检索结果-内蒙古大学图书馆

IEEE Information technology, Networking, electronic and Automation Control Conference

作者： Mingzhi Zhu Di Wu Binbin Xu Shunhua Cao Jie Cao Kaiwei Wang Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen China College of Civil and Transportation Engineering Shenzhen University Shenzhen China College of Economics Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Electronic Information Products Reliability Technology Guangzhou China China Electronic Product Reliability and Environmental Testing Research Institute GuangZhou China

ISBN: (数字)9798350370805

ISBN: (纸本)9798350370812

Applying advanced image processing and deep learning techniques to the segmentation and recognition of oracle bone inscriptions can help accelerate the research process and improve the efficiency of cultural relic protection and historical and cultural research. Firstly, mathematical morphology methods are used to denoise the original oracle bone rubbings, which can better identify and process interfering elements. Subsequently, by applying one of the most advanced visual algorithm models, YOLOv8, to image recognition and segmentation of raw oracle bone rubbings, the recognition and segmentation tasks can be quickly and accurately completed. Finally, an improved ConvNeXt, which represents the most advanced convolutional neural network, was firstly applied to the classification experiment of oracle bone character images, achieving a validation accuracy of 94.5%. Through the aforementioned steps, a complete and effective method for pre-processing, image recognition, image segmentation, and image classification of oracle bone inscriptions is constructed in this paper.

关键词： Fault diagnosis Deep learning Image segmentation Visualization Image recognition Accuracy Morphology Bones Mathematical models Image classification

来源：评论

学校读者我要写书评

暂无评论

Fault Analysis of Bearings in Various States Based on Continuous Wavelet and Improved Residual Network

Fault Analysis of Bearings in Various States Based on Contin...

引用

electronic Information technology and Smart Agriculture (ICEITSA), International Conference on

作者： Qingnan Wang Jihui Tu School of Intelligent Manufacturing Huaihua University Key Laboratory of Intelligent Control Technology for Wuling Mountain Ecological Agriculture Hunan Province Huaihua China School of Electronic and Information Yangtze University Jingzhou China

ISBN: (纸本)9781665464024

The bearing fault signals are complex and difficult to collect, which leads to a limited number of fault samples, and it is difficult to analyze the changeable bearing faults with conventional methods. In this paper, an automatic signal feature extraction method by improved residual network and wavelet transform is presented, which is suitable for bearing fault analysis in various states. Continuous wavelet transform (CWT) can obtain enough time-frequency images by superposing the original vibration signals. Improve the residual network, increase the attention mechanism and better deal with complex features. Transfer learning is applied to various working states, and the common features of bearing faults concealment are extracted and learned, so as to improve the applicability of diagnosis. The prediction ability of the bearing is tested in various working states, which proves the applicability of our fault analysis method. The problem of low accuracy of small sample identification caused by lack of actual fault data is solved.

关键词： Vibrations Fault diagnosis Time-frequency analysis Continuous wavelet transforms Convolution Transfer learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Cross-Component Transferable Transformer Pipeline Obeying Dynamic Seesaw for Rotating Machinery with Imbalanced Data

SSRN

引用

SSRN 2023年

作者： Xu, Binbin Ma, Boquan Yang, Zheng Chen, Fei Li, Xiaobing Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen518118 China School of Mechanical and Aerospace Engineering Jilin University Changchun130025 China Guangdong Provincial Key Laboratory of Electronic Information Products Reliability Technology Guangzhou511370 China

Due to the lack of fault data in the daily work of rotating machinery components, existing data-driven fault diagnosis procedures cannot accurately diagnose fault classes and are difficult to apply to most components. At the same time, the complex and variable working conditions of components pose a challenge to the feature extraction capability of the models. Therefore, this work proposes a novel hierarchical window transformer model that obeys a dynamic seesaw (HWT-SS), and a creative strategy of transfer diagnosis between multiple rotating mechanical components combined with transfer learning is proposed. A transferable pipeline is constructed to solve the fault diagnosis of multiple components in the presence of imbalanced data. The advantages of the proposed model are validated using four datasets with different imbalance ratios, including two bearing datasets, one gearbox dataset and one motor dataset. The comparison with the benchmark models proves that the proposed model has the advantages of strong feature extraction capability and low influence of imbalanced data. The transfer tests between datasets and the visual interpretation of the model prove that the transfer diagnosis between components can further improve the diagnostic capability of the model for extremely imbalanced data. © 2023, The Authors. All rights reserved.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive position tracking control of the lower limb exoskeleton robot with an uncertain dynamic model 18

Adaptive position tracking control of the lower limb exoskel...

