检索结果-内蒙古大学图书馆

2021 International Conference on Digital Society and intelligent Systems, DSInS 2021

作者： Zhang, Qin Pan, Jinlong Chen, Hu Feng, Yixiong Hong, Zhaoxi Huzhou Vocatinal Technical College Key Laboratory of Robot System Integration and Intelligent Equipment of Huzhou Huzhou313000 China Shanghai Space Propulsion Technology Research Institute Shanghai201109 China Shanghai Institute of Special Equipment Inspection and Technical Research Shanghai200062 China Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Hangzhou310027 China Zhejiang University Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province Hangzhou310027 China

ISBN: (纸本)9781665406307

Affected by uncertain factors such as customer demand, product design process will face with varying degrees of upgrade risk. In order to response to change requirements and reduce the impact of component changes, change path optimization for complex products considering upgrade risk is proposed. The goal of this work is to optimize change paths with multi-objective programming. The optimization model is constructed with the goal of minimizing the change complexity, the minimizing change propagation intensity and minimizing the change time. The improved whale algorithm is proposed to solve the model. A set of non-dominated solutions is obtained which can guide decision makers to choose the appropriate scheme. Finally, a product change path optimization for an elevator is given to verify the effectiveness of the proposed method. © 2021 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Analysis of overload-based cascading failure in multilayer spatial networks

引用

Chinese Physics B 2020年第9期29卷 404-414页

作者： Min Zhang Xiao-Juan Wang Lei Ji Mei Song Zhong-Hua Liao School of Science Beijing University of Posts and TelecommunicationsBeijing 100876China School of Electronic Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation CenterBeijing 100854China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System EngineeringBeijing 100854China

Many complex networks in real life are embedded in space and most infrastructure networks are interdependent,such as the power system and the transport *** this paper,we construct two cascading failure models on the multilayer spatial *** our research,the distance l between nodes within the layer obeys the exponential distribution P(l)~exp(-l/ζ),and the length r of dependency link between layers is defined according to node *** entropy approach is applied to analyze the spatial network structure and reflect the difference degree between *** metrics,namely dynamic network size and dynamic network entropy,are proposed to evaluate the spatial network robustness and *** the cascading failure process,the spatial network evolution is analyzed,and the numbers of failure nodes caused by different reasons are also counted,***,we discuss the factors affecting network *** demonstrate that the larger the values of average degree,the stronger the network *** the length r decreases,the network performs *** the probability p is small,asζdecreases,the network robustness becomes more *** p is large,the network robustness manifests better performance asζ*** results provide insight into enhancing the robustness,maintaining the stability,and adjusting the difference degree between nodes of the embedded spatiality systems.

关键词： cascading failure multilayer network load distribution spatial network entropy

来源：评论

学校读者我要写书评

暂无评论

Matching Design and Multi-objective Optimization of Integarated joint for collaborative robot

Matching Design and Multi-objective Optimization of Integara...

引用

IEEE Conference on Industrial electronics and Applications (ICIEA)

作者： Hui Zhang Chi Zhang Feng Yi Qinghao Du Pingping Lv Shupei Li Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Ningbo China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Ningbo China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo China

ISBN: (数字)9798350360868

ISBN: (纸本)9798350360875

Driving joints are the core components of collaborative robots, but existing joints have low torque density and poor dynamic response performance. This article proposes a novel integrated joint composed of a hollow AFPM motor and an embedded planetary gear reducer, which enhance the output performance, i.e., high torque density and efficiency, high dynamic response. Aiming at achieving the superior performance, a matching-oriented design method is proposed for the integrated joint. This design method reveals the impacts mechanisms between the structural parameters (including AFPM motor and planetary reducer) and the output performance. The multi-objective optimization is conducted to obtain the optimal design parameters by using NSGA-II. The optimized design is compared with the initial one, which indicates that the weight of the optimized joint is reduced by 49g, the joint torque density is increased by 36.8%, and the dynamic response performance is improved by 31.5%.

