Search Results (18)

With the widespread application of electric vehicles and electrical energy storage systems, the accurate monitoring of lithium battery states has become crucial for ensuring safety and improving efficiency in terms of the applications. For this reason, this study proposes an algorithm focusing on Bayesian optimization-based adaptive extended Kalman filter (BO-AEKF) to enhance the numerical accuracy and stability of state-of-charge (SOC) estimation for lithium batteries under various operating conditions. By comparing with traditional methods, the proposed algorithm, introducing a temperature-adaptive mechanism and a dynamic parameter updating strategy, can effectively address the estimation limitations under severe temperature variations and initial SOC uncertainties. Experimental results demonstrate that the proposed algorithm exhibits superior estimation performance at different temperatures, including −10 °C, 0 °C, 25 °C, and 50 °C; particularly under dynamic operating conditions, the maximum error (MAX) and root mean square error (RMSE) are reduced by 51.9% and 74.5%, respectively, compared to the extended Kalman filter (EKF) and adaptive extended Kalman filter (AEKF) algorithms. Furthermore, the BO-AEKF achieves rapid convergence even with unknown initial SOC values, demonstrating its robustness and adaptability. These findings provide more reliable technical support for the development of battery management systems, making them suitable for state estimation in electric vehicles and renewable energy storage systems. Full article

Cold chain logistics is crucial in ensuring food quality and safety in modern supply chains. The required temperature control systems increase operational costs and environmental impacts compared to conventional logistics. To reduce these costs while maintaining service quality in real-world distribution scenarios, efficient route planning is essential, particularly when products with different temperature requirements need to be delivered together using multi-compartment refrigerated vehicles. This substantially increases the complexity of the routing process. We propose a novel deep reinforcement learning approach that incorporates a vehicle state encoder for capturing fleet characteristics and a dynamic vehicle state update mechanism for enabling real-time vehicle state updates during route planning. Extensive experiments on a real-world road network show that our proposed method significantly outperforms four representative methods. Compared to a recent ant colony optimization algorithm, it achieves up to a 6.32% reduction in costs while being up to 1637 times faster in computation. Full article

With the increasing penetration of distributed photovoltaics (PVs) in distribution networks (DNs), issues like voltage violations and fluctuations are becoming more prominent. This paper proposes a spatio-temporal adaptive voltage coordination control strategy involving multiple timescales and multi-device collaboration. Aiming at the heavy workload caused by the continuous sampling of real-time data in the whole domain, an intra-day innovative construction of intra-day minute-level optimization and real-time adaptive control double-layer control mode are introduced. Intra-day minute-level refinement of on-load tap changer (OLTC) and step voltage regulator (SVR) day-ahead scheduling plans to fully utilize OLTC and SVR voltage regulation capabilities and improve voltage quality is discussed. In real-time adaptive control, a regional autonomy mechanism based on the functional area voltage quality risk prognostication coefficient (VQRPC) is innovatively proposed, where each functional area intelligently selects the time period for real-time voltage regulation of distributed battery energy storage systems (DESSs) based on VQRPC value, in order to improve real-time voltage quality while reducing the data sampling workload. Aiming at the state of charge (SOC) management of DESS, a novel functional area DESS available capacity management mechanism is proposed to coordinate DESS output and improve SOC homogenization through dynamically updated power–capacity availability (PCA). And vine model threshold band (VMTB) and deviation optimization management (DOM) strategies based on functional area are innovatively proposed, where DOM optimizes DESS output through the VMTB to achieve voltage fluctuation suppression while optimizing DESS available capacity. Finally, the DESS and electric vehicle (EV) cooperative voltage regulation mechanism is constructed to optimize DESS capacity allocation, and the black-winged kite algorithm (BKA) is used to manage DESS output. The results of a simulation on a modified IEEE 33 system show that the proposed strategy reduces the voltage fluctuation rate of each functional area by an average of 36.49%, reduces the amount of data collection by an average of 68.31%, and increases the available capacity of DESS by 5.8%, under the premise of a 100% voltage qualification rate. Full article

