检索结果-内蒙古大学图书馆

2023 China Automation Congress, CAC 2023

作者： Zheng, Haoyuan Hou, Enguang Jiang, Yuyi Shen, Zhen Xiong, Gang Li, Chuanfu Han, Tao The College of Rail Transit of Shandong Jiaotong University Jinan China Qingdao Academy of Intelligent Industries Qingdao China Institute of Automation Chinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Beijing China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China Shandong Hi-Speed Qingdao Development Company Group Qingdao China

ISBN: (纸本)9798350303759

The detection of fallen pedestrians is one of the key problems in automatic driving. Due to complex road conditions, the detection of fallen pedestrians during driving is still challenging for occlusion and small targets. Usually, existing methods such as convolutional networks have low detection accuracy for these cases. Therefore, in this paper we propose to apply the Coord-Aware Transformer YOLOv7 (T-YOLOv7) method to the detection of fallen pedestrians. The CoordConv Feature Pyramid Networks (C-FPN) and the CoordConv perception Detect (C-Detect) are designed. By introducing feature coordinate channels, the network can perceive the spatial information of the feature map, improve the detection of occluded targets. Add the Biformer module to the C-FPN to improve the detection accuracy of small targets. In addition, we use the Wise-IoU to replace the original network CIoU, it can focus on ordinary prediction boxes. The improved network model achieved 87.45% mAP on the open source data set Fall detection Database, which increased by 3.72%mAP and 5.25%mAP compared with YOLOv7 and PDD-FCOS, respectively. © 2023 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

A systematic evaluation of helicopter cabin noise:Case study of Robinson R44 RAVEN Ⅱ

引用

Chinese Journal of Aeronautics 2025年第5期 168-183页

作者： Dan YAO Jie ZHANG Ruiqian WANG Chang CHEN Yumei ZHANG Yue ZHAO Jie PANG College of Aviation Engineering Civil Aviation Flight University of China State Key Laboratory of Polymer Materials Engineering/Polymer Research Institute Sichuan University School of Mechanical Engineering and Rail Transit Changzhou University Key Laboratory of Aerodynamic Noise Control China Aerodynamics Research and Development Centre

This paper presents a comprehensive test and systematic evaluation analysis of cabin noise in the Robinson R44 RAVEN II ***,microphones were placed within the cabin to conduct systematic assessments of noise levels under various flight conditions,including takeoff,climbing,level flight,landing,hovering,***,time–frequency analysis was conducted on the test data utilizing traditional A-weighted sound pressure levels,which was followed by quantitative comparisons across different flight ***,detailed evaluation and discussion were conducted,taking into account the subjective perceptions and communication challenges of cabin crew *** assessment incorporated the use of aviation noise indicators,speech interference levels,and metrics related to sound ***,potential noise reduction measures and their effects were preliminarily *** results indicate that helicopter cabin noise exhibited variations across different flight states or positions within the same state,ranging from 87.6 d B(A) to 92.6 dB(A).Discrepancies between A-weighted sound pressure level and psychoacoustic parameters were observed,particularly during hovering states,which indicate that there is a necessity for the combination of multiple evaluation ***,damping measure can serve as a pivotal factor in mitigating cabin noise.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DMI Image Information Recognition Based on Improved YOLOv4 with Focal Loss 5

DMI Image Information Recognition Based on Improved YOLOv4 w...

引用

5th International Conference on Traffic engineering and Transportation System, ICTETS 2021

作者： He, Han Li, Kaicheng Yuan, Lei Wang, Fei National Engineering Laboratory for Urban Rail Transit Communication and Operation Control Beijing Jiaotong University Beijing100044 China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China Signal & Communication Research Institute of CARS Beijing100081 China

ISBN: (纸本)9781510649910

In the ATP function test project of train control system, the image information recognition of driver machine interface (DMI) is an important part of realizing test automation, because of the reason the real-time detection of DMI image information is very important. In the process of realizing DMI image information recognition based on machine vision, aiming at the problem of low generalization of the model caused by small amount of training data and single background of training image in machine vision system, combined with a variety of data enhancement strategies, a data set construction scheme of the system is proposed. In order to solve the problem of low attention to hard samples when using YOLOv4 model for small target detection, based on the idea of focus loss, a weighted fusion loss function of focus loss + CIoU loss is proposed, and the optimal parameters are obtained through experiments. The results show that the average accuracy of this method for DMI image information recognition is 98.76%, which is 2.6% higher than the traditional YOLOv4 detection model, and the single detection time is 76.9ms, which has a certain engineering application value. © 2021 SPIE

