检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Li, Xiao-Di Fan, Xing-Rong Zhang, Xian-Ming Zhang, Han-Zhi Huang, Chun-Jie Xu, Cheng 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: (纸本)9798350368604

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) ü 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. © 2024 IEEE.

关键词： Ball bearings

来源：评论

学校读者我要写书评

暂无评论

Event-triggered impulsive synchronization of heterogeneous neural networks

引用

Science China(Information Sciences) 2024年第2期67卷 331-332页

作者： Zhengxin WANG Chongfang JIN Wangli HE Min XIAO Guo-Ping JIANG Jinde CAO College of Science Nanjing University of Posts and Telecommunications Jiangsu Engineering Lab for IOT Intelligent Robots (IOTRobot) Nanjing University of Posts and Telecommunications Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and Technology School of Automation Nanjing University of Posts and Telecommunications School of Mathematics Southeast University Yonsei Frontier Lab Yonsei University

Synchronization is one of the most important dynamics in neural networks. Several scholars have studied the quasi-synchronization of heterogeneous neural networks [1],wherein external controllers play a significant role. Impulsive control, a kind of energy-saving control, is activated instantaneously only at specific discrete moments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

detection of wrong and missing installation of threaded steel wire based on pointnet++

Detection of wrong and missing installation of threaded stee...

引用

2022 International Conference on Advanced manufacturing Technology and manufacturing Systems, ICAMTMS 2022

作者： Cheng, Qilong Gou, Rui Su, Rui Gou, Wei Shenyang Institute of Automation Chinese Academy of Sciences Liaoning Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Liaoning Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory on Intelligent Detection and Equipment Technology of Liaoning Province Liaoning Shenyang110179 China Xi'an Aerospace Engine Co. Ltd Xi'an710199 China

ISBN: (纸本)9781510656840

In the mechanical manufacturing industry, the detection of wrong and missing installation of threaded steel wire is of great significance and ensures the reliability and quality of products. Especially in aerospace engineering, the traditional detection of wrong and missing installation mostly adopts two-dimensional detection technology, which has the problems of poor detection effect and affected by light source. Aiming at this problem, a detection method of wrong and missing installation of threaded steel wire based on pointnet++ was proposed, which constructs a network framework based on pointnet++, by training the network,it realizes the recognition and direction judgment of threaded steel wire, and the accuracy is more than 95%. © 2022 SPIE.

关键词： Light sources

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 5

Research on cylindrical labels unfolding algorithm based on ...

引用

5th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2021

作者： Zhang, Zelu Xu, Min Chen, Shuai 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

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. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient and Accurate Approximation: Tensor Decomposition Based on Randomized Block Krylov Iteration

arXiv

引用

arXiv 2022年

作者： Qiu, Yichun Sun, Weijun Zhou, Guoxu Zhao, Qibin School of Automation Guangdong University of Technology Guangzhou510006 China Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China Key Laboratory of Intelligent Detection The Internet of Things in Manufacturing Ministry of Education Guangzhou510006 China Joint International Research Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China RIKEN Tokyo103-0027 Japan

Efficient and accurate low-rank approximation (LRA) methods are of great significance for large-scale data analysis. Randomized tensor decompositions have emerged as powerful tools to meet this need, but most existing methods perform poorly in the presence of noise interference. Inspired by the remarkable performance of randomized block Krylov iteration (rBKI) in reducing the effect of tail singular values, this work designs an rBKI-based Tucker decomposition (rBKI-TK) for accurate approximation, together with a hierarchical tensor ring decomposition based on rBKI-TK for efficient compression of large-scale data. Besides, the error bound between the deterministic LRA and the randomized LRA is studied. Numerical experiences demonstrate the efficiency, accuracy and scalability of the proposed methods in both data compression and denoising. © 2022, CC BY.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Bayesian Robust Tensor Ring Model for Incomplete Multiway Data

arXiv

引用

arXiv 2022年

作者： Huang, Zhenhao Qiu, Yuning Chen, Xinqi Sun, Weijun Zhou, Guoxu The School of Automation Guangdong University of Technology Guangzhou510006 China RIKEN Tokyo103-0027 Japan Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of Education