Autonomous vehicles must make quick and accurate decisions to operate efficiently in complex and dynamic urban traffic environments, necessitating a reliable and stable learning mechanism. The proximal policy optimization (PPO) algorithm stands out among reinforcement learning (RL) methods for its consistent learning process, ensuring stable decisions under varying conditions while avoiding abrupt deviations during execution. However, the PPO algorithm often becomes trapped in a limited search space during policy updates, restricting its adaptability to environmental changes and alternative strategy exploration. To overcome this limitation, we integrated Lévy flight’s chaotic and comprehensive exploration capabilities into the PPO algorithm. Our method helped the algorithm explore larger solution spaces and reduce the risk of getting stuck in local minima. In this study, we collected real-time data such as speed, acceleration, traffic sign positions, vehicle locations, traffic light statuses, and distances to surrounding objects from the CARLA simulator, processed via Apache Kafka. These data were analyzed by both the standard PPO and our novel Lévy flight-enhanced PPO (LFPPO) algorithm. While the PPO algorithm offers consistency, its limited exploration hampers adaptability. The LFPPO algorithm overcomes this by combining Lévy flight’s chaotic exploration with Apache Kafka’s real-time data streaming, an advancement absent in state-of-the-art methods. Tested in CARLA, the LFPPO algorithm achieved a 99% success rate compared to the PPO algorithm’s 81%, demonstrating superior stability and rewards. These innovations enhance safety and RL exploration, with the LFPPO algorithm reducing collisions to 1% versus the PPO algorithm’s 19%, advancing autonomous driving beyond existing techniques. Full article

The auction mechanism stands as a pivotal distributed solution approach for addressing the task allocation problem in unmanned aerial vehicle (UAV) swarms, with its rapid solution capability well-suited to meet the real-time requirements of aerial mission planning for UAV swarms. Building upon the auction mechanism, this paper proposes a distributed task allocation method for multi-UAV grounded in swarm benefits optimization. The method introduces individual benefit variation to quantify the effect of a task on the benefit of a single UAV, thereby enabling direct optimization of swarm benefit through these individual benefit variations. Within the formulated individual benefit calculation, both the spatial distance between tasks and UAVs and the initial task value along with its temporal decay are taken into account, ensuring a thorough and accurate assessment. Additionally, the method incorporates real-time updates of individual benefits for each UAV, reflecting the dynamic state of task benefit fluctuations within the swarm. Monte Carlo simulation experiments demonstrate that, for a swarm size of 16 UAVs and 80 tasks, the proposed method achieves an average swarm benefit improvement of approximately 2% and 4% over the Consensus-Based Bundle Algorithm (CBBA) and Performance Impact (PI) methods, respectively, thus validating its effectiveness. Full article

Urban traffic congestion poses significant economic and environmental challenges worldwide. To mitigate these issues, Adaptive Traffic Signal Control (ATSC) has emerged as a promising solution. Recent advancements in deep reinforcement learning (DRL) have further enhanced ATSC’s capabilities. This paper introduces a novel DRL-based ATSC approach named the Sequence Decision Transformer (SDT), employing DRL enhanced with attention mechanisms and leveraging the robust capabilities of sequence decision models, akin to those used in advanced natural language processing, adapted here to tackle the complexities of urban traffic management. Firstly, the ATSC problem is modeled as a Markov Decision Process (MDP), with the observation space, action space, and reward function carefully defined. Subsequently, we propose SDT, specifically tailored to solve the MDP problem. The SDT model uses a transformer-based architecture with an encoder and decoder in an actor–critic structure. The encoder processes observations and outputs, both encoded data for the decoder, and value estimates for parameter updates. The decoder, as the policy network, outputs the agent’s actions. Proximal Policy Optimization (PPO) is used to update the policy network based on historical data, enhancing decision-making in ATSC. This approach significantly reduces training times, effectively manages larger observation spaces, captures dynamic changes in traffic conditions more accurately, and enhances traffic throughput. Finally, the SDT model is trained and evaluated in synthetic scenarios by comparing the number of vehicles, average speed, and queue length against three baselines, including PPO, a DQN tailored for ATSC, and FRAP, a state-of-the-art ATSC algorithm. SDT shows improvements of 26.8%, 150%, and 21.7% over traditional ATSC algorithms, and 18%, 30%, and 15.6% over the FRAP. This research underscores the potential of integrating Large Language Models (LLMs) with DRL for traffic management, offering a promising solution to urban congestion. Full article