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Modeling ground vibration excited by a high-speed train running along a viaduct railway using a new structure-soil interaction method

引用

Science of the Total Environment 2024年 956卷 177136页

作者： He, Yuanpeng Sheng, Xiaozhen Han, Jian Zhang, Yang Xiao, Xinbiao School of Mechanical Engineering Southwest Jiaotong University Sichuan Chengdu610031 China School of Urban Railway Transportation Shanghai University of Engineering Science Shanghai201620 China Department of Civil and Environmental Engineering Hong Kong Polytechnic University Kowloon100872 Hong Kong State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong University Sichuan Chengdu610031 China

Ground vibrations generated by high-speed trains running along railways either at grade or on viaduct bridges, are greatly concerned by the railway industry. Considering the train-track-bridge-abutment-pile-soil interactions involved, modeling the problem in an analytical manner is almost impossible, while conventional numerical methods struggle to accurately simulate the dynamic properties of infinitely large soils. Therefore, this study introduces a new substructure methodology for train-track-bridge-abutment-pile-soil interactions that leverages an ingenious combination of the 2.5-dimensional finite element-boundary element method (2.5D FE-BE) for dynamics of infinitely long periodic structures, and a local 3-dimensional finite element model for pile-soil interaction. This innovative method allows for the consideration of detailed pile-soil coupling using a local finite element model, all while retaining the ability to account for the infinite size of the soil structure using the 2.5-dimensional finite element-boundary elements. After a comparison between model prediction and field measurement, the model is employed to explore the environmental vibration characteristics of on-viaduct high-speed railways and analyze the vibration reduction effects of various measures, including rail fasteners, track slab pads, and bridge bearings. © 2024

关键词： Piles

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation and Multi-Factor Optimization of Spatio-Temporal Stress Evolution in Shale Reservoir Based on Plackett-Burman and Central Composite Design

SSRN

引用

SSRN 2024年

作者： Mu, Shuxing Zhao, Lianheng Liu, Yuxuan School of Civil Engineering Central South University Hunan Province Changsha410075 China Key Laboratory of Heavy-Haul Railway Engineering Structure Ministry of Education Hunan Province Changsha410075 China Hunan Provincial Key Laboratory for Disaster Prevention and Mitigation of Rail Transit Engineering Structures Hunan Province Changsha410075 China State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation Southwest Petroleum University Sichuan Province Chengdu610500 China

Multi-factor analysis and accurate prediction of dynamic stress in shale reservoirs are of great practical significance for designing gas well fracturing. The seepage-geomechanics of reservoirs in the development of shale gas is a multi-physical and multi-scale coupling problem. In this paper, we propose a hydro-mechanical model considering geomechanical heterogeneity and multi-scale seepage mechanisms of shale gas to simulate the spatio-temporal evolution of gas well stress. The numerical model is validated by Terzaghi's theory. The Plackett-Burman method is used for sensitivity analysis to screen the significant factors affecting reservoir stress. Then, in combination with central composite design and numerical simulation, the combined effect of significant factors on reservoir stress is studied, and a mathematical model for predicting stress is established. The results indicate that the initial reservoir pressure, as well as the length and width of hydraulic fractures, are the key factors influencing reservoir stress. The proposed method is effective for predicting reservoir stress. The research results are helpful for gaining a deeper understanding of the evolution mechanism of dynamic stress fields in shale reservoirs and provide guidance for treatment design and dynamic optimization of gas wells. © 2024, The Authors. All rights reserved.

关键词： Gases

来源：评论

学校读者我要写书评

暂无评论

A Novel Sliding Mode Control for Dual Three-phase PMSM System 7

A Novel Sliding Mode Control for Dual Three-phase PMSM Syste...