引用

18th IEEE Conference on Industrial electronics and Applications, ICIEA 2023

作者： Yuan, Ting Zhang, Chi Yi, Feng Lv, Pingping Li, Shupei Zhang, Meitong Ningbo University Ningbo Instituteof Materials Technology and Engineering Chinese Academy of Sciences Faculty of Electrical Engineering and Computer Science Ningbo315201 China Chinese Academy of Sciences Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Ningbo Institute of Materials Technology and Engineering Ningbo315201 China University of Chinese Academy of Sciences Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences College of Materials Science and Opto-Electronic Technology Ningbo315201 China Hebei University of Science and Technology Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences School of Electrical Engineering Ningbo315201 China

ISBN: (纸本)9798350312201

In this paper, an adaptive position control method combining proportional-derivative (PD) control, RBF neural network-based sliding mode (SM) control, and feedforward (FF) control, i.e., PD-FF-SM control, is proposed to deal with the dynamic uncertainties, disturbances, and slow response in lower limb exoskeleton robot system. The Lagrange method is utilized to establish dynamic models that ignore the uncertainties and disturbances in the swing phase and supporting phase. Then, the PD feedback controller is designed with a sliding surface function, to keep the system stable. The FF controller is adopted to improve the response by using dynamic models. And the RBF neural network-based SM controller is designed to compensate for the uncertainties and disturbances. The system's stability is verified by Lyapunov's theorem. The simulation results show that the proposed control method can effectively reduce the error of position tracking and response time with inaccurate dynamic modeling. © 2023 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Modeling, simulation and experiment of an origami robot with a coupled bar-hinge mechanism

Modeling, simulation and experiment of an origami robot with...

引用

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Junpeng Mai Hanzhao Shao Shaojie Liu Yuanzhuo Zhang Liangming Chen Huijuan Feng School of System Design and Intelligent Manufacturing and Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern University of Science and Technology Shenzhen P. R. China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen P. R. China Department of Mechnical and Energy Engineering Southern University of Science and Technology Shenzhen P. R. China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

This paper aims to analyze the motion behavior of an origami robot with a coupled bar-hinge mechanism. By disassembling the planar six-hinge mechanism into two planar four-hinge mechanisms with coupled motion, this paper derives the kinematics of the planar six-hinge mechanism based on the algebraic differential kinematics of the planar four-hinge motions. The rotational angle change and the moving step length of the origami robot are further calculated. Finally, the theoretical motion model is verified with the motion simulation data of the planar six-hinge mechanism origami robot in SolidWorks and the experimental data of the physical model. This verification proves the feasibility of the theoretical analysis, simulation model, and physical model.

关键词： Solid modeling Analytical models Prototypes Kinematics Three-dimensional printing Mathematical models Data models

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Model Engineering Environment Integration Based on OpenMBEE 21st

Research and Implementation of Model Engineering Environment...

引用

21st Asia Simulation Conference, AsiaSim 2022

作者： Xue, Junjie Zhou, Junhua Shi, Guoqiang Feng, Chaoqun Xu, Lin Liu, Penghua Quan, Hongyan Engineering Research Center Beijing Simulation Center Beijing100854 China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing100854 China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing100854 China Yunnan Chensheng Tendering Consulting Co. Ltd. Kuming650102 China School of Computer Science and Technology East China Normal University Shanghai200062 China

ISBN: (纸本)9789811991974

Aiming at the problem of integrating open tools in a user development environment in complex product design, an integration strategy of model engineering environment based on OpenMBEE is studied. It is based on the technologies of user identity unified authentication and user interaction data collaboration. Specifically, in the solution of unified identity authentication on cross-platform, the extended controller method is provided based on the message queue information flow mechanism. Then, the separation of business logic, data information, and interactive view of user unified authentication are realized, on the basis, that the function of unified identity authentication is realized by using the Software Development Kit (SDK) of OpenMBEE. Besides, in the study of user interaction data collaboration technology, three-layer collaboration mechanisms are proposed, they are the presentation layer collaboration, the business layer collaboration, and the persistence layer collaboration. When the jQuery programming framework is integrated into the bootstrap front-end framework, combing with the OpenMBEE back-end server interface, the collaboration of user interaction data is realized. Through experiments and project practice analysis, the user unified authentication strategy and user interactive collaboration strategy are tested respectively for proving the effectiveness and feasibility of the proposed method. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Precision Control technology and Device for Miniature Bearing Assembly

Precision Control Technology and Device for Miniature Bearin...