关键词： Industrial electronics Torque Gears Design methodology Collaborative robots Motors Structural engineering

来源：评论

学校读者我要写书评

暂无评论

Semantic segmentation of track image based on deep neural network

引用

The Journal of China Universities of Posts and Telecommunications 2020年第5期27卷 23-33页

作者： Wang Zhaoying Zhou Junhua Liao Zhonghua Zhai Xiang Zhang Lianping School of Electronic Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Complex Product Advanced Manufacturing Kngineering Research Center Beijing Simulation CenterBeijing 100854China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System EngineeringBeijing 100854China Alibaba Cloud Computing Beijing 100020China

In this paper,deep learning technology was utilited to solve the railway track recognition in intrusion detection *** railway track recognition can be viewed as semantic segmentation task which extends image processing to pixel level *** encoder-decoder architecture DeepLabv3+model was applied in this work due to its good performance in semantic segmentation *** images of the railway track collected from the video surveillance of the train cab were used as experiment dataset in this work,the following improvements were made to the *** first aspect deals with over-fitting problem due to the limited amount of training *** augmentation and transfer learning are applied consequently to rich the diversity of data and enhance model robustness during the training ***,different gradient descent methods are compared to obtain the optimal optimizer for training model *** third problem relates to data sample imbalance,cross entropy(CE)loss is replaced by focal loss(FL)to address the issue of serious imbalance between positive and negative *** of the improved DeepLabv3+model with above solutions is demonstrated by experiment results with different system parameters.

关键词： railway track recognition convolutional neural networks semantic segmentation DeepLabv3+

来源：评论

学校读者我要写书评

暂无评论

Microstructural Evolution, Mechanical and Functional Properties of Selective Laser Melting Niti Shape Memory Alloys with Varying Volume Energy Density

SSRN

引用

SSRN 2022年

作者： Ge, Jinguo Yuan, Bo Zhao, Lun Yan, Ming Chen, Wei Zhang, Liang Institute of Intelligent Manufacturing Technology ShenZhen Polytechnic Shenzhen518055 China School of Mechanical and Electrical Engineering Guilin University of Electronic Technology China Shenzhen Key Laboratory for Additive Manufacturing of High-performance Materials Department of Materials Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Selective laser melting (SLM) was adopted to manufacture equi-atomic NiTi shape memory alloy (SMA) through varying volume energy density. The processing quality, phase transformation and microstructural evolution of the SLM-fabricated samples were studied to explore the dominant mechanisms responsible for mechanical and functional properties. The results show that only micro-sized spherical gaseous defects were dispersedly remained within deposit. One-stage phase transformation occurred without intermediate R-phase transition, and the temperature of both endothermic and exothermic peaks was lower than that of the ingot. The SLM-fabricated microstructure was prior to grow along the building direction, but displayed different crystal orientation between coarse columnar grains and refined irregular sub-grains. The micro-hardness mapping measurement revealed that homogenous anti-indentation properties were acquired independent of location variations. While the anisotropic behavior in tensile properties occurred caused by the passive effect of columnar B2 austenitic grains, a synergistic effect of strength and plasticity was acquired, largely due to the combined sub-grain refinement strengthening and transformation-induced plasticity. The pre-deformed SLM-fabricated NiTi samples could recover to its original shape upon heating above its critical phase transition point. This work demonstrated that the crack-free NiTi SMA with exceptional comprehensive performances could be fabricated by SLM through energy density control. © 2022, The Authors. All rights reserved.

关键词： Microstructural evolution

来源：评论

学校读者我要写书评

暂无评论

Decoupled Prototype Learning for Reliable Test-Time Adaptation

arXiv

引用

arXiv 2024年

作者： Wang, Guowei Ding, Changxing Tan, Wentao Tan, Mingkui the School of Electronic and Information Engineering South China University of Technology 381 Wushan Road Tianhe District Guangzhou510000 China the Pazhou Lab Guangzhou510330 China the School of Future Technology South China University of Technology 381 Wushan Road Tianhe District Guangzhou510000 China the School of Software Engineering the Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou510006 China

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels. However, its performance is significantly affected by noisy pseudo-labels. This study reveals that minimizing the classification error of each sample causes the cross-entropy loss’s vulnerability to label noise. To address this issue, we propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation. First, we decouple the optimization of class prototypes. For each class prototype, we reduce its distance with positive samples and enlarge its distance with negative samples in a contrastive manner. This strategy prevents the model from overfitting to noisy pseudo-labels. Second, we propose a memory-based strategy to enhance DPL’s robustness for the small batch sizes often encountered in TTA. We update each class’s pseudo-feature from a memory in a momentum manner and insert an additional DPL loss. Finally, we introduce a consistency regularization-based approach to leverage samples with unconfident pseudo-labels. This approach transfers feature styles of samples with unconfident pseudo-labels to those with confident pseudo-labels. Thus, more reliable samples for TTA are created. The experimental results demonstrate that our methods achieve state-of-the-art performance on domain generalization benchmarks, and reliably improve the performance of self-training-based methods on image corruption benchmarks. The code will be released. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Structural design and simulation analysis of an orthodontic wire bending robot

Structural design and simulation analysis of an orthodontic ...

