检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Electronic Technology, Communication and Information, ICETCI 2021

作者： Xu, Hongqing Tian, Junmin Li, Chengpeng Zhao, Qian Yang, Xu Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Tobacco Shaanxi Industrial Company Limited Xi'an710065 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Key Laboratory on Intelligent Detection and Equipment Technology of Liaoning Province Shenyang110179 China SIASUN Robot & Automation Co. Ltd. Shenyang110169 China

ISBN: (纸本)9781665432511

In the process of cigarette, the dynamic splicing of running bobbin paper and spare bobbin paper plays a very important role in the continuous operation of Cigarette Making and Filter Assembling Group. However, at present, the dynamic splicing system of some domestic Cigarette Making and Filter Assembling Group mostly adopts magnetic particle clutch. After using the magnetic particle clutch for a period of time, it will not rotate or rotate too slowly due to wear and tear. It is easy to cause the rotation speed of spare bobbin paper and running bobbin paper to be inconsistent when splicing, resulting in relative speed, resulting in failure of splicing. Therefore, a dynamic splicing system based on Lenze 9400 servo controller is proposed. The system can guarantee the smooth splicing of the running and spare bobbin paper, reduce The Times of maintenance and improve the production efficiency. ©2021 IEEE.

关键词： Tobacco

来源：评论

学校读者我要写书评

暂无评论

Adversarially robust deep multi-view clustering: a novel attack and defense framework 24

Adversarially robust deep multi-view clustering: a novel att...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Haonan Huang Guoxu Zhou Yanghang Zheng Yuning Qiu Andong Wang Qibin Zhao School of Automation Guangdong University of Technology Guangzhou CHINA and RIKEN AIP Tokyo JAPAN School of Automation Guangdong University of Technology Guangzhou CHINA and Key Laboratory of Intelligent Detection and the Internet of Things in Manufacturing Ministry of Education Guangzhou CHINA School of Automation Guangdong University of Technology Guangzhou CHINA RIKEN AIP Tokyo JAPAN RIKEN AIP Tokyo JAPAN and School of Automation Guangdong University of Technology Guangzhou CHINA

Deep Multi-view Clustering (DMVC) stands out as a widely adopted technique aiming at enhanced clustering performance by leveraging diverse data sources. However, the critical issue of vulnerability to adversarial attacks is unexplored due to the lack of well-defined attack objectives. To fill this crucial gap, this paper is the first work to investigate the possibility of adversarial attacks on DMVC models. Specifically, we introduce an adversarial attack with Generative Adversarial Networks (GANs) with the aim to maximally change the complementarity and consistency of multiple views, thus leading to wrong clustering. Building upon this adversarial context, in the realm of defense, we propose a novel Adversarially Robust Deep Multi-View Clustering by leveraging adversarial training. Based on the analysis from an information-theoretic perspective, we design an Attack Mitigator that provides a foundation to guarantee the adversarial robustness of our DMVC models. Experiments conducted on multiview datasets confirmed that our attack framework effectively reduces the clustering performance of the target model. Furthermore, our proposed adversarially robust method is also demonstrated to be an effective defense against such attacks. This work is a pioneer in exploring adversarial threats and advancing both theoretical understanding and practical strategies for robust multiview clustering. Code is available at https://***/libertyhhn/AR-DMVC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mixture of Experts for Network Optimization: A Large Language Model-enabled Approach

arXiv

引用

arXiv 2024年

作者： Du, Hongyang Liu, Guangyuan Lin, Yijing Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization tasks for individual users complicates developing and applying numerous DRL models, leading to substantial computation resource and energy consumption and can lead to inconsistent outcomes. To address this issue, we propose a novel approach utilizing a Mixture of Experts (MoE) framework, augmented with Large Language Models (LLMs), to analyze user objectives and constraints effectively, select specialized DRL experts, and weigh each decision from the participating experts. Specifically, we develop a gate network to oversee the expert models, allowing a collective of experts to tackle a wide array of new tasks. Furthermore, we innovatively substitute the traditional gate network with an LLM, leveraging its advanced reasoning capabilities to manage expert model selection for joint decisions. Our proposed method reduces the need to train new DRL models for each unique optimization problem, decreasing energy consumption and AI model implementation costs. The LLM-enabled MoE approach is validated through a general maze navigation task and a specific network service provider utility maximization task, demonstrating its effectiveness and practical applicability in optimizing complex networking systems. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Grinding Robot Control System for Circumferential Weld on Inner Wall of Pipe

Design and Implementation of Grinding Robot Control System f...