引用

2021 International Conference on Mechanical Engineering, intelligent manufacturing and Automation technology, MEMAT 2021

作者： Li, Yingang Li, Fei Pu, Yang Zhu, Haitian Ma, Guocai Jin, Xin School of Mechanical Engineering Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing China Beijing Shiny Tech. Co. Ltd Beijing China

The traditional assembly equipment of tension link components has a degree of automation and few types of equipment, which have a greater impact on the assembly quality, assembly accuracy, and assembly efficiency of the linkage mechanism. This article firstly combines the current assembly status of the tension connecting rod components in my country and proposes a high-precision press-fitting method for connecting rods with continuous clamping, alignment, press-fitting, and pre-tightening actions. Secondly, an assembly platform for high-precision automatic press-fitting of tension connecting rods was developed and designed, and the structure design of the high-precision tension connecting rod press-fitting platform and the working principle of each module were explained, including a non-destructive clamping mechanism, a two-degree-of-freedom macro-motion platform, and vision alignment module, and other designs. Then through the assembly force experiment, the distribution of the bearing press-fitting force is obtained. The platform can increase the assembly coaxially of the 10mm inner bearing to within 5μm. © Published under licence by IOP Publishing Ltd.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Precise segmentation of offshore farms in high-resolution SAR Images based on improved UNet++

Precise segmentation of offshore farms in high-resolution SA...

引用

2021 International Conference on Computer Application and Information Security, ICCAIS 2021

作者： Yu, Chuang Liu, Yunpeng Xia, Xin Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781510655218

The segmentation of the offshore farm area in the high-resolution SAR image is of great significance for the statistics of the farming area and the analysis of the rationality of the farming layout. However, the SAR images have the characteristics of a lot of noise and inconspicuous features. It is difficult to achieve precise segmentation by directly using non-learning image segmentation methods. Therefore, we propose a precise segmentation scheme for offshore farms in high-resolution SAR images based on improved UNet++. We first adopt a simulated annealing strategy for the update of the learning rate during the network training. By initializing the learning rate multiple times, we avoid the network from falling into a local optimum. Secondly, for the data set studied, we verify that the segmentation performance of resizing the image to 256×256 pixels is better than that of 512×512 pixels. Finally, we propose an improved UNet++, which uses SE-Net as the feature extraction network to enhance the feature learning ability. Extensive experimental results show that, compared to some state-of-the-art methods, the proposed scheme achieves superior performance with a Frequency Weighted Intersection over Union (FWIoU) of 0.9853 on the high-resolution SAR offshore farm data set. © The Authors.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Studying the Travel Direction Patterns in Urban Mobility: A Case Study of Taxis

Studying the Travel Direction Patterns in Urban Mobility: A ...

引用

International Conference on Wavelet Active Media technology and Information Processing (ICWAMTIP)

作者： Nie Weipeng Li Zetao Zhao Zhidan Cai Shimin Compleχ Lab School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science Complexity Computation Laboratory School of Engineering Shantou University Shantou China Key Laboratory of Intelligent Manufacturing Technology (Ministry of Education) Shantou University Shantou China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu China

Travel direction is important information in urban mobility and reflects the trend of urban travel. Understanding travel direction patterns in urban mobility is crucial for urban planning, transportation management, and resource allocation. Through analyzing the travel direction distribution and direction entropy of three taxi trip datasets from Chengdu, New York City and Beijing, this research examines the relationship between travel behavior and city structure by analyzing travel direction patterns in urban mobility. The analysis reveals that travel direction distributions are influenced by city morphology, indicating a connection with urban shape and temporal factors. Moreover, spatial heterogeneity in travel direction entropy is across different city regions, highlighting varying levels of mobility chaos. Additionally, the analysis reveals temporal variations in travel direction entropy during weekdays, and weekends, reflecting temporal regularities in mobility. These findings contribute to a better understanding of population movement dynamics and inform urban planning and transportation management strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hard Sample Matters a Lot in Zero-Shot Quantization

Hard Sample Matters a Lot in Zero-Shot Quantization

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Huantong Li Xiangmiao Wu Fanbing Lv Daihai Liao Thomas H. Li Yonggang Zhang Bo Han Mingkui Tan South China University of Technology Information Technology R&D Innovation Center of Peking University Changsha Hisense Intelligent System Research Institute Co. Ltd School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China Hong Kong Baptist University Key Laboratory of Big Data and Intelligent Robot Ministry of Education PengCheng Laboratory

Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network quantization is performed using synthetic samples, thus, the performance of quantized models depends heavily on the quality of synthetic samples. Nonetheless, we find that the synthetic samples constructed in existing ZSQ methods can be easily fitted by models. Accordingly, quantized models obtained by these methods suffer from significant performance degradation on hard samples. To address this issue, we propose HArd sample Synthesizing and Training (HAST). Specifically, HAST pays more attention to hard samples when synthesizing samples and makes synthetic samples hard to fit when training quantized models. HAST aligns features extracted by full-precision and quantized models to ensure the similarity between features extracted by these two models. Extensive experiments show that HAST significantly outperforms existing ZSQ methods, achieving performance comparable to models that are quantized with real data.

关键词：

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：