引用

7th IEEE International Conference on Power and Renewable Energy, ICPRE 2022

作者： Peng, Weifa Lin, Tao Liu, Annan Chen, Yumeng Liu, Jun Xu, Xiaoling East China Jiaotong University School of Electrical and Automation Engineering Nanchang China East China Jiaotong University School of Tianyou Nanchang China East China Jiaotong University State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure Seae Nanchang China East China Jiaotong University School of Electrical and Automation Engineering Nanchang China

ISBN: (数字)9781665450638

ISBN: (纸本)9781665450638

The speed control problem of dual three-phase permanent magnet synchronous motor has the characteristics of nonlinearity, parameter perturbation and load disturbance. To solve this problem, a new sliding mode approach law is proposed. The saturation function is used to replace the sign function to suppress chattering, and the approach law is used to design a sliding mode speed controller for dual three-phase permanent magnet synchronous motor. According to the established mathematical model, the vector control model of the sliding mode speed controller based on the new approach law is established. Under three states of motor starting, steady state and sudden load, the new sliding mode approach law has less phase current impact , almost no buffeting, fast response of speed and torque, no overshoot of speed. The simulation results show that the speed controller can effectively improve the static and dynamic characteristics of the dual three-phase permanent magnet synchronous motor drive system. © 2022 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Ni Mesh-Reinforced Ultrasonic-Assisted Cu/Sn58Bi/Cu Joint Performance: Experiments and First-Principles Calculations

SSRN

引用

SSRN 2024年

作者： Huang, Xi Zhang, Liang Chen, Yu-Hao Sun, Lei Yu, Xin-Quan Lu, Quan-Bin School of Materials Science and Engineering Xiamen University of Technology Xiamen361000 China School of Mechanical Engineering and Rail Transit Changzhou University Changzhou213164 China State Key Laboratory of Advanced Brazing Filler Metals & Technology Zhengzhou Research Institute of Mechanical Engineering Co. Ltd. Zhengzhou450001 China

The Ni mesh was incorporated into the Cu/Sn58Bi/Cu bonding as a reinforcing skeleton to achieve an enhancement effect analogous to steel reinforcement in concrete. Ultrasonic-assisted soldering (UAS) improved the metallurgical bond among the solder, Ni mesh, and substrate. It facilitated the formation of (Cu, Ni)6Sn5 intermetallic compounds (IMCs) layers, increasing the joint strength. Observations indicated that ultrasonic treatment effectively refined the (Cu, Ni)6Sn5 grains and induced a uniform preferred orientation of β-Sn and Bi grains in the joint matrix adjacent to the Ni mesh. The shear strength of the joint reached 72.23 MPa when the ultrasonic application was sustained for 15 seconds, achieving the fabrication of a high-strength point with low energy consumption. First-principles calculations have confirmed that changes in the Ni content within (Cu, Ni)6Sn5 IMCs improved the stability of the crystal structure. Furthermore, the variations in content could potentially improve the mechanical and electrical properties of the (Cu, Ni)6Sn5. Enhancements in ultrasonic efficiency and the reinforcement of IMC structures offer new avenues for research in green and high-performance electronic packaging material joining technologies. © 2024, The Authors. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Event-Driven Optimization Strategy for Enhancing Piezoelectric Vibration Energy Harvesting in railway Scenarios

SSRN

引用

SSRN 2023年

作者： Qu, Shuai Ren, Yuhao Hu, Guobiao Dong, Liwei Yang, Jizhong Wu, Zaixin Zhu, Shengyang Yang, Yaowen Zhai, Wanming Train and Track Research Institute State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong University Chengdu610031 China School of Civil and Environmental Engineering Nanyang Technological University 639798 Singapore Guangzhou China Institute of Rail Transit Tongji University Shanghai201804 China China Railway Eryuan Engineering Group Co. LTD Chengdu China Sichuan Shudao New System Rail Group Co. LTD Chengdu China

