coverage range in outdoor monitoring systems utilizing LoRa, where the network performance is affected by the density of gateways (GWs) and end devices (EDs), as well as environmental conditions. To mitigate interference, data throughput losses, and high-power consumption, the proposed spreading factor (SF) and hybrid (data rate|SF) models dynamically adjust the transmission parameters. The orchestration of concurrent data modifications within the network server (NS) is crucial for uninterrupted communication between GWs and EDs, especially in monitoring electric vehicle (EV) stations to reduce traffic congestion and pollution. Employing K-means and density-based spatial clustering of applications with noise (DBSCAN) algorithms optimizes ED allocation, averts data congestion, and improves the signal-to-interference noise ratio (SINR). These methods ensure seamless information reception by meticulously allocated EDs across various GW combinations. To estimate the free-space losses (FSL), a log-distance path loss model (log-PL) is used. Exploring various bandwidths (BWs), bidirectional communications, and duty cycles (DCs) helps to prevent saturation, thus prolonging the operational lifespan of EDs. Empirical findings reveal a notable packet rejection rate (PRR) of 0% for the DBSCAN (hybrid model). In contrast, the K-means exhibits a PRR ranging from 5% (hybrid model) to 35.29% (SF model) for the ten GWs combination. Notably, the network saturation is reduced to 10.185% and 9.503%, respectively, highlighting an improvement in the average efficiency of slotted ALOHA (91.1%) and pure ALOHA (90.7%). These enhancements increase the lifespan of EDs to 15,465.27 days.

The rail transit system plays a crucial role in modern transportation. With the increasing demand for clean and green energy in the transport sector, its energy system is expected to achieve low-carbon and highly efficient energy utilization in rail transit. However, the gradual development of the rail transport energy system has led to an increase in its complexity, and the rising difficulty of system assessment has faced the limitations of traditional assessment methods. Hence, it is essential to develop effective assessment methods. This paper begins by providing a systematic review of the development status of Reliability, Availability, Maintainability and Safety (RAMS) assessment and analyzing the shortcomings of traditional RAMS assessment technology in the context of rail transit energy systems. Subsequently, based on the four fundamental properties of RAMS, it summarizes the current state of key assessment technologies in the field of rail transit. Moreover, the paper delves into the challenges and potential solutions concerning the implementation of RAMS assessment technology for rail transit energy systems. Finally, the paper offers an outlook on the future development of RAMS assessment for rail transport energy systems. By comprehensively analyzing these aspects, the paper aims to contribute valuable insights into optimizing the rail transit energy system, promoting its sustainable and efficient operation in the context of clean and green energy utilization.

In this paper, a novel model-based fault detection in the battery management system of an electric vehicle is proposed. Two adaptive observers are designed to detect state-of-charge faults and voltage sensor faults, considering the impact of battery aging. Battery aging primarily affects capacity and resistance, becoming more pronounced in the later stages of a battery lifespan. By incorporating aging effects into our fault diagnosis scheme, our proposed approach prevents false or missed alarms for the aged battery cells. The aging effect of battery, capacity fading and resistance growth, are considered unknown parameters. An adaptive observer is employed to design a fault detector, considering unknown parameters in the battery model. The adaptive observers are designed for two different scenarios: In the first scenario, it is presumed that aging effects remain constant over time due to their slow rate of change. Then, it is assumed that aging effects are time-varying. Therefore, the fault detection scheme can detect faults of new battery cells as well as aged cells. Some simulations have been conducted on a Lithium-ion battery cell and extended to battery pack, to demonstrate the performance of the proposed approach in more real-world scenarios. The results showed that the designed observers can detect faults correctly in a seven years old battery as well as a new one.

Electric vertical takeoff and landing (eVTOL) aircraft have emerged as a potential alternative to the existing transportation system, offering a transition from two-dimensional commuting and logistics to three-dimensional mobility. As a groundbreaking innovation in both the automotive and aviation sectors, eVTOL holds significant promise but also presents notable challenges. This paper aims to address the overall aircraft design (OAD) approach specifically tailored for eVTOL in the context of Urban Air Mobility (UAM). In contrast to traditional OAD methods, this study introduces and integrates disciplinary methodologies specifically catered to eVTOL aircraft design. A case study is conducted on a tilt-duct eVTOL aircraft with a typical UAM mission, and the disciplinary performance, including initial sizing, aerodynamics, electric propulsion systems, stability and control, weight, mission analysis and noise, is examined using the OAD methodologies. The findings demonstrate that the current approach effectively evaluates the fundamental aircraft-level performance of eVTOL, albeit further high-fidelity disciplinary analysis and optimization methods are required for future MDO-based eVTOL overall aircraft design.