检索结果-内蒙古大学图书馆

2021 International Conference on Advances in Optics and Computational Sciences, ICAOCS 2021

作者： Zhang, Hongyang Xiang, Weier Zhou, Kailai Xu, Lin School of Wuhan University of Technology Wuhan China Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Wuhan430070 China

This paper proposes a new control strategy based on the In-Arm Torsional Electromagnetic Active Suspension (ITEAS), which can improve the vehicle ride comfort through adjusting the damper in ITEAS to optimize the kinetic characteristics of the vehicle composed by two ITEAS systems. Firstly, the structure and principle of the new type system is introduced followed by the description of the vehicle and the damper in ITEAS. Secondly, according to theoretical mechanics and fluid mechanics, the dynamic model of ITEAS system and the hydraulic model of shock absorber are established under forced vibration. Then, the PID control simulation model of the front suspension is established in AMESIM with a passive model as reference, due to the special assemble features of the vehicle. The rear suspension adopts predictive control method and the simulation model is built in MATLAB/SIMULINK, whose theory can be summarized as adjusting the duty ratio of the valve in damper to improve the stability of the vehicle under the condition that the road surface information is already known. Lastly, this paper tests the suspension characteristics on the MTS bench, which verifies the proposed control method improves the ride comfort performance and the feasibility of predictive system. © Published under licence by IOP Publishing Ltd.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Research on driving comfort evaluation of lower limb based on muscular forces

Research on driving comfort evaluation of lower limb based o...

引用

2nd International Conference on Precision Mechanical Instruments and Measurement technology, ICPMIMT 2014

作者： Li, Zhuo Zhao, Meng Yang Zhou, Liang Wuhan University of Technology Hubei Key Laboratory of Advanced Technology for Automotive Components 122 Luoshi Road Hongshan District Wuhan 430070 China

ISBN: (纸本)9783038351948

Driving comfort is one of the most important indexes for automobile comfort evaluation. The joint torque calculation model of the lower limb in driving posture is established in the presented work firstly. The relationship between cab layout parameters and the joint torque can be obtained through dynamical simulation in the MATLAB by employing Kane method. A new method based on muscular forces is proposed to evaluate the automobile comfortableness. The force of each muscle can be obtained by employing static optimization algorithm of inverse dynamics. The impact of cab layout parameters, joint torque and the muscular forces on driving comfort and the relationship between them can be found through the analysis. As an reference, these parameters can be used to optimize the cab and offer an important support for its optimization. © (2014) Trans Tech Publications, Switzerland.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

3D Object Detection Based on Local Feature Fusion 5

3D Object Detection Based on Local Feature Fusion

引用

5th International Conference on Mechatronics and Computer technology Engineering, MCTE 2022

作者： Liu, Jianguo Liao, Xinjia Yan, Fuwu Zhang, Rui Chen, Yingzhi Wu, Youhua Sun, Yunfei Hu, Dafeng Chen, Nuo Foshan XianHu Laboratory Guangdong Foshan China Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Hubei Wuhan China Collaborative Innovation Center for Automotive Components Technology Hubei Wuhan China Research Center for New Energy & Intelligent Connected Vehicle Hubei Wuhan China Ningbo Huade Automobile Parts Co. Ltd Zhejiang Ningbo China Ningbo Huake Automobile Parts Co. LTD Zhejiang Ningbo China

ISBN: (纸本)9781510661073

The existing 3D object detection networks based on the cross-attention mechanism from the bird's-eye view perspective mostly use the parameters calibrated by the camera to take the features corresponding to project each 3D feature point from the front view feature by projecting the 3D point onto the two-dimensional image. The features obtained by this method are affected by the calibration parameters and the projection position. To reduce the influence of the camera calibration parameters and the accuracy of the projection position on the obtained features, a local feature fusion network is proposed, which fuses the features within a certain range near the projection point to represent the corresponding features of the 3D point, thus improving the feature representation capability. The experimental results on the nuScenes val set show that the NDS value is increased by 1.4% compared with the benchmark. In addition, the network has robustness. Under the same noise, its accuracy reduction rate is reduced by more than 56% compared with the benchmark and has a practical value in automatic driving. © 2022 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

RGB and LiDAR Fusion-based 3D Semantic Segmentation for Autonomous Driving 4

RGB and LiDAR Fusion-based 3D Semantic Segmentation for Auto...