Robust tensor completion (RTC) aims to recover a low-rank tensor from its incomplete observation with outlier corruption. The recently proposed tensor ring (TR) model has demonstrated superiority in solving the RTC problem. However, the existing methods either require a pre-assigned TR rank or aggressively pursue the minimum TR rank, thereby often leading to biased solutions in the presence of noise. In this paper, a Bayesian robust tensor ring decomposition (BRTR) method is proposed to give more accurate solutions to the RTC problem, which can avoid exquisite selection of the TR rank and penalty parameters. A variational Bayesian (VB) algorithm is developed to infer the probability distribution of posteriors. During the learning process, BRTR can prune off slices of core tensor with marginal components, resulting in automatic TR rank detection. Extensive experiments show that BRTR can achieve significantly improved performance than other state-of-the-art methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Application of Sensors in Flexible Process Control of intelligent manufacturing

Application of Sensors in Flexible Process Control of Intell...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Jianxiong Qiu Zhaoshui He Cheng Yan Hailong Zhou Guangdong University of Technology Guangzhou China School of Automation Guangdong University of Technology Key Laboratory of Information Processing and System Integration of IoT Ministry of Education Guangzhou China Huizhou Metal Cutting Processing Unit Intelligent Manufacturing Engineering Technology Research Center Huizhou China Tianjin Bonuo Intelligent Robot Technology Co. Ltd. Tianjin China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

In order to carry out the intelligent production of typical chemical products for the application of order-based flexible production system, based on intelligent measurement and control technology, a new generation of information technology such as industrial Internet, intelligent management and control, data visualization, and informatization is integrated. In this paper, we study the establishment of an order-based flexible production process with definable configuration according to the intelligent processing mode of process automation. After selecting the sensor reasonably, Configuration of the industrial intelligent detection system, System signal processing and digitalization, Industrial information network construction and debugging, Programming operation and debugging of intelligent measurement and control systems, Production tasks such as visualization and remote monitoring of the production process. The study found,The sensor plays a vital role in the control system control of the DCS -based controller, Liquid level sensors and flow/weight sensors and other key sensors can monitor various parameters in the production process in real time, provide accurate data support for the control system to ensure the accuracy and stability of the ingredient system. And realize the flexible ingredients controlled by program control, and then make the feeding at the same time to improve production efficiency. This research provides a strong technical guarantee for actual production, and provides a feasible implementation method for our intelligent manufacturing process industrial control.

关键词： Temperature measurement Temperature sensors Accuracy Data visualization Process control Production Control systems

来源：评论

学校读者我要写书评

暂无评论

Optimal Routing and Charging Strategy for Shared Electric Vehicle Service

SSRN

引用

SSRN 2022年

作者： Zeng, Weiliang Han, Yu Yao, Ruoyu Liu, Panlong Liao, Li Xie, Shengli School of automation Guangdong University of Technology Guangdong Guangzhou510006 China Joint International Research Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong Provincial Key Laboratory of Intelligent Transportation System Guangdong510006 China Guangdong Engineering Center of Auto-detection Technology for Intelligent Manufacturing Guangdong University of Technology Guangzhou510006 China

How to jointly optimize the routing and charging strategy is a critical issue for the operation of shared electric vehicle (SEV). Existing studies usually addressed the shared routing problem and electricity charging problem independently based on some strict premises which cannot optimize the operation cost globally. To fill this gap, this study models the routing and charging problem of the SEV system as a general formulation, considering ride-matching, charging amount and charging station selection as a whole. And then the global optimization problem is decomposed into four sub-problems. Particularly, this model enables to optimize the global cost of the SEV fleet while adapting to the time-of-use electric price and satisfying the constraints of passengers’ preferences and vehicle states. The performance of the proposed optimization model is validated using 39,700 rides extracted from the Shenzhen taxi dataset. We quantify the success rate of the requests, the average travel time delay, the number of active vehicles and the cost of energy consumption with expanded travel demand levels in the real-world road network by numerical simulation. The simulation results show that the proposed model can reduce 49% of the active vehicles in the road network at the rush hour. Our model also avoids the collective charging behaviors during the power consumption peak time, enabling to relieve the pressure on power supply, and saves more than 20% of the cost of energy. © 2022, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Hybrid RAG-empowered Multi-modal LLM for Secure Data Management in Internet of Medical Things: A Diffusion-based Contract Approach