Quantitative research on the evolution and transformation of topics in China’s energy policy can enhance the theoretical and methodological framework of policy document analysis. Utilizing dynamic topic modeling (DTM) and social network analysis, this study examined 1872 energy policy documents issued in China between 1980 and 2023, focusing on detecting hot topics and analyzing trend evolution. DTM identified five core topics: State Grid and new energy, comprehensive energy conservation and emission reduction, intelligent building energy management, promotion of energy-saving products and new energy vehicles, and standardization of energy industry management. Temporal analysis of these core topics reveals a shift in policy focus over time, moving from infrastructure development and standardization management to new energy development and modernization of the energy system. The co-occurrence network of thematic terms transitions from an “independent and loose” structure to a “concentrated and balanced” one, with increasing network scale and frequency. The conclusions of this study offer valuable insights for establishing a dynamic monitoring and real-time updating mechanism for energy policies, enhancing the integration and coordination of energy policy topics, and effectively supporting national energy strategies in response to global energy market challenges. Full article

The design of trajectory tracking controllers for smart driving cars still faces problems, such as uncertain parameters and it being time-consuming. To improve the tracking performance of the trajectory tracking controller and reduce the computation of the controller, this paper proposes an improved model predictive control (MPC) method based on fuzzy control and an online update algorithm. First, a vehicle dynamics model is constructed and a feedforward MPC controller is designed; second, a real-time updating method of the time domain parameters is proposed to replace the previous method of empirically selecting the time domain parameters; lastly, a fuzzy controller is proposed for the real-time adjustment of the weight coefficient matrix of the model predictive controller according to the lateral and heading errors of the vehicle, and a state matrix-based cosine similarity updating mechanism is developed for determining the updating nodes of the state matrix to reduce the controller computation caused by the continuous updating of the state matrix when the longitudinal vehicle speed changes. Finally, the controller is compared with the traditional model prediction controller through the co-simulation of CARSIM and MATLAB/Simulink, and the results show that the controller has great improvement in terms of tracking accuracy and controller computational load. Full article

Unmanned surface vehicles (USVs) have garnered significant attention across various application fields. A sufficiently accurate kinetic model is essential for achieving high-performance navigation and control of USVs. However, time-varying unobservable internal states and external disturbances pose challenges in accurately modeling the USV’s kinetics, and existing methods face difficulties in accurately estimating unknown time-varying disturbances online while ensuring precise mechanism modeling. To address this issue, a novel grey-box modeling method based on incremental learning and mechanisms (GBM-ILM) is proposed. Its union structure combines the advantages of both incremental learning networks and physical mechanisms for estimating the USV’s full kinetics. Depending on the linear parameter-varying (LPV) mechanism, it not only adheres to physical laws but also calculates the unstructured model errors. An incremental learning network is implemented to continuously refine model errors, by accounting for the USV’s time-varying characteristics and iteratively updating the network parameters and structures to adapt to different USV states and environmental disturbances. To validate this method, we developed the ‘Salmon’ USV and conducted identification experiments in a lake. Compared to tests of other state-of-the-art methods, our method has better adaptability, with 46.34%, 14.86%, and 6.87% accuracy improvements when estimating the USV’s forward, turning, and sideslip dynamic model, respectively. Full article

Multiple unmanned aerial vehicles (Multi-UAV) systems have recently demonstrated significant advantages in some real-world scenarios, but the limited communication range of UAVs poses great challenges to multi-UAV collaborative decision-making. By constructing the multi-UAV cooperation problem as a multi-agent system (MAS), the cooperative decision-making among UAVs can be realized by using multi-agent reinforcement learning (MARL). Following this paradigm, this work focuses on developing partially observable MARL models that capture important information from local observations in order to select effective actions. Previous related studies employ either probability distributions or weighted mean field to update the average actions of neighborhood agents. However, they do not fully consider the feature information of surrounding neighbors, resulting in a local optimum often. In this paper, we propose a novel partially multi-agent reinforcement learning algorithm to remedy this flaw, which is based on graph attention network and partially observable mean field and is named as the GPMF algorithm for short. GPMF uses a graph attention module and a mean field module to describe how an agent is influenced by the actions of other agents at each time step. The graph attention module consists of a graph attention encoder and a differentiable attention mechanism, outputting a dynamic graph to represent the effectiveness of neighborhood agents against central agents. The mean field module approximates the effect of a neighborhood agent on a central agent as the average effect of effective neighborhood agents. Aiming at the typical task scenario of large-scale multi-UAV cooperative roundup, the proposed algorithm is evaluated based on the MAgent framework. Experimental results show that GPMF outperforms baselines including state-of-the-art partially observable mean field reinforcement learning algorithms, providing technical support for large-scale multi-UAV coordination and confrontation tasks in communication-constrained environments. Full article

Widespread usage of unmanned aerial vehicles (UAVs) in new and emerging applications needs dynamic and adaptive networking. The development of routing protocols for UAV ad hoc networks faces numerous issues because of the unique characteristics of UAVs, such as rapid mobility, frequent changes in network topology, and limited energy consumption. The Optimized Link State Routing (OLSR) protocol seems to be a promising solution as it offers improved delay performance. It is expected that OLSR will satisfy the strict demands of real-time UAV applications such as “search and rescue” (SAR) missions as it involves the most recent update of routing information. The classical OLSR routing protocol and its enhanced versions, D-OLSR, ML-OLSR, and P-OLSR, use different techniques to make an appropriate decision for routing packets. These routing techniques consider the quality of a wireless link, type of antenna, load, and mobility-aware mechanism to select the best UAV to send the message to the destination. This study evaluates and examines the performance of the original and modified OLSR routing protocols in UAV ad hoc networks for three SAR scenarios: (1) increasing mobility, (2) increasing scalability, and (3) increasing the allowed space of UAVs. It analyzes and validates the performance of the four OLSR-based routing protocols. It determines the best OSLR routing protocol by taking into account the packet delivery ratio, latency, energy consumption, and throughput. The four routing protocols and the SAR scenarios were simulated using NS-3.32. Based on the simulation results, ML-OLSR outperforms OLSR, D-OLSR, and P-OLSR in the considered measures. Full article

The problem of vehicle re-identification in surveillance scenarios has grown in popularity as a research topic. Deep learning has been successfully applied in re-identification tasks in the last few years due to its superior performance. However, deep learning approaches require a large volume of training data, and it is particularly crucial in vehicle re-identification tasks to have a sufficient amount of varying image samples for each vehicle. To collect and construct such a large and diverse dataset from natural environments is labor intensive. We offer a novel image sample synthesis framework to automatically generate new variants of training data by augmentation. First, we use an attention module to locate a local salient projection region in an image sample. Then, a lightweight convolutional neural network, the parameter agent network, is responsible for generating further image transformation states. Finally, an adversarial module is employed to ensure that the images in the dataset are distorted, while retaining their structural identities. This adversarial module helps to generate more appropriate and difficult training samples for vehicle re-identification. Moreover, we select the most difficult sample and update the parameter agent network accordingly to improve the performance. Our method draws on the adversarial networks strategy and the self-attention mechanism, which can dynamically decide the region selection and transformation degree of the synthesis images. Extensive experiments on the VeRi-776, VehicleID, and VERI-Wild datasets achieve good performance. Specifically, our method outperforms the state-of-the-art in MAP accuracy on VeRi-776 by 2.15%. Moreover, on VERI-Wil, a significant improvement of 7.15% is achieved. Full article

