Green Energy and Intelligent Transportation最新文献

One of the key components of any smart city is considered to be its intelligent transportation systems (ITSs). Unmanned aerial vehicles (UAVs) are envisioned in several ITS application fields because of their autonomous operation, mobility, communication/processing capabilities, and other factors. In this paper, cooperative terahertz (THz) communication is proposed for flying ad hoc networks (FANETs), which is a particular kind of network made up of a collection of small UAVs linked in an ad hoc fashion and working together to accomplish high-level objectives. The frequency spectrum for wireless communication has been expanding continuously in order to meet the demand for bandwidth. For the forthcoming 6G and beyond, communications in the THz range will be vital, similar to how mmWave-band communications are currently influencing the 5G of wireless mobile communications. The finite state machine (FSM) of the proposed cooperative communication system for THz band is presented. A Markov chain model-based analytical study is carried out, which derives relationships among parameters. Furthermore, numerical results are provided to support the analytical study.

Unmanned Aerial Vehicles (UAVs) offer a strategic solution to address the increasing demand for cellular connectivity in rural, remote, and disaster-hit regions lacking traditional infrastructure. However, UAVs’ limited onboard energy storage necessitates optimized, energy-efficient communication strategies and intelligent energy expenditure to maximize productivity. This work proposes a novel joint optimization model to coordinate charging operations across multiple UAVs functioning as aerial base stations. The model optimizes charging station assignments and trajectories to maximize UAV flight time and minimize overall energy expenditure. By leveraging both static ground base stations and mobile supercharging stations for opportunistic charging while considering battery chemistry constraints, the mixed integer linear programming approach reduces energy usage by 9.1 ​% versus conventional greedy heuristics. The key results provide insights into separating charging strategies based on UAV mobility patterns, fully utilizing all available infrastructure through balanced distribution, and strategically leveraging existing base stations before deploying dedicated charging assets. Compared to myopic localized decisions, the globally optimized solution extends battery life and enhances productivity. Overall, this work marks a significant advance in UAV energy management by consolidating multiple improvements within a unified coordination framework focused on joint charging optimization across UAV fleets. The model lays a critical foundation for energy-efficient aerial network deployments to serve the connectivity needs of the future.

Efficient airport airside ground movement (AAGM) is key to successful operations of urban air mobility. Recent studies have introduced the use of multi-objective multigraphs (MOMGs) as the conceptual prototype to formulate AAGM. Swift calculation of the shortest path costs is crucial for the algorithmic heuristic search on MOMGs, however, previous work chiefly focused on single-objective simple graphs (SOSGs), treated cost enquires as search problems, and failed to keep a low level of computational time and storage complexity. This paper concentrates on the conceptual prototype MOMG, and investigates its node feature extraction, which lays the foundation for efficient prediction of shortest path costs. Two extraction methods are implemented and compared: a statistics-based method that summarises 22 node physical patterns from graph theory principles, and a learning-based method that employs node embedding technique to encode graph structures into a discriminative vector space. The former method can effectively evaluate the node physical patterns and reveals their individual importance for distance prediction, while the latter provides novel practices on processing multigraphs for node embedding algorithms that can merely handle SOSGs. Three regression models are applied to predict the shortest path costs to demonstrate the performance of each. Our experiments on randomly generated benchmark MOMGs show that (i) the statistics-based method underperforms on characterising small distance values due to severe overestimation; (ii) A subset of essential physical patterns can achieve comparable or slightly better prediction accuracy than that based on a complete set of patterns; and (iii) the learning-based method consistently outperforms the statistics-based method, while maintaining a competitive level of computational complexity.

In intelligent lithium-ion battery management, the state of health (SOH) of battery is essential for the batteries’ running in electric vehicles. Popularly, the battery SOH is estimated by using suitable features and data-driven methods. However, it is difficult to extract appropriate features characterizing battery SOH from the charging and discharging data of batteries owing to various state of charges (SOCs) and working conditions of batteries. In order to effectively estimate the battery SOH, an estimation method based on gradual decreasing current, double correlation analysis and gated recurrent unit (GRU) is proposed in this paper. Firstly, gradual decreasing current in the constant voltage charging phase is measured as the raw data. Then, the double correlation analysis method is proposed to select combined features characterizing the battery SOH from different categories of features. Meanwhile, the number of input features is also ensured by the method. Finally, the GRU algorithm is employed to set up a SOH estimation model whose learning rate is improved by using a sparrow search algorithm (SSA) for the purpose of capturing the hidden relationship between features and SOH. The adaptability of the proposed method is validated by SOH estimation experiments of a single battery and a battery pack. Additionally, contrast experiments are performed to show the advanced estimation performance of the proposed method.

Micro short circuit (MSC) fault diagnosis is thought functional in preventing thermal runaway of lithium-ion battery packs. Inconsistencies in the initial state-of-charge and aging state inevitably exist among cells of a battery pack. The existing method for MSC diagnosis disregards the symptoms originating from cell-to-cell inconsistency, which may lead to misdiagnosing inconsistent cells as MSC cells and vice versa. This work presents a method for detecting and quantitatively diagnosing MSC faults in lithium-ion battery packs, while taking cell inconsistency into consideration. Initially, the median incremental capacity (IC), derived based on ranking the terminal voltages of cells, is used as a benchmark representing the state of normal cells. Subsequently, the correlation coefficients between the ICs of individual cells and their median IC are calculated in both the time and frequency domains, as to distinguish the normal, inconsistent, and MSC cells. After detecting the MSC cell, an algorithm, which is based on a recursive least squares algorithm with forgetting factor and an adaptive H_∞ Kalman filtering, is designed to calculate the short-circuit resistance online. The experimental results demonstrate that the short-circuit resistance estimated by the proposed algorithm exhibits rapid convergence to the actual values, thereby confirming the utility of the proposed algorithm in real-life contexts.

Due to their potential for high energy density, low cost, and environmental sustainability, zinc-ion batteries (ZIBs) have emerged as a promising energy storage technology. The performance, safety, and overall efficiency of ZIBs are significantly impacted by the properties of the electrolyte, such as ionic conductivity, electrochemical stability window, viscosity, and compatibility with other battery components. The use of ionic liquids (ILs) in ZIBs has gained extensive attention in recent years due to their desirable properties, such as high thermal stability, low volatility, wide electrochemical window, and tunable physicochemical properties. Therefore, this paper provides a bibliometric analysis of recent advances in the use of ILs as electrolytes in ZIBs. Current research trends, authorship patterns, and publications of ILs in ZIBs are analyzed. Our review reveals a growing interest in the use of ILs as electrolytes in ZIBs, and the development of novel ILs with tailored properties to meet the specific requirements of ZIBs is of a specific focus. This paper provides insights into the recent advancements and future research directions in the field of ILs as electrolytes for ZIBs.

Deep learning-based intelligent vehicle perception has been developing prominently in recent years to provide a reliable source for motion planning and decision making in autonomous driving. A large number of powerful deep learning-based methods can achieve excellent performance in solving various perception problems of autonomous driving. However, these deep learning methods still have several limitations, for example, the assumption that lab-training (source domain) and real-testing (target domain) data follow the same feature distribution may not be practical in the real world. There is often a dramatic domain gap between them in many real-world cases. As a solution to this challenge, deep transfer learning can handle situations excellently by transferring the knowledge from one domain to another. Deep transfer learning aims to improve task performance in a new domain by leveraging the knowledge of similar tasks learned in another domain before. Nevertheless, there are currently no survey papers on the topic of deep transfer learning for intelligent vehicle perception. To the best of our knowledge, this paper represents the first comprehensive survey on the topic of the deep transfer learning for intelligent vehicle perception. This paper discusses the domain gaps related to the differences of sensor, data, and model for the intelligent vehicle perception. The recent applications, challenges, future researches in intelligent vehicle perception are also explored.

Aviation biofuel, which is derived from renewable feedstocks, is typically seen as being fundamentally sustainable. However, a variety of industries are involved in its creation, and several societal actors are involved as well. Therefore, it is crucial to comprehend and assess not just the process's consequences on the environment but also its economic and political ones. Studies examining the social and political implications of aviation biofuel are now uncommon in scholarly literature. The aim of this study, therefore, is to assess key effects of economic, social and politics in aviation biofuel production and usage in aviation industry in Malaysia. This paper addresses this gap by investigating the issues with pertaining to economic, social, and political effects of using biofuels in aviation, usage, adoption, and challenges in aviation industries. A grounded theory approach in qualitative data analysis was used to examine 20 interviews with experts of varying roles and experiences in aviation. Semi-structured were used to interview experts to answer, respond to or comment on them in a way that they think best. Discourse analysis method was used for data collection and analysed using thematic analysis. A total of 21 themes were identified with the first dataset (socioeconomic feasibility) had 16 themes and second dataset (political feasibility) had a total of 5 themes. The study revealed that experts had mixed reactions on the adoption level of biofuels in the aviation industry with most of them indicating that the level of adoption of biofuels in Malaysian aviation industry is high.

Renewable energy sources are gaining popularity, where solar photovolaics (PV) being the most preferred option due to its cleanliness, affordability, and abundance. The energy output of solar PV is primarily based on temperature & irradiance. Therefore, a weather-based intelligent model is needed for estimating solar energy output to fulfil energy demand and decision making. Predicting PV power output is essential for energy management, security, and operation. In addition to enhancing the output efficiency of PV power plants, the power grid's stability can be enhanced by enhancing the efficacy of PV power plants' electricity generation. This work focuses on LSTM and BPNN for forecasting solar plant power output and it is observed that their findings are virtually compatible with realistic power production in terms of MAE, MAPE, RMSPE, and R² score. LSTM model comparisons with different layers for each weather season are also analysed. Comparing the extent of errors in the LSTM and BPNN models reveals that LSTM provides more accurate predictions.

Modelling, predicting and analysing driver behaviours are essential to advanced driver assistance systems (ADAS) and the comprehensive understanding of complex driving scenarios. Recently, with the development of deep learning (DL), numerous driver behaviour learning (DBL) methods have been proposed and applied in connected vehicles (CV) and intelligent transportation systems (ITS). This study provides a review of DBL, which mainly focuses on typical applications in CV and ITS. First, a comprehensive review of the state-of-the-art DBL is presented. Next, Given the constantly changing nature of real driving scenarios, most existing learning-based models may suffer from the so-called “catastrophic forgetting,” which refers to their inability to perform well in previously learned scenarios after acquiring new ones. As a solution to the aforementioned issue, this paper presents a framework for continual driver behaviour learning (CDBL) by leveraging continual learning technology. The proposed CDBL framework is demonstrated to outperform existing methods in behaviour prediction through a case study. Finally, future works, potential challenges and emerging trends in this area are highlighted.