arXiv

引用

arXiv 2024年

作者： Su, Cheng Wen, Jinbo Kang, Jiawen Wang, Yonghua Su, Yuanjia Pan, Hudan Zhong, Zishao Hossain, M. Shamim School of Automation The GuangdongHongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology Guangzhou510006 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Automation The Guangdong Basic Research Center of Excellence for Ecological Security and Green Development Key Laboratory for City Cluster Environmental Safety Green Development The Ministry of Education Guangdong University of Technology Guangzhou510006 China School of Automation The Key Laboratory of Intelligent Detection and IoT in Manufacturing Ministry of Education Guangdong University of Technology Guangzhou510006 China School of Automation Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangdong University of Technology Guangzhou510006 China Guangzhou University of Traditional Chinese Medicine State Key Laboratory of Traditional Chinese Medicine Syndrome The Second Affiliated Hospital of Guangzhou University of Chinese Medicine Chinese Medicine Guangdong Laboratory Hengqin 519000 China Second Affiliated Hospital of Guangzhou University of Chinese Medicine Chinese Medicine Guangdong Laboratory Hengqin 519000 China Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh12372 Saudi Arabia

Secure data management and effective data sharing have become paramount in the rapidly evolving healthcare landscape, especially with the growing integration of the Internet of Medical Things (IoMT). The rise of generative artificial intelligence has further elevated Multi-modal Large Language Models (MLLMs) as essential tools for managing and optimizing healthcare data in IoMT. MLLMs can support multi-modal inputs and generate diverse types of content by leveraging large-scale training on vast amounts of multi-modal data. However, critical challenges persist in developing medical MLLMs, including security and freshness issues of healthcare data, affecting the output quality of MLLMs. To this end, in this paper, we propose a hybrid Retrieval-Augmented Generation (RAG)-empowered medical MLLM framework for healthcare data management. This framework leverages a hierarchical cross-chain architecture to facilitate secure data training. Moreover, it enhances the output quality of MLLMs through hybrid RAG, which employs multi-modal metrics to filter various unimodal RAG results and incorporates these retrieval results as additional inputs to MLLMs. Additionally, we employ age of information to indirectly evaluate the data freshness impact of MLLMs and utilize contract theory to incentivize healthcare data holders to share their fresh data, mitigating information asymmetry during data sharing. Finally, we utilize a generative diffusion model-based deep reinforcement learning algorithm to identify the optimal contract for efficient data sharing. Numerical results demonstrate the effectiveness of the proposed schemes, which achieve secure and efficient healthcare data management. Copyright © 2024, The Authors. All rights reserved.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

tnGPS: discovering unknown tensor network structure search algorithms via large language models (LLMs) 24

tnGPS: discovering unknown tensor network structure search a...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Junhua Zeng Chao Li Zhun Sun Qibin Zhao Guoxu Zhou School of Automation Guangdong University of Technology Guangzhou China RIKEN Center for Advanced Intelligence Project (RIKEN-AIP) Tokyo Japan Tencent Inc. Shenzhen China 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

Tensor networks are efficient for extremely high-dimensional representation, but their model selection, known as tensor network structure search (TN-SS), is a challenging problem. Although several works have targeted TN-SS, most existing algorithms are manually crafted heuristics with poor performance, suffering from the curse of dimensionality and local convergence. In this work, we jump out of the box, studying how to harness large language models (LLMs) to automatically discover new TN-SS algorithms, replacing the involvement of human experts. By observing how human experts innovate in research, we model their common workflow and propose an automatic algