检索结果-内蒙古大学图书馆

Battery voltage fault diagnosis for electric vehicles considering driving condition variation

IET INTELLIGENT TRANSPORT SYSTEMS 2024年第4期18卷 574-590页

作者： Zhang, Hui Li, Shaopeng Chen, Feng Pan, Xiaofeng Feng, Hongxia Sun, Yifan Wuhan Univ Technol Intelligent Transportat Syst Res Ctr Wuhan 430063 Hubei Peoples R China

To ensure the real-time operation safety of electric vehicles (EVs), it is essential to diagnose the fault in a battery pack timely and accurately. In this paper, with considering driving condition, a battery voltage fault diagnosis method is proposed based on the real-world operation data of EVs with a high sampling frequency. Firstly, based on driving behaviour, the driving condition of EVs is classified into four categories, and accordingly, the operation process is divided into four segments. The influencing mechanism of driving condition on battery voltage is revealed by detailed analysis on extracted operation segments. Secondly, four BP neural network (BPNN)-based voltage prediction models are developed, respectively, for the four kinds of driving conditions. Based on the statistical analysis of prediction error and the comparison with other voltage prediction models, the superiority and stability of the four well-trained BPNN models are verified. Thirdly, the voltage abnormity levels and thresholds for fault diagnosis are set considering driving condition differences. The effectiveness of the proposed method is verified using the actual operational data. The verification results show that the proposed method can achieve good voltage prediction and fault diagnosis for EVs under various driving conditions during the entire operation process.

关键词： BP neural network-based voltage prediction models power engineering computing voltage abnormity thresholds automotive electric vehicles neural nets fault diagnosis Other topics in statistics sampling frequency Neural nets automotive computing Automobile electronics and electrics operation safety traffic engineering computing driving behaviour battery voltage fault diagnosis method electric vehicles voltage abnormity levels BPNN models backpropagation driving condition variation statistical analysis battery powered vehicles Power engineering computing traffic engineering computing

来源：评论

学校读者我要写书评

暂无评论

Prediction of airport surface potential conflict based on GNN-LSTM

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2025年第1期19卷

作者： Yuan, Ligang Fang, Daoming Chen, Haiyan Liu, Jing Nanjing Univ Aeronaut & Astronaut Coll Civil Aviat Nanjing Peoples R China State Key Lab Air Traff Management Syst Nanjing Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China

The development of the civil aviation industry has contributed to a steady increase in the number of daily flight operations at airports, which in turn has led to increasingly complex airport ground layouts. To aid airport managers in understanding the operational situation on the airport surface, this paper introduces a predictive model for airport ground conflict situations based on GNN-LSTM. This model identifies potential conflicts, conflict hotspots, and conflict hotspots zones, designating key intersections on taxiways as conflict hotspots according to taxiing rules. A conflict network is constructed, employing GNN with an integrated attention mechanism to extract structural features of the network, while LSTM is utilized to capture temporal features. After tuning the model parameters, predictions are made regarding the overall potential number of potential conflicts on the surface. To validate the effectiveness of the model, experimental analysis is conducted using AirTOp simulation data from Shenzhen Bao'an Airport, comparing GNN-LSTM model with GNN-GRU, LSTM, and GRU models, using RMSE and MAE as loss functions. The results demonstrate that he proposed modelling approach effectively extracts the temporal features of potential conflict and GNN-LSTM model outperforms other models in predicting the overall number of potential conflicts.