引用

作者： Kai Chang Jie Gao Bo Liu Jian Yin Minghui Yan Guoyue Zhang Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent ManufacturingChinese Academy of Sciences Key Laboratory on Intelligent Detection and Equipment Technology of Liaoning Province Xi'an Aerospace Engine Co. Ltd.

For the problems of poor working environment and low efficiency in the grinding process of circumferential weld on inner wall of pipe,an automatic grinding control system based on industry robot was designed and *** pipe was positioned by servo *** on the calibration results of tool and workpiece coordinates,the robot grinding trajectory was automatically planned by off-line programming *** the grinding process was simulated and verified in the offline programming software,the generated grinding trajectory code was downloaded to the robot control system to carry out the technological *** the grinding technological experiment,the basic technological parameters and the final process of automatic debugging were *** the automatic operation and detection,the overall network architecture of the control system was set up.

关键词： automatic grinding coordinate system robot trajectory planning technological experiment

来源：评论

学校读者我要写书评

暂无评论

Noisy Tensor Completion via Low-Rank Tensor Ring

arXiv

引用

arXiv 2022年

作者： Qiu, Yuning Zhou, Guoxu Zhao, Qibin Xie, Shengli The School of Automation Guangdong University of Technology Guangzhou510006 China The Key Laboratory of Intelligent Detection The Internet of Things in Manufacturing Ministry of Education Guangdong University of Technology Guangzhou510006 China RIKEN Tokyo103-0027 Japan The School of Automation Guangdong University of Technology Guangzhou510006 China The Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology Guangzhou510006 China

Tensor completion is a fundamental tool for incomplete data analysis, where the goal is to predict missing entries from partial observations. However, existing methods often make the explicit or implicit assumption that the observed entries are noise-free to provide a theoretical guarantee of exact recovery of missing entries, which is quite restrictive in practice. To remedy such drawback, this paper proposes a novel noisy tensor completion model, which complements the incompetence of existing works in handling the degeneration of high-order and noisy observations. Specifically, the tensor ring nuclear norm (TRNN) and least-squares estimator are adopted to regularize the underlying tensor and the observed entries, respectively. In addition, a non-asymptotic upper bound of estimation error is provided to depict the statistical performance of the proposed estimator. Two efficient algorithms are developed to solve the optimization problem with convergence guarantee, one of which is specially tailored to handle large-scale tensors by replacing the minimization of TRNN of the original tensor equivalently with that of a much smaller one in a heterogeneous tensor decomposition framework. Experimental results on both synthetic and real-world data demonstrate the effectiveness and efficiency of the proposed model in recovering noisy incomplete tensor data compared with state-of-the-art tensor completion models. Copyright © 2022, The Authors. All rights reserved.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Automatic installation system of soft rubber caps based on multi-rivet aircraft structural parts

Automatic installation system of soft rubber caps based on m...

引用

Electrical Engineering and Automation (IFEEA), International Forum on

作者： Qingshi Zhang Jianwei Mu Bowen Xu Chuanjun Yu Xin Tong Wei Wang Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Key Laboratory on Intelligent Detection and Equipment Technology of Liaoning Province Shenyang China AVIC Shenyang Aircraft Industrial (Group) Co. Ltd Shenyang China School of Mechanical Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9781665464222

Many structural parts are connected and fixed with rivets or screws in aircraft assembly. Due to the requirements of sealing, anticorrosion or fastening, soft rubber caps coated with sealant need to be bonded. The current production mode is mostly manual operation, there are a lot of problems, such as heavy workload, high hollow rate of sealing cap, low production efficiency, not environmental-friendly and so on. In this paper, a multi-rivet automatic identification and rubber cap installation system of micro-curved structural parts based on robotic linear laser scanning is designed by cooperative-robot to carry a linear laser camera and a soft rubber cap pickup fixture. The system can realize the automatic scanning, identification, classification and positioning of rivets or screws, automatically pick up different types of rubber caps according to the classification, and link with the automatic glue injection system to complete the quantitative glue injection of rubber caps, and automatically complete the installation of rubber caps according to the positioning information.

关键词： Sealing materials Visualization Semiconductor lasers Production Fasteners Rubber Aircraft

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Dimension Measurement System for Industrial Part Inspection

Deep Learning-Based Dimension Measurement System for Industr...

引用

Chinese Automation Congress (CAC)

作者： Xiao-Di Li Xing-Rong Fan Xian-Ming Zhang Han-Zhi Zhang Chun-Jie Huang Cheng Xu Chongqing Engineering Laboratory for Detection Control and Integrated System School of Artificial Intelligence Chongqing Technology and Business University Chongqing China Engineering Research Centre for Waste Oil Recovery Technology and Equipment Ministry of Education Chongqing Key Laboratory Chongqing Technology and Business University Chongqing China School of Computer Science and Information Engineering Chongqing Technology and Business University Chongqing China Chongqing Intelligent Supply Chain Engineering & Technology Research Center Chongqing Jiaotong University Chongqing China Chongqing Aerospace Bashan Motorcycle Manufacturing Co. Ltd. Chongqing China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

This paper develops a deep learning-based system for the dimension measurement of industrial parts. The system employs a general self-supervised image segmentation network to perform dichotomous image segmentation (DIS) on the parts, effectively extracting binary images of the target components from complex backgrounds without requiring preprocessing steps such as filtering or denoising. Following segmentation, contour detection, and dimension measurement are executed. The system utilizes a CMOS area scan camera and was tested on a computer equipped with a GTX1050 graphics card. The tests, conducted on two typical thrust ball bearing components (i.e., the ball retainer and the shaft ring) - yielded ten measurements per part. Comparison with a vernier caliper as the reference standard reveals that under normal operating conditions, the maximum standard deviation is 0.007 mm and the maximum absolute error is 0.017 mm.

关键词： Shafts Image segmentation Accuracy Measurement uncertainty Noise reduction Manuals Size measurement Stability analysis Robustness Standards

来源：评论

学校读者我要写书评

暂无评论

Research on cylindrical labels unfolding algorithm based on machine vision

Research on cylindrical labels unfolding algorithm based on ...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Zelu Zhang Min Xu Shuai Chen Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Key Laboratory on Intelligent Detection and Equipment Technology of Liaoning Province Shenyang China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

It is a difficult problem for imaging the cylindrical label, and this paper presents an algorithm for unfolding the cylindrical label. First, the cylindrical label is positioned by the monocular camera, and the 3D point sets of the cylindrical label are established. Second, the observation range of each camera is determined based on the poses of the cylinders. Then, the cylindrical distortion is corrected in each camera. Finally, two adjacent images are stitched together to obtain a continuous and normalized unfolding image of the cylindrical label. Real-world and synthetic data experiments results show that the algorithm can correct the cylindrical distortion, and it takes only about 160 ms to obtain the cylindrical label unfolding image. The algorithm execution process does not require complicated steps and additional auxiliary, and the algorithm execution speed meets the industrial requirements.

关键词： Three-dimensional displays Machine vision Pose estimation Production Distortion Cameras Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Optical, Structural, and Synchrotron X-ray Absorption Studies for GaN Thin Films Grown on Si by Molecular Beam Epitaxy

引用

Materials 2024年第12期17卷 2921页

作者： Feng, Zhe Chuan Liu, Jiamin Xie, Deng Nafisa, Manika Tun Zhang, Chuanwei Wan, Lingyu Jiang, Beibei Lin, Hao-Hsiung Qiu, Zhi-Ren Lu, Weijie Klein, Benjamin Ferguson, Ian T. Liu, Shiyuan State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China Southern Polytechnic College of Engineering and Engineering Technology Kennesaw University MariettaGA30060 United States Science Exploring Lab Arbour Glenn Drive LawrencevilleGA30043 United States School of Electronic & Electrical Engineering and Physics Fujian University of Technology Fuzhou350118 China Center on Nano-Energy Research Laboratory of Optoelectronic Materials & Detection Technology Guangxi Key Laboratory for the Relativistic Astrophysics School of Physical Science & Technology Guangxi University Nanning530004 China Department of Electrical Engineering Graduate Institute of Photonics and Optoelectronics National Taiwan University Taipei10617 Taiwan State Key Laboratory of Optoelectronic Materials and Technologies School of Physics Sun Yat-sen University Guangzhou510275 China Hexagonal Scientific Lab LLC DaytonOH45459 United States