引用

2023 4th International Conference on Internet of Things, Artificial Intelligence and Mechanical Automation, IoTAIMA 2023

作者： Liu, Jianguo Jia, Zhiling Li, Gongbo Yan, Fuwu Wu, Youhua Sun, Yunfei Foshan Xianhu Laboratory The Advanced Energy Science and Technology Guangdong Laboratory Guangdong Foshan528200 China Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Wuhan430070 China Ningbo Huade Automobile Parts Co. Ltd. Zhejiang Ningbo315000 China

Projection-based multimodal 3D semantic segmentation methods suffer from information loss during the point cloud projection process. This issue becomes more prominent for small objects. Moreover, the alignment of sparse target features with the corresponding object features in the camera image during the fusion process is inaccurate, leading to low segmentation accuracy for small objects. Therefore, we propose an attention-based multimodal feature alignment and fusion network module. This module aggregates features in spatial directions and generates attention matrices. Through this transformation, the module could capture remote dependencies of features in one spatial direction. This helps our network precisely locate objects and establish relationships between similar features. It enables the adaptive alignment of sparse target features with the corresponding object features in the camera image, resulting in a better fusion of the two modalities. We validate our method on the nuScenes-lidar seg dataset. Our CAFNet achieves an improvement in segmentation accuracy for small objects with fewer points compared to the baseline network, such as bicycles (6% improvement), pedestrians (2.1% improvement), and traffic cones (0.9% improvement). © Published under licence by IOP Publishing Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimization of Baja Racing Car Frame Based on GA/MOGA/SA Algorithm and Experimental Research on Bending-Torsional Stiffness of Frame 4

Optimization of Baja Racing Car Frame Based on GA/MOGA/SA Al...

引用

4th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2022

作者： Tian, Zhewen Tang, Yun Ning, Xinfei Fan, Mingxin Zhang, Ping Zhang, Xiaosong Hubei Key Laboratory of Advanced Technology for Automotive Components Hubei Collaborative Innovation Center for Automotive Components Technology University of Technology Wuhan430070 China Hubei Research Center for New Energy and Intelligent Connected Vehicle Wuhan University of Technology Wuhan430070 China Wuhan Shen Dong Automobile Electronic and Equipment Co. Ltd Wuhan430070 China

ISBN: (纸本)9781450398343

In order to realize the lightweight design of the Baja racing car, this paper takes the Baja frame as the research object, and establishes a CATIA frame model, taking three working conditions of bending, torsion, and the combination of extreme braking and steering as examples. The strength and stiffness of the frame are analyzed in ANSYS, and the simulation shows that the safety factor of the frame is low. The total weight of the frame is 29.718kg, and there is still room for optimization. Then, under two typical working conditions, the bending and torsional rigidity test of the frame was carried out, and the difference between the test result and the simulation was less than 10%, which verified the accuracy of the frame model. Finally, with the frame quality as the optimization goal, the frame optimization function is established by using the sub-objective multiplication and division method, and the steel tube wall thickness of the frame is optimized by using the Genetic Algorithm (GA), Simulated Algorithm (SA), and Multi Objective Genetic Algorithm (MOGA).Then calculated the optimized frame quality. The results show that the optimization effect of the MOGA algorithm is the best, and the optimized mass is reduced by 26.59%. This research can provide an effective idea for the lightweight design of the racing car frame. © 2022 ACM.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor fusion 3D object detection based on channel attention 9

Multi-sensor fusion 3D object detection based on channel att...

引用

9th International Symposium on Sensors, Mechatronics, and Automation System, ISSMAS 2023

作者： Liu, Jianguo Li, Gongbo Jia, Zhiling Yan, Fuwu Hu, Jie Wu, Youhua Sun, Yunfei Foshan Xianhu Laboratory of the Advanced Energy Science and Technology Guangdong Laboratory Foshan528200 China Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Wuhan430070 China Hubei Collaborative Innovation Center for Automotive Components Technology Wuhan430070 China Hubei Research Center for New Energy & Intelligent Connected Vehicle Wuhan430070 China Ningbo Huade Automobile Parts Co. Ltd Zhejiang Ningbo315000 China

ISBN: (纸本)9781510672802

The existing 3D target detection network based on feature layer fusion of multi-view images and lidar point cloud fusion is mostly fused by directly splicing the multi-sensor features output by the backbone or the BEV features under the unified perspective of the two modalities. The features obtained by this method will be affected by the original data feature modality conversion and multi-sensor feature fusion's effect. Aiming at this problem, a 3D object detection network based on feature fusion based on channel attention is proposed to improve the feature aggregation ability of BEV feature fusion, thereby improving the representation ability of the fused features. The experimental results on the nuScenes open source dataset show that compared with the baseline network, the overall feature grasp of the object is increased, and the average orientation error and average speed error are reduced by 4.9% and 4.0%, respectively. In the process of automatic driving, It can improve the vehicle's ability to perceive moving obstacles on the road, which has certain practical value. © 2024 SPIE.