关键词： airports time series traffic engineering computing transport modelling and microsimulation

来源：评论

学校读者我要写书评

暂无评论

Exploring the impacts of traffic flow states on freeway normal crashes, primary crashes, and secondary crashes

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2024年第3期18卷 517-527页

作者： Yang, Bo Guo, Yanyong Zhang, Weihua Yao, Ying Wu, Yiping Anhui Univ Sch Internet Hefei 230009 Anhui Peoples R China Southeast Univ Sch Transportat Jiangsu Key Lab Urban ITS Nanjing Jiangsu Peoples R China Hefei Univ Technol Sch Automot & Traff Engn Hefei Anhui Peoples R China Beijing Univ Technol Coll Metropolitan Transportat Beijing Peoples R China

This study aims to explore the relationship between traffic flow states and crash type/severity in the scenarios of normal crashes, primary crashes, and secondary crashes using the association rules mining approach. The crash data and real-time traffic data were collected from the I-880 freeway for five years in California, USA. The secondary crashes were identified using a speed contour plot approach. traffic flow states were identified by the three-phase flow theory. The results showed that the free flow is associated with the proportion of the sideswipe normal crash, the hit object primary crash, and the injury primary crash. The synchronized flow, the wide moving jams, and the transitional state from synchronized flow to wide moving jams are associated with the proportion of the rear-end secondary crash. The transitional state from synchronized flow to free flow is associated with the proportion of the rear-end primary crash and the property damage only primary crash. In addition, the unsafe speed behaviour can increase the proportion of the rear-end normal, primary, and secondary crashes. The unsafe lane change behaviour can increase the proportion of the sideswipe normal, primary, and secondary crashes. These results have the potential to reduce the secondary crash probability.

关键词： data mining rear-end normal, primary, crash data rear-end primary crash injuries injury primary crash probability rear-end secondary crash free flow road traffic primary crashes intelligent transportation systems road vehicles property damage only primary crash secondary crashes traffic flow states sideswipe normal crash road accidents Systems theory applications in transportation secondary crash probability traffic engineering computing sideswipe normal, primary, Data handling techniques road safety hit object primary crash synchronized flow transitional state freeway normal crashes traffic engineering computing

来源：评论

学校读者我要写书评

暂无评论

Positioning method of expressway ETC gantry by multi-source traffic data

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2024年第3期18卷 540-554页

作者： Guo, Feng Zou, Fumin Luo, Sijie Chen, Haobin Yu, Xiang Zhang, Cheng Liao, Lyuchao Fuzhou Univ Coll Comp & Data Sci Fuzhou Fujian Peoples R China Fujian Univ Technol Fujian Key Lab Automot Elect & Elect Drive Fuzhou 350118 Fujian Peoples R China Hunan Univ Finance & Econ Coll Informat Technol & Management Changsha Hunan Peoples R China

With the rapid development of expressway Electronic Toll Collection (ETC) technology in China, the expressway management system is becoming digital and intelligent, which provides a solid foundation for expressway vehicle infrastructure cooperation and autonomous driving. The gantry position is the key part of the ETC system. However, there are still some problems (e.g. gantry position missing or false), which can seriously affect the intelligent development of expressways. To address these two issues, an ETC gantry positioning method is proposed. First, the ETC transaction data and the GPS data on expressways are preprocessed to remove abnormal data and retrieve missed data. Then, combined with Dead Reckoning (DR) and Median Center, the potential position of the gantry is calculated from ETC transaction data and GPS data. Finally, the switching strategy based on Kalman Filter (KF) is used to capture the final gantry position. By comparing the results of the proposal with the collected gantry position, it is found that the positioning error of the gantry position calculated by this proposal is about 37 m. The positioning accuracy is 98.78% with the threshold of 100 m. The experimental results show that the proposal can effectively locate the expressway gantry.

关键词： positioning error positioning accuracy expressway vehicle infrastructure cooperation intelligent development abnormal data Global Positioning System multisource traffic data expressway Electronic Toll Collection technology road traffic Filtering methods in signal processing intelligent transportation systems road vehicles collected gantry position traffic engineering computing Kalman filters GPS data ETC transaction data expressway gantry ETC gantry positioning method potential position traffic engineering computing final gantry position expressway management system

来源：评论

学校读者我要写书评

暂无评论

Enhanced motorway capacity estimation considering the impact of vehicle length on the fundamental diagram