GaN on Si plays an important role in the integration and promotion of GaN-based wide-gap materials with Si-based integrated circuits (IC) technology. A series of GaN film materials were grown on Si (111) substrate using a unique plasma assistant molecular beam epitaxy (PA-MBE) technology and investigated using multiple characterization techniques of Nomarski microscopy (NM), high-resolution X-ray diffraction (HR-XRD), variable angular spectroscopic ellipsometry (VASE), Raman scattering, photoluminescence (PL), and synchrotron radiation (SR) near-edge X-ray absorption fine structure (NEXAFS) spectroscopy. NM confirmed crack-free wurtzite (w-) GaN thin films in a large range of 180–1500 nm. XRD identified the w- single crystalline structure for these GaN films with the orientation along the c-axis in the normal growth direction. An optimized 700 °C growth temperature, plus other corresponding parameters, was obtained for the PA-MBE growth of GaN on Si, exhibiting strong PL emission, narrow/strong Raman phonon modes, XRD w-GaN peaks, and high crystalline perfection. VASE studies identified this set of MBE-grown GaN/Si as having very low Urbach energy of about 18 meV. UV (325 nm)-excited Raman spectra of GaN/Si samples exhibited the GaN E2(low) and E2(high) phonon modes clearly without Raman features from the Si substrate, overcoming the difficulties from visible (532 nm) Raman measurements with strong Si Raman features overwhelming the GaN signals. The combined UV excitation Raman–PL spectra revealed multiple LO phonons spread over the GaN fundamental band edge emission PL band due to the outgoing resonance effect. Calculation of the UV Raman spectra determined the carrier concentrations with excellent values. Angular-dependent NEXAFS on Ga K-edge revealed the significant anisotropy of the conduction band of w-GaN and identified the NEXAFS resonances corresponding to different final states in the hexagonal GaN films on Si. Comparative GaN material properties are invest

关键词： Synchrotron radiation

来源：评论

学校读者我要写书评

暂无评论

Dynamic integrated process planning and scheduling under multi-resource constraints in workshops with reconfigurable manufacturing cells: a novel hyper-heuristic approach

引用

Expert Systems with Applications 2025年 289卷

作者： Haoxin Guo Kunping Li Jianhua Liu Cunbo Zhuang Fengque Pei Laboratory of Digital Manufacturing School of Mechanical Engineering Beijing Institute of Technology Beijing 100081 China Hebei Key Laboratory of Intelligent Assembly and Detection Technology Tangshan Research Institute Beijing Institute of Technology Tangshan 063000 China School of Mechanical and Electrical Engineering Hohai University Changzhou 213022 China

This study addresses the challenges of hybrid production lines, reconfigurable characteristics, frequent disturbances, and multi-resource constraints in complex aerospace product assembly and testing workshops. We propose a Dynamic Integrated Process Planning and Scheduling under Multi-Resource Constraints in Workshops with Reconfigurable manufacturing Cells (MRC-DIPPS-RMC). By establishing an integrated mathematical model that combines process planning, cell reconfiguration, task scheduling, and resource allocation, we designed a Genetic Programming Hyper-Heuristic with Bloat Control Mechanism (GPHH-BC) based on multi-heuristic co-evolution. The algorithm employs population segmentation to co-evolve four types of heuristic rules, effectively solving five critical subproblems in dynamic environments while successfully suppressing efficiency degradation caused by rule bloating. Experimental results demonstrate that the proposed method demonstrates a 52.67 % improvement in computational efficiency compared to conventional baseline approaches while ensuring solution feasibility; when compared to state-of-the-art algorithms, it achieves a further 7.40 % improvement in computational efficiency.

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：