关键词： Object detection Feature fusion Point clouds Cameras Image fusion LIDAR Head Matrices Feature extraction Network architectures

来源：评论

学校读者我要写书评

暂无评论

Microstructure and texture evolution of nonoriented silicon steel during the punching process

引用

International Journal of Minerals,Metallurgy and Materials 2022年第11期29卷 2064-2071页

作者： Xiang Fang Wei Wang François Brisset Anne-Laure Helbert Thierry Baudin School of Automotive Engineering Wuhan University of TechnologyWuhan 430070China Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of TechnologyWuhan 430070China Hubei Collaborative Innovation Center for Automotive Components Technology Wuhan University of TechnologyWuhan 430070China Hubei Research Center for New Energy&Intelligent Connected Vehicle Wuhan University of TechnologyWuhan 430070China Institut de Chimie Moléculaire et des Matériaux d’Orsay UniversitéParis-SaclayCNRS91405 OrsayFrance

The iron core of a motor is mainly manufactured from rolled nonoriented silicon steel using a punching process that leads to deformation and texture evolution at the cutting *** to this process,circular samples of nonoriented silicon steel were prepared by punching using blunt punch *** this work,two positions along the rolling and transverse directions at the cutting edge were *** main mechanisms of deformation for both positions are dislocation slip and formation of shear *** two mechanisms lead to similar texture evolutions for both *** dislocation slip leads to the formation of the{221}component in the unbending area(200μm away from the cutting edge)and intermediate continuum-bent ***,the evolution of the texture from the{111}γfiber to the{110}fiber was observed at the extremity of the cutting edge with the formation of shear bands.

关键词： microstructure texture nonoriented silicon steel punching

来源：评论

学校读者我要写书评

暂无评论

The Study of Vehicle Bumper Crash Characteristics

The Study of Vehicle Bumper Crash Characteristics

引用

2015 Joint International Mechanical,Electronic and Information technology Conference(JIMET 2015)

作者： Qiao Weigao Zuo Yishun Tu Jinjin Li Yuan Hubei Collaborative Innovation Center for Automotive Components Technology Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology School of Automotive Engineering Wuhan University of Technology Huaxia College

ISBN: (纸本)9781510817982

With the mass production of cars and utilities, the incidence of car accidents is increasing, while the case of car accidents in a variety,collision probability is highest. The theory of the explicit nonlinear finite element which is adopted in the crash simulation is expounded. According to the European regulation of ECE-R42, a finite element model of low-speed crash between car bumper system and pendulum are established. The stress and strain contours, the displacement of node which on the deformation parts of bumper beam, the amount of compression of crash box and the process of energy conversion, etc. In the simulation results are objectively and deeply analyzed through Hyper View. Finally, the paper discusses the influence factors on collision characteristics, such as the section shape, thickness and material properties of bumper beam.

关键词： Car bumper collision explicit nonlinear finite element LS-DYNA

来源：评论

学校读者我要写书评

暂无评论

Simulation of dynamic characteristics of suspension hydraulic bushing 4

Simulation of dynamic characteristics of suspension hydrauli...

引用

2022 4th International Conference on Mechanical Engineering and Automation, MEA 2022

作者： Zha, Wenjing Lu, Chihua Liu, Zhien Li, Guohong Luo, Jinliang Hubei Key Laboratory of Advanced Technology for Automotive Components Wuhan University of Technology Hubei Wuhan430070 China Shiyan Dongsen Automotive Seals Co. Ltd. Hubei Shiyan442012 China Hubei Collaborative Innovation Center for Automotive Components Technology Hubei Wuhan430070 China

The hydraulic bushing is a common vibration isolator, and its dynamic characteristics influence the ride comfort of the vehicle. Aiming at a suspension hydraulic bushing with inertia components, a one-dimensional model of the hydraulic bushing is established based on Amesim. Secondly, a parameter identification method is proposed, and the equivalent piston area of the hydraulic bushing and the diaphragm strain stiffness are identified by this method. Finally, the identified parameters are input into the Amesim model, and the data results are compared with the experimental results after processing with MatLab. The results show that the dynamic characteristic curve of the hydraulic bushing calculated by this method is consistent with the test curve and can well predict the dynamic characteristics of the hydraulic bushing with inertia elements. © 2023 Institute of Physics Publishing. All rights reserved.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Detailed characteristic comparison between PEN of planar SOFC prepared by APS and SPS

Detailed characteristic comparison between PEN of planar SOF...

引用

3rd International Conference on Energy and Environmental Protection, ICEEP 2014

作者： Yang, Yun Zhen Xia, Wei Sheng Hubei Key Laboratory of Advanced Technology of Automobile parts Wuhan University of Technology Wuhan 430070 China State Key Laboratory of Materials Processing and Die and Mould Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9783038351344

On the help of the atmosphere plasma spraying (APS) and suspension plasma spraying (SPS) conditions optimized previously, APS and SPS were both introduced to prepare the PEN (Positive- Electrolyte-Negative) of planar solid oxide fuel cells (SOFCs). Then the microstructure and material components of the PEN cells were analyzed. Experimental results show that the electrolyte layer fabricated by SPS represents higher densification, thinner thickness and more homogeneous component distribution than that manufactured by APS, and meets the microstructure and density requirements of SOFC. The porosities of cathode and anode layers by APS and SPS reached 25%-35%. Therefore, the SPS could be a better and suitable approach to fabricate PENs of SOFC stacks, and effectively improve the conductivity of electrodes. © (2014) Trans Tech Publications, Switzerland.

关键词： Plasma spraying

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：