检索结果-内蒙古大学图书馆

Sensing, measurement & Data Analytics in the era of Artificial Intelligence (ICSMD), International Conference on

作者： Sirui Chen Shiji Wang Wenke Chen Baohua Li Jiaqing Qiao School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Beijing Aerospace Measurement and Control Technology Co. Ltd Beijing China

ISBN: (数字)9798331529192

ISBN: (纸本)9798331529208

As the functions of automobiles continue to increase and become more intelligent, the data exchange and communication between onboard electronic devices have become increasingly important. To ensure the reliability and stability of these systems in practical applications, it is necessary to manually simulate the testing and verification of ECUs with erroneous bus data packets. This paper designs a vehicular bus signal simulation device that can simulate the generation of CAN, LIN, FlexRay, CXPI, and SENT bus signals and their fault data packets. The hardware part of the device consists of an arbitrary waveform generator and an upper computer, while the software part uses QT to design the user interface and C++ to write the programmable software. Finally, experiments have verified the performance and accuracy of the simulation device. The waveforms captured by the digital storage oscilloscope are consistent with the expected input parameters, proving the effectiveness of the device. This device has significant application value in the development, teaching, and training of automotive electronic systems, capable of reducing the reliance on real-vehicle testing, and reducing test costs and time.

关键词： Performance evaluation Accuracy Oscilloscopes Automotive electronics User interfaces Signal generators Software Hardware Digital storage Testing

来源：评论

学校读者我要写书评

暂无评论

Real-Time Scheduling Strategy of Electric Vehicle Load Aggregation Quotient Based on Incentive and Price of Demand Response 37th

Real-Time Scheduling Strategy of Electric Vehicle Load Aggre...

引用

37th Annual Conference on Power System and Automation in Chinese Universities, CUS-EPSA 2022

作者： Shao, Bowei Wang, Hui Wang, He Li, Wenliang Jilin Institute of Chemical Technology Jilin City China Changchun Institute of Technology Changchun China Control and Safe Operation National and Local Joint Engineering Research Center for Intelligent Distribution Network Measurement Beijing130012 China State Grid Jilin Marketing Service Center Jilin City China

ISBN: (纸本)9789819914388

With the increase in the number of electric vehicles (EVs) connected to the power grid and the continuous increase in battery capacity, the disorderly charging of EVs will bring enormous pressure to the power grid, and even affect the operation of the power grid. Combining incentive-based and price-based demand response measures, this paper proposes two load poly and commercial (LPC) scheduling strategies for EVs: incentive-based electricity pricing and dynamic electricity pricing. First, according to different scheduling strategies, optimization is carried out for different EV groups. Second, the demand response measures are used as the dispatching channel between the load aggregator and the EV, and the load aggregator scheduling model is established with the goal of maximizing the net income of the load aggregator and balancing the load fluctuation. Simulation and verification are carried out through a numerical example, and the results show that compared with the traditional disordered charging mode, the scheduling strategy proposed in this paper can effectively improve the net income of the load aggregator while reducing the load fluctuation. © 2023, State Grid Electric Power.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Multiclass Classification of Remote Sensing Images Using Deep Learning Techniques

Multiclass Classification of Remote Sensing Images Using Dee...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Tahir Arshad Zhang Junping Qingyan Wang School of Electronics and Information Engineering Harbin Institute of Technology China School of Measurement-Control and Communication Engineering Harbin University of Science and Technology

Deep learning has strong learning ability to extract the features from Image datasets. In recent years, deep networks especially deep convolutional neural networks have revolutionized this field. When exposed to a huge number of datasets and their labels, deep learning techniques like Convolutional Neural Networks (CNNs) can produce precise categorization results. However, employing CNNs with scant labeled data might have a number of issues, including the problem of heavy overfitting. Convolutional Neural Networks are the backbone of modern deep learning architectures for the purpose of image classification. We solved image classification problem with different architectures and compare their performances. The objective of this work lies in the approach to study the given datasets. We use domain adaptation approach to highlight the underlying characteristics of these datasets and the different parameters (activation function, weights, regularization, neural simulation etc.) associated with these architectures. In our work, we use three datasets—RS19, UC Merced, and EuroSat images—were utilized in the CNN implementation to training the suggested model. The obtained results effectively demonstrate the local representation capacity of CNNs. Furthermore, this work shows that transfer learning improves classification outcomes in optical remote sensing images, particularly when the training sample is small.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heat transfer of copper mesh-powder composite-based sintered-wick vapor chamber

Heat transfer of copper mesh-powder composite-based sintered...