Path tracking plays a crucial role in autonomous driving. In order to ensure the real-time performance of the controller and at the same time improve the stability and adaptability of the path tracking controller, a lateral path control strategy based on the improved LQR algorithm is proposed in this paper. To begin with, a discrete LQR controller with feedforward and feedback components is designed based on the error model of vehicle lateral dynamics constructed by the natural coordinate system. Then, a fuzzy control method is applied to adjust the weight coefficients of the LQR in real time according to the state of the vehicle. Furthermore, an update mechanism based on cosine similarity is designed to reduce the computational effort of the controller. The improved LQR controller is tested on a joint Simulink–Carsim simulation platform for a two-lane shift maneuver. The results show that the control algorithm improves tracking accuracy, steering stability and computational efficiency. Full article

Recently, correlation filter (CF)-based tracking algorithms have attained extensive interest in the field of unmanned aerial vehicle (UAV) tracking. Nonetheless, existing trackers still struggle with selecting suitable features and alleviating the model drift issue for online UAV tracking. In this paper, a robust CF-based tracker with feature integration and response map enhancement is proposed. Concretely, we develop a novel feature integration method that comprehensively describes the target by leveraging auxiliary gradient information extracted from the binary representation. Subsequently, the integrated features are utilized to learn a background-aware correlation filter (BACF) for generating a response map that implies the target location. To mitigate the risk of model drift, we introduce saliency awareness in the BACF framework and further propose an adaptive response fusion strategy to enhance the discriminating capability of the response map. Moreover, a dynamic model update mechanism is designed to prevent filter contamination and maintain tracking stability. Experiments on three public benchmarks verify that the proposed tracker outperforms several state-of-the-art algorithms and achieves a real-time tracking speed, which can be applied in UAV tracking scenarios efficiently. Full article

With railway interoperability, new trains are allowed to move on the French railway network. These trains may present different designs from standard trains. This work aims to complete the current approach for vehicle admission on the railway network, which is defined in technical baselines. Historically, computation rules for traffic conditions are based on simplified analytical works, which are considerably qualitative. They have evolved through feedback and experimental campaigns to comply with the track structure evolution. An efficient methodology based on numerical simulation is needed to evaluate railway vehicle admission to answer this issue. A perspective to update these computation rules is to evaluate the structural fatigue in the rail. That is to say, fatigue is caused by bending and shear stresses. The complexity of the railway system has led to an investigation at first of the vertical response of the railway track and quantifying its contribution to the rail’s stress response. In that sense, this paper investigates the vertical track response to a moving railway vehicle at low frequencies. For this purpose, a lightweight numerical model for the track, a multi-body model for the vehicle, and a random vertical track irregularity are proposed. More explicitly, the track model consists of a two-layer discrete support model in which the rail is considered as a beam and sleepers are point masses. The rail pads and ballast layer are modelled as spring/damper couples. Numerical results show a negligible effect of track inertia forces due to high track stiffness and damping. Nevertheless, this assumption is valid for normal rail stresses but not for ballast loading, especially in the case of sleeper voids or unsupported sleepers. Hence, the prediction of the mechanical stress state in the rail for fatigue issues is achieved through a static track model where the equivalent loading is obtained from a dynamic study of a simplified vehicle model. A statistical analysis shows that the variability of the vertical track irregularity does not influence the output variabilities like the maximum in time and space of the normal and shear stress. Full article