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2024年第S1期18卷 2995-3012页

作者： Giesen Loo, Erik Corbally, Robert Feely, Lewis O'Sullivan, Andrew ROD IS Roughan & ODonovan Res & Innovat Arena Rd Dublin Ireland Transport Infrastruct Ireland Network Operat Dublin Ireland

The ability to understand the underlying fundamentals of traffic flow behaviour facilitates improved planning and decision-making for road operators. This paper presents an overview of the various models which can be used to describe the interaction between the different parameters governing traffic flows. 5-years of measured data from Ireland's M50 motorway are used to demonstrate the application of traffic flow theory using real data, and a detailed investigation of factors affecting the fundamental traffic behaviour is presented. The road capacity is shown to be impacted by different traffic behaviour during morning and evening-peak periods, during dry vs. wet weather conditions and between lanes on the approach to junctions. It is demonstrated that the mean vehicle length is an important factor to consider when using traffic flow models. A novel 3-dimensional fundamental diagram model linking mean vehicle speed, mean vehicle length, and density is introduced which enhances capacity estimation and illustrates the importance of considering vehicle length when using the fundamental diagram to interpret traffic flows and estimate the capacity of the motorway. This paper presents an the application of various fundamental diagram models to real traffic data to examine factors which influence their ability to model traffic behaviour. A new model, which allows the vehicle length to be included is developed and allows motorway capacity estimates to be made, with consideration of the vehicle length effect. image

关键词： management and control traffic traffic engineering computing traffic modelling

来源：评论

学校读者我要写书评

暂无评论

An evaluation of lane management strategy for CAV priority in mixed traffic

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2024年第3期18卷 467-479页

作者： Wang, Zhengwu Mi, Qi Xiang, Jian Zhang, Zhaolei Tang, Jinjun Changsha Univ Sci & Technol Key Lab Highway Engn Minist Educ Changsha Peoples R China Changsha Univ Sci & Technol Sch Traff & Transportat Engn Changsha 410114 Peoples R China Cent South Univ Sch Traff & Transportat Engn Changsha Peoples R China

The emergence of connected autonomous vehicles (CAVs) has the potential to dramatically increase road capacity, and the provision of dedicated lanes for CAVs is a common management strategy to ensure that CAVs take appropriate priority over other vehicles. However, existing models of CAV lane management do not perform well at low CAV market penetration rates. Therefore, a novel model is proposed to address this shortcoming in this paper, and qualified human-driven vehicles (HDVs) are allowed to enter the CAV priority lane when there is a low CAV penetration rate. A theoretical model is proposed to examine the impacts of three managed lane strategies under mixed traffic and then compare three lane management strategies under different CAV penetration rates and traffic demands. The results show that these lane management strategies can improve throughput, reduce travel time, increase speed, and reduce the variance of the distribution of vehicle speeds under different penetration rates and traffic demands.

关键词： CAV priority lane common management strategy connected autonomous vehicles lane management strategy human-driven vehicles dedicated lanes low CAV penetration rate road traffic lane strategies intelligent transportation systems road vehicles road traffic control different CAV penetration rates different penetration rates Systems theory applications in transportation traffic engineering computing low CAV market penetration rates traffic demands appropriate priority Road-traffic system control CAV lane management mixed traffic traffic engineering computing

来源：评论

学校读者我要写书评

暂无评论

Binary residual feature pyramid network: An improved feature fusion module based on double-channel residual pyramid structure for autonomous detection algorithm

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2023年第7期17卷 1288-1301页

作者： Luo, Tong Wang, Hai Cai, Yingfeng Chen, Long Wang, Kuan Yu, Yijie Jiangsu Univ Automot Engn Res Inst Zhenjiang 212013 Jiangsu Peoples R China Jiangsu Univ Sch Automot & Traff Engn Zhenjiang Jiangsu Peoples R China