引用

作者： Zhao, Zhengang Li, Lei Wang, Yuyuan Wang, Yaxin Hui, Yueyao Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Green Energy Electric Power Measurement Digitalization Control and Protection Kunming650500 China Yunnan Institute of Measuring and Testing Technology Kunming650228 China

With the rapid spread of high-power density equipment, the vapor chamber must adapt to more applicable environments and exhibit a better heat transfer performance. The copper mesh and powder are sintered in this work to make a composite wick vapor chamber (CW-VC). Six sections of copper wire are cut and sintered together with the wick as the inner support column of the CW-VC. The effects of filling ratio and inclination on the heat transfer performance of the vapor chamber are investigated. The experimental results showed that the maximum thermal power of the CW-VC is 23.29 W at the optimal liquid filling ratio of 80% and the lowest thermal resistance is 0.33 °C/W. Below the liquid filling ratio of 60%, when the inclination angle of the CW-VC increases, its thermal resistance increases. At filling ratios of 70%, 80%, and 90%, the inclination angle of 30° can reduce the thermal resistance of the CW-VC. It implies that the inclination angle of the CW-VC can be increased appropriately to reduce the thermal resistance when the filling ratio is high. However, when the liquid filling ratio is low, increasing the inclination angle of the CW-VC will make the liquid film of the evaporator thinner and dry out earlier and its thermal resistance will increase. © 2023 Author(s).

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

LIFTEDCL: LIFTING CONTRASTIVE LEARNING FOR HUMAN-CENTRIC PERCEPTION 11

LIFTEDCL: LIFTING CONTRASTIVE LEARNING FOR HUMAN-CENTRIC PER...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Chen, Ziwei Li, Qiang Wang, Xiaofeng Yang, Wankou School of Automation Southeast University China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Y-tech Kuaishou Technology China Institute of Automation Chinese Academy of Sciences China

Human-centric perception targets for understanding human body pose, shape and ***-training the model on large-scale datasets and fine-tuning it on specific tasks has become a well-established paradigm in human-centric ***, self-supervised learning methods have re-investigated contrastive learning to achieve superior performance on various downstream *** handling human-centric perception, there still remains untapped potential since 3D human structure information is neglected during the task-agnostic *** this paper, we propose the Lifting Contrastive Learning (LiftedCL) to obtain 3D-aware human-centric representations which absorb 3D human structure *** particular, to induce the learning process, a set of 3D skeletons is randomly sampled by resorting to 3D human kinematic *** this set of generic 3D samples, 3D human structure information can be learned into 3D-aware representations through adversarial *** results demonstrate that LiftedCL outperforms state-of-the-art self-supervised methods on four human-centric downstream tasks, including 2D and 3D human pose estimation (0.4% mAP and 1.8 mm MPJPE improvement on COCO 2D pose estimation and Human3.6M 3D pose estimation), human shape recovery and human parsing. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Camera Parameter Calibration Based on the Correction of Center Positioning Deviation in Machine Vision 12th

Camera Parameter Calibration Based on the Correction of Cent...