This study proposes a comprehensive approach for optimizing piezoelectric energy harvesters (PEHs) in railway settings, aiming at enhancing their applicability for railway structural health monitoring (SHM) applications. Unlike conventional methods that align the fundamental frequency of the PEH with the dominant frequency of the vibration source, this study introduces and applies an event-driven optimization strategy. Our approach begins by developing a high-fidelity dynamic model of the PEH and an advanced vehicle-track coupled dynamic model. The vehicle-track interaction forces and vehicle-induced track vibrations are predicted at various train speeds, on different track structures, and over varying track irregularities. Utilizing these predicted track vibrations, we assess the energy harvesting performance of designed PEHs using the developed high-fidelity PEH dynamic model. In this study, we consider 12 distinct vehicle-track conditions, resulting in a total of 3600 sets of simulation data, each representing a specific event. We employ the particle swarm optimization (PSO) algorithm to identify optimal PEH designs for different events. To streamline the process, instead of offering one optimal solution for each event, we employ the K-means algorithm to cluster similar events. Subsequently, we choose the centroid design for each cluster as the representative to address events in that cluster. This approach allows us to use a limited number of representative PEHs to effectively address most events across different clusters. Finally, we thoroughly examine and evaluate the dynamic responses of these representative designs to demonstrate their robust performance. This study represents a pioneering exploration of PEH design optimization toward applications in rail transportation systems under diverse operational conditions. © 2023, The Authors. All rights reserved.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Spatial Variation Motion Blur Bridge Image Quality Improvement

Spatial Variation Motion Blur Bridge Image Quality Improveme...

引用

Frontiers Technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Dan Tao Suyuan Deng Guangying Qiu Dequan You Linming Wu State Key Laboratory of Rail Transit Infrastructure Performance Monitoring and Guarantee East China Jiaotong University Nanchang China School of Electrical and Automation Engineering East China Jiaotong University Nanchang China Fujian Communications Research Institute Co. Ltd. Fuzhou China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

China is a leading nation in bridge construction, with bridge infrastructure not only forming a critical part of the transportation network but also driving regional economic development. To ensure the safety and reliability of these structures, regular inspection and maintenance are required, with crack detection being particularly crucial. With technological advancements, machine vision has started to be applied in bridge health monitoring. However, due to issues such as low light, noise, and camera shake, images often exhibit motion blur, leading to the loss of key details and structural deformation, which affects the accuracy of crack detection. To address this, this paper proposes an image restoration algorithm that incorporates a strip attention mechanism, leveraging intra- and inter-strip attention blocks within the Transformer framework to handle blurs of different directions and magnitudes. Additionally, an operator is used for sharpening to reduce artifacts and noise, thereby improving the deblurring effect. Experimental results demonstrate that this algorithm effectively enhances image quality, improving the reliability of data used for bridge health management.

关键词： Bridges Image quality Strips Machine vision Noise Transportation Transformers Safety Maintenance Monitoring

来源：评论

学校读者我要写书评

暂无评论

Research on Anti-Swing Strategies for Bridge Cranes

Research on Anti-Swing Strategies for Bridge Cranes

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Shiqi Hou, Enguang Zheng, Haoyuan Jiang, Yuyi Shen, Zhen Xiong, Gang The College of Rail Transit Shandong Jiaotong University Jinan250399 China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao266144 China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China State Key Laboratory of Multimodal Artifcial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9798350368604

A study is conducted on the LH5T-13.5M electric crane, focusing on the swing characteristics of the load during steel coil lifting operations and the displacement issue of the crane. Initially, the system model is formulated using the Lagrange dynamic equations, translating the practical challenges into a solvable mathematical framework and deriving the transfer function of interest. Subsequently, the development of three control strategies is elucidated, formulated on the basis of the established model: a conventional PID control system, a fuzzy PID control system, and an adaptive proportional factor fuzzy neural PID controller. These systems are simulated and validated using Simulink. A comparative experimental setup is employed to evaluate performance. The results show that when the step input signal is 1, the maximum absolute load swing Angle of the traditional PID, fuzzy PID and adaptive scale factor fuzzy neural PID controller are 0.185°, 0.054° and 0.049° respectively for the working condition 1 experiment. The percentage overshoot corresponding to the wheelbarrow is 37.1%, 40.0%, and 30.5%, respectively. The findings indicate that the introduced fuzzy neural PID controller, equipped with an adaptive scaling factor, exhibits superior stability and effectiveness in maintaining the crane’s operation within the optimal range of parameters. © 2024 IEEE.

关键词： Bridge cranes

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：