The vehicle detection algorithm based on visual perception has been applied in all types of automatic driving scenes. However, there are still flaws in the current detection algorithm model, especially for small objects. The detection effect of vehicle objects with small pixels in the image is often missed and wrongly detected. This research proposes an improved feature fusion module based on double-channel residual pyramid (DRP) structure for autonomous detection algorithm which named binary residual feature pyramid network (BiResFPN) to solve the above problems. Firstly, a DRP structure, which can effectively supplement the shallow information of the network, is proposed. The residual structure is added to the output feature map for further supplement. Then, an average sampling method of positive and negative samples based on intersection-over-union (IOU) value is proposed on the basis of this structure, aimed at the unbalanced sampling of positive and negative samples in the training stage of faster regions with CNN features (RCNN). It leads to the reduction of the interference of a large number of simple negative samples, which makes the learned model better. The experimental results based on the KITTI and BDD100K dataset datasets show that the capability of the feature fusion module based on DRP structure is strong for small object detection. Compared with Faster-RCNN (FPN), the detection algorithm of small object detection accuracy AP(small) was increased by 2.6%, AP(medium) and AP(large) was increased by 1.1% and 0.3%.

关键词： traffic engineering computing feature extraction learning (artificial intelligence) positive samples object detection accuracy AP current detection algorithm model Neural nets CNN features Optical, image and video signal processing image fusion Computer vision and image processing techniques autonomous detection algorithm convolutional neural nets sampling methods traffic engineering computing object detection output feature map DRP structure deep learning (artificial intelligence) Image recognition binary residual feature pyramid network vehicle objects detection effect simple negative samples double-channel residual pyramid structure vehicle detection algorithm improved feature fusion module residual structure

来源：评论

学校读者我要写书评

暂无评论

A deep learning and ensemble learning based architecture for metro passenger flow forecast

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2023年第3期17卷 483-498页

作者： Wang, Xin Zhu, Changfeng Jiang, Jiahao Lanzhou Jiaotong Univ Sch Traff & Transportat Lanzhou 730070 Peoples R China Southwest Jiaotong Univ Sch Transportat & Logist Chengdu Peoples R China

Accurate short-term forecast of metro outbound passenger flow is of great significance for real-time traffic control and guidance. A good forecast method should have high accuracy, timeliness and practicality. Based on deep learning and ensemble learning technology, this study proposes an end-to-end forecast hybrid architecture for metro outbound passenger flow that integrates multiple passenger flow features. The architecture innovatively integrates bagging ensemble learning strategy and transfer learning with deep learning, and includes multiple extensible passenger flow feature processing components. In addition, this study presents a new coding method to incorporate the operating characteristics of the metro into the forecasting architecture. Use the automatic fare collection (AFC) data of Chengdu Metro Tianfu Square Station for training and verify the forecast architecture on workdays, weekends and holidays. The results reveal that compared with other widely used passenger flow forecast models, the architecture proposed in this study has achieved the highest forecast accuracy in the above-mentioned different time types. Furthermore, the fusion of transfer learning improves the accuracy of forecast model while significantly speeding up the convergence of training, increasing its timeliness and practicability.

关键词： multiple extensible passenger flow feature processing components forecasting theory ensemble learning strategy traffic engineering computing railways ensemble learning based architecture real-time traffic control Chengdu Metro Tianfu Square Station passenger flow forecast models forecast accuracy data handling Neural nets deep learning based architecture metro outbound passenger flow traffic engineering computing accurate short-term forecast Data handling techniques forecast architecture deep learning (artificial intelligence) metro passenger flow forecast transfer learning computing in other engineering fields learning technology forecast model forecast method end-to-end forecast hybrid architecture forecasting architecture

来源：评论

学校读者我要写书评

暂无评论

Decentralised CAVs based on micro-macro flow control (MiMaFC) strategy for multi-intersection traffic network

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2023年第3期17卷 499-517页

作者： Zhu, Zhengze Adouane, Lounis Quilliot, Alain Univ Clermont Auvergne UMR CNRS 6602 Inst Pascal F-63178 Aubiere France Hubei Univ Automot Technol Inst Automot Engineers Shiyan Peoples R China Univ Technol Compiegne UMR CNRS 7253 Heudiasyc Compiegne France Univ Clermont Auvergne LIMOS UMR CNRS 6158 Aubiere France

Advanced intersection control systems have been created to alleviate traffic congestion. CAVs may benefit from cooperative navigation in order to address the regular traffic issue. Due to whole uncertainty in transportation network, the conventional motion planning for local areas may lead to undesirable effects in long run. In prior works, a micro-macro flow control (MiMaFC) strategy is used to investigate CAVs' navigation at unsignalised intersections by taking flow velocity and vehicle passing priority into account. To get a better understanding of motion control and how it can be utilised to impact traffic flow behaviour, this study expands the intersection navigation protocol and develops a velocity planning methodology based on the proposed MiMaFC technology. Correspondingly, cooperative navigation protocol used in the addressed architecture is specifically developed for CAVs that continually cross intersections. Further, spatio-temporal velocity adaption mechanism is presented in this work. Depending on the vehicles' location and speed, CAVs might use either the MiMaFC-based or self-interested velocity strategy. Simulation results, which include a congested traffic network, are shown to demonstrate the proposed method's potential. The study found that the suggested motion planning framework may increase urban network mobility over a non-supervised CAVs system.

关键词： traffic engineering computing motion control transportation advanced intersection control systems Spatial variables control traffic congestion road safety MiMaFC technology flow velocity micromacro flow control strategy congested traffic network multiintersection traffic network path planning decentralised CAV intersection navigation protocol self-interested velocity strategy conventional motion planning Control engineering computing road traffic control traffic flow behaviour traffic engineering computing CAV navigation Road-traffic system control suggested motion planning framework regular traffic issue spatio-temporal velocity adaption mechanism road vehicles nonsupervised CAV system unsignalised intersections

来源：评论

学校读者我要写书评

暂无评论

Hybrid models of subway passenger flow prediction based on convolutional neural network

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2023年第4期17卷 716-729页

作者： Lai, Yuan-wen Wang, Yang Xu, Xin-ying Easa, Said M. Zhou, Xiao-wei Fuzhou Univ Coll Civil Engn Fuzhou 350108 Fujian Peoples R China Putian City Rail Transit Co Ltd Putian Fujian Peoples R China Ryerson Univ Depattment Civil Engn Toronto ON Canada

Accurate and stable short-term passenger flow prediction is an indispensable part of current intelligent transportation systems. This paper proposes two deep learning prediction models based on convolutional neural networks (CNN) and long short-term memory neural network (LSTM). Combining the CNN characteristics and the LSTM, the ConvXD-LSTM extracts passenger flow features through CNN and then inputs the time series into the LSTM. The ConvLSTM converts the weight calculation of the LSTM into convolution operation to realize short-term passenger flow prediction. Fuzhou Metro Line 1 passenger flow data was used for verification. The models were used to predict the passenger flow of subway stations and cross-sections and compared with the traditional prediction models. In terms of prediction accuracy, ConvLSTM has the highest accuracy, followed by ConvXD-LSTM. In terms of running time, ConvXD is the fastest and LSTM takes the longest. ConvXD-LSTM and ConvLSTM are in the middle of the two models, achieving a good balance between accuracy and efficiency. Compared with ConvXD-LSTM, ConvLSTM has a relatively simple network structure, which reduces the computational burden and improves the prediction accuracy.

关键词： traffic engineering computing railways convolutional neural network recurrent neural nets passenger flow features ConvLSTM CNN traditional prediction models Time series time series Neural nets prediction accuracy convolutional neural nets long short-term memory neural network deep learning prediction models traffic engineering computing hybrid models deep learning (artificial intelligence) intelligent transportation systems short-term passenger flow prediction computing in other engineering fields Fuzhou Metro Line 1 passenger flow data ConvXD-LSTM subway passenger flow prediction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：