A5064940003- Traffic Prediction and Management Techniques
- Advanced Battery Technologies Research
- Electric Vehicles and Infrastructure
- Electric and Hybrid Vehicle Technologies
- Advanced Algorithms and Applications
- Vehicle emissions and performance
- Autonomous Vehicle Technology and Safety
- Traffic control and management
- Vehicular Ad Hoc Networks (VANETs)
- Vehicle Dynamics and Control Systems
- Fault Detection and Control Systems
- Advancements in Battery Materials
- Traffic and Road Safety
- Artificial Immune Systems Applications
- Evaluation Methods in Various Fields
- Complex Network Analysis Techniques
- Anomaly Detection Techniques and Applications
- Advanced Sensor and Control Systems
- Industrial Technology and Control Systems
- Human Mobility and Location-Based Analysis
- Chaos-based Image/Signal Encryption
- Mobile Agent-Based Network Management
- Image and Signal Denoising Methods
- Smart Grid and Power Systems
- Infrastructure Maintenance and Monitoring
Changsha University of Science and Technology
2009-2024
State Key Laboratory of Vehicle NVH and Safety Technology
2023
Inner Mongolia Electric Power (China)
2012-2021
Hunan Institute of Engineering
2012
Tongji University
2011
North China Electric Power University
2007-2008
Hebei Agricultural University
2007
China Institute Of Communications
2005
In a mixed traffic environment of human and autonomous driving, it is crucial for an vehicle to predict the lane change intentions trajectories vehicles that pose risk it. However, due uncertainty intentions, accurately predicting great challenge. Therefore, this paper aims establish connection between propose dual Transformer model target vehicle. The contains intention prediction trajectory model. able extract social correlations in terms states outputs probability vector. fuses vector,...
Abstract The concept of green and sustainable development is driving the convergence transportation systems energy technologies. New harvesting technology (EHT) an important way in intelligent system. Comparing with power supply via batteries or cables, it has advantages convenient, sustainable, low carbon to harvest mechanical from traffic environment convert into electrical widely distributed small electromechanical systems. There are many studies on environment, few them have...
Accurate state of charge (SOC) plays a vital role in battery management systems (BMSs). Among several developed SOC estimation methods, the extended Kalman filter (EKF) has been extensively applied. However, EKF cannot achieve valid when model accuracy is inadequate, noise covariance matrix uncertain, and sensor large errors. This paper makes two contributions to overcome these drawbacks: (1) A variable forgetting factor recursive least squares (VFFRLS) proposed accomplish parameters...
Monitoring various types of disasters involves diversified requirements, such as the spectral band, resolution, and timeliness. However, at present, different observation platforms are separately operated. This isolated resource organization model is insufficient to meet requirements Earth-observation tasks, especially when occur. As a result, it necessary construct an network that contains space-air-ground resources makes unified task planning for included heterogeneous resources,...
Liquid cooling battery thermal management systems (BTMSs) are prevalently used in electric vehicles (EVs). With the use of fast charging and high-power cells, there is an increasing demand on performance. In this context, a bionic fish scale (BFS) channel structure optimization design method proposed to optimize The effects different structural parameters liquid plate BTMS its performance, including BFS notch diameter (D), depth (H), spacing (S), investigated. To minimize maximum temperature...
摘要: 自动驾驶车辆与传统车辆混行的交通环境中,车辆的换道意图预测能够为自动驾驶车辆安全行驶提供有效保证。为了更准确地预测车辆的换道意图,将多头注意力与卷积神经网络(Convolution neural network,CNN)和长短时记忆(Long-short term memory,LSTM)网络结合,提出一种新型车辆换道意图预测算法。首先对NGSIM(Next generation Simulaion)数据集进行处理,提取车辆横向位置信息和周围环境信息。然后输入基于多头注意力(Multi-headattention)的CNN-LSTM模型,提高对输入序列特征的提取能力和预测精度。最后在NGSIM数据集验证该模型的有效性。试验结果表明,该模型能够从大量数据中提取到重要特征,同时通过特征对比试验发现,横向位置信息作为预测的主要特征,而周围环境信息作为预测的辅助特征。最后通过模型的对比试验得出,该模型的换道意图预测准确率在换道前1s、2s、3s相比于LSTM、CNN、CNN-LSTM模型具有更好的预测精度,可以为自动驾驶汽车设计先进的意图预测算法提供帮助和参考。
A coordinated torque distribution method (CTDM) combined with balanced vectoring (BTVDM) and differential braking (DBDM) is proposed to enhance vehicle lateral stability improve ride comfort. The phase plane of sideslip angle its angular velocity three regions are used evaluate stability. models region boundary parameters considering velocity, steering angle, road adhesion coefficient established on the basis nonlinear partial least squares regression model (NLPLSRM). Vehicle dynamically...
The key to traffic prediction is accurately depict the temporal dynamics of flow traveling in a road network, so it important model spatial dependence network. essence describe how information transmission affected by other nodes and GNN-based model, as benchmark for prediction, has become most common method ability transmitting with message passing mechanism. However, existing methods local static dependence, which cannot transmit global-dynamic (GDTi) required long-term prediction....
Detecting carbon emissions is the key to peaking and neutrality goals. Existing research has focused on utilizing data-driven method study off a single object. This proposes regional prediction method. The area objects are divided into dynamic for vehicles static buildings. For object, modeled using vehicle location provided by BeiDou satellite navigation system (BDS). neural network R3det (rotation remote sensing target detection) used identify buildings in images, then trained ARIMA time...
With the rapid development and application of autonomous technology in vehicles, we are going to see more vehicles on roads a foreseeable future. While may have advantage reducing traffic accidents caused by human drivers’ neglect and/or fatigue, one challenges is how develop driving algorithms such that can be safely deployed mixed environment with both human-driven vehicles. Instantaneous lane-changing type significantly different for drivers, which would lead other including In this...
The initial state can influence the accuracy of accident reconstruction results, so pedestrian in needs to be studied deeply. vehicle-pedestrian impact was modeled by PC-Crash code, and then crossing speed direction on throw distance injury head were analyzed using results from simulations. In order know more information about pedestrian, a traffic survey experiment conducted at without lights Changsha. law presented. Furthermore, analyzed. It found that influenced significantly trip...