引用

12th International Workshop of Advanced Manufacturing and Automation, IWAMA 2022

作者： Zhang, Guiyang Wu, Jian Zhu, Lingyu Wang, Jing Yuan, Qian School of Mechanical Engineering Changshu Institute of Technology Suzhou215500 China Optical Measurement Center Suzhou TZTEK Technology Company Limited Suzhou215153 China Key Laboratory of Elevator Intelligent Safety in Universities of Jiangsu Province Suzhou215500 China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin150001 China School of Electronics and Control Engineering Changan University Changan710064 China

ISBN: (纸本)9789811993374

This study primarily investigates the blurred edge and eccentricity of spatial circular projection problem whilst the stereo vision system uses circular feature points to calibrate. The high-precision positioning of the circle center is carried out by eccentric error correction to improve the calibration accuracy of the camera parameters. Firstly, the high-precision pixel coordinate positioning of the circle edge is realized by the Zernike moment of the projected image, and then the influencing factors of the deviation between the projected ellipse center and the projection of the real center of the space circle are analyzed. Moreover, the deviation of the fitted circle center is compensated to make it approach the real circle center projection. Lastly, the proposed strategy is utilized to extract the center of the 99-circle calibration plate and adopt it for camera parameter calibration. According to the experiment results, the precision of the circle center fitting is higher than that of the traditional algorithms and the three-dimensional reconstruction accuracy of the camera calibration parameters is improved, which implies that the proposed approach should therefore have potential for practical application prospects. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Fine-graded image classification network based on Faster MMAL-Net 2

Fine-graded image classification network based on Faster MMA...

引用

2nd International Conference on Electronic Information engineering and Computer Communication, EIECC 2022

作者： Han, Ke Ji, Xiu Xie, Beimin Wang, Yong Gao, Shuai State Grid Jilin Power Supply Company UHV Branch State Grid Jilin Electric PowerSupply Company China Jilin Institute of Chemical Technology National Local Joint Engineering Research Center for Smart Distribution Grid Measurement and Control with Safety Operation Technology China

ISBN: (纸本)9781510663121

In the fine-grained image classification task, the huge intra class variance determines that the classification of the task depends on coarse-grained and fine-grained information. However, there is still a lack of research on how to quickly and effectively fuse multi granularity features. Therefore, this paper proposes a fine-grained image classification network based on fast MMAL net, and studies the impact on the classification accuracy and convergence speed of fine-grained classification network. The fast aolm module is used to predict the position of the object, and the fast APPM module is used to predict the information of the key areas of the object without the need for bounding boxes or labels. The method proposed in this paper achieves high accuracy on the three data sets of Stanford cars cub-200-2011, fgvc aircraft and Stanford cars respectively, which shows that this method can obtain excellent classification performance. © 2023 SPIE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Optimization of electrode of a right-angled electromagnetic flowmeter using CFD simulation 19

Optimization of electrode of a right-angled electromagnetic ...

引用

19th International Flow measurement Conference 2022, FLOMEKO 2022

作者： Chen, Weijie Xu, Haohao Tu, Chengxu Li, Xianfeng Gao, Wenkun Zhang, Jianli Li, Xiang Bao, Fubing Zhejiang Energy Technology Research Institute Co. Ltd Hangzhou Hangzhou310018 China Zhejiang Provincial Key Laboratory of Flow Measurement Technology College of Metrology and Measurement Engineering China Jiliang University Hangzhou China Shanghai Tianshi Measurement & Control Equipment Co. Ltd Shanghai China

ISBN: (纸本)9781713871989

Currently, electromagnetic flowmeters must typically be inserted into a straight pipe, which usually requires a larger installation space. To improve installation adaptability, a novel right-angled electromagnetic flowmeter is proposed. As the measurement signal of the electromagnetic flowmeter is closely related to the flow state of its internal fluid, a large-eddy simulation (LES) was used to study the influence of the shape of the electrode and the contraction section of the flowmeter on the flow characteristics inside the flowmeter to reveal the relationship between them along with the measurement accuracy. A comparison between the numerical results and the experimental results was also performed. The velocity fluctuations of the monitoring points around the cone and flat electrodes were compared, and it was found that the overall measurement error of the cone electrodes was smaller than that of the flat electrodes. The experimental results showed that the pulsation of the voltage signal measured from the cone electrode is smaller than that of the flat electrode. In addition, the absolute value of the error in the small flowrate is much smaller than that of the flat electrode. Consequently, the measurement performance of the cone electrode is better. In addition, the largest velocity fluctuation occurred between the electrode wall and tube wall, indicating that installing the coil should avoid exciting strong magnetic fields here. © FLOMEKO *** rights reserved

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Mobilenetv2-SSD Target Detection Method Based on Multi-scale Feature Fusion 8th

Mobilenetv2-SSD Target Detection Method Based on Multi-scale...

引用

8th International Conference on Cognitive Systems and Information Processing, ICCSIP 2023

作者： Li, Boao Jiang, Du Tang, Xinjie Sun, Ying Weng, Yaoqing Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China Hubei Longzhong Laboratory Hubei Xiangyang441000 China

ISBN: (纸本)9789819980208

Most of the deep learning networks used in target detection algorithms are very complex, which poses difficulties for edge devices with limited storage capacity and computing power, such as mobile terminals. A MobileNetv2-SSD target detection algorithm based on multi-scale feature fusion is proposed in this paper. We use MobileNetv2 to improve the SSD algorithm by replacing the original network’s backbone network VGG16 with the lightweight network MobileNetv2 to perform the model streamlining. The problem of accuracy loss due to model compression is improved by the designed feature fusion module and finally tested on the dataset. The experimental results show that the mAP and FPS are 90.37% and 50FPS, respectively, and the detection accuracy is improved by 3.24% compared with the original SSD network, the detection speed is 1.9 times of the original one, and the size of the model is only 28.5M, which is only 30.5% of the original model. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Temperature and strain sensitivities of surface and hybrid acoustic wave Brillouin scattering in optical microfibers

引用

Chinese Physics B 2022年第9期31卷 333-339页

作者： Yi Liu Yuanqi Gu Yu Ning Pengfei Chen Yao Yao Yajun You Wenjun He Xiujian Chou Taiyuan University of Technology Key Laboratory of Advanced Transducers and Intelligent Control SystemMinistry of Education and Shanxi ProvinceTaiyuan 030024China Taiyuan University of Technology Institute of Optoelectronic EngineeringCollege of Physics and OptoelectronicsTaiyuan 030024China Strong Digital Technology Co. Ltd.(Thinvent)Nanchang 410000China North University of China Key Laboratory of Instrumentation Science and Dynamic Measurement Ministry of EducationTaiyuan 030051China North University of China College of Mechatronics EngineeringTaiyuan 030051China North University of China Science and Technology on Electronic Test and Measurement LaboratorySchool of Instrument and ElectronicsTaiyuan 030051China

Temperature and strain sensitivities of surface acoustic wave(SAW)and hybrid acoustic wave(HAW)Brillouin scat-tering(BS)in 1μm-1.3μm diameter optical microfibers are *** contrast to stimulated Brillouin scattering(SBS)from bulk acoustic wave in standard optical fiber,SAW and HAW BS,due to SAWs and HAWs induced by the coupling of longitudinal and shear waves and propagating along the surface and core of microfiber respectively,facilitate innovative detection in optical microfibers *** highest temperature and strain sensitivities of the hybrid acoustic modes(HAMs)are 1.082 MHz/℃and 0.0289 MHz/με,respectively,which is suitable for microfiber sensing applica-tion of high temperature and strain ***,the temperature and strain sensitivities of the SAMs are less affected by fiber diameter changes,ranging from 0.05 MHz/℃/μm to 0.25 MHz/℃/μm and 1×10^(-4) MHz/με/μm to 5×10^(-4) MHz/με/μm,*** can be found that that SAW BS for temperature and strain sensing would put less stress on manufacturing constraints for optical ***,the simultaneous sensing of temperature and strain can be realized by SAW and HAW BS,with temperature and strain errors as low as 0.30℃-0.34℃and 14.47με-16.25με.

关键词： Brllouin scatering surface acoustic waves hybrid acoustic waves optical microfiber sensing

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：