引用

IEEE International Conference on Mechatronics and Automation

作者： Liu Han Jiang Jingang Li Yanze Zhang Yongde Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology No.52 of Xuefu Road Harbin Heilongjiang Province China Foshan Baikang Robot Technology Co. Ltd Room B429 Block B Nanhai Industrial Think Tank City Phase I Taoyuan Road Foshan City Guangdong Province China

Based on the manual orthodontic wire bending motion, the type and number of degrees of freedom required for bending complex closed gap curves were analysed, and the resulting degrees of freedom were processed and calculated as the basic requirements for the structural design of the robot, while the current problem of the orthodontic wire bending robot not being able to continuously feed the wire was solved by using the counter-rotating collet feeding mechanism, which improved the operational efficiency of the robot. The kinematic model of the robot was established using the D-H method, and the kinematic analysis and simulation of the robot were carried out using MATLAB to verify the smoothness of the robot’s motion. At the same time, ANSYS simulation software was used to verify the stiffness characteristics of the robot during operation, completing the verification of feasibility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Macroscopic effects on the Terahertz generation from the two-color filamentation

引用

Optics Express 2025年第12期33卷 26628-26640页

作者： Zhi-Hong Jiao Xin-Xin Zhang Sheng Zhang Jin-Xu Du Guo-Li Wang Song-Feng Zhao Yizhu Zhang Yuhai Jiang Key Laboratory of Atomic and Molecular Physics and Functional Materials of Gansu Province College of Physics and Electronic Engineering Northwest Normal University Lanzhou 730070 China School of Intelligent Manufacturing Nanjing University of Science and Technology Jiangyin 214443 China School of Precision Instrument and Optoelectronics Engineering Tianjin University Tianjin 300072 China Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai 201210 China Center for Transformative Science and School of Physical Science and Technology ShanghaiTech University Shanghai 201210 China

We recently investigated the influence of laser propagation in gas medium on Terahertz (THz) yield. The dependence of THz yield on the distance between two spatially discrete foci was reproduced when the two collimated driver beams were focused separately. In this study, we further account of the THz field propagation and the interference of local THz sources in the far field; thus, the THz spectra are even reproduced successfully. We provide full explanations for the spectral characteristics of THz radiation generated by using two different driver configurations of overlapping and separating foci. The spectral broadening using the separating foci driver mainly benefits from the improvement of phase matching in the far field due to adjusting the amplitude and phase distribution of the driver beam. Our theoretical modeling effectively validates the availability of the photocurrent model for THz radiation across a wide spectral range.

关键词： Effective refractive index Four wave mixing Gas lasers Laser beams Phase matching Phase shift

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

arXiv

引用

arXiv 2023年

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

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. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

key Techniques on Unified Identity Authentication in OpenMBEE Integration 4

Key Techniques on Unified Identity Authentication in OpenMBE...

引用

4th IEEE International Conference on electronics and Communication Engineering, ICECE 2021

作者： Xue, Junjie Zhou, Junhua Shi, Guoqiang Feng, Chaoqun Liu, Penghua Quan, Hongyan Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing China State Key Laboratory of Intelligent Manufacturing System Technology Beijing China Institute of Electronic System Engineering Beijing China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing China School of Computer Science and Technology East China Normal University Shanghai China

ISBN: (纸本)9781728194226

In order to make full use of the concept of model-based systems engineering (MBSE) and the collaborative design capability of the open model-based engineering environment (OpenMBEE) in establishing complex product development platform, we propose an effective method to solve the problem of unified identity authentication in OpenMBEE integration. The proposed method is based on the Model View Controller(MVC) architecture in OpenMBEE, which has the characteristics strong plasticity and can be benefit for expanding the function in the controller layer. In our research, we make full use of the Software Development Kit (SDK) of OpenMBEE to expand the existing functions in the controller layer, and increase the function of communicating with the application development platform, then realize the function of sharing user authentication information between the development platform and OpenMBEE. After expansion, the system includes three modules, including the Front-end Service Module(FSM), MQ based Information Receiving Service Module(IFRSM), and the OpenMBEE Back-end Server Module(BSM). The effectiveness of the proposed strategies is verified by some practical instances, which verifies that our study can provide an effective design idea for the identity authentication in OpenMBEE integration. ©2021 IEEE

关键词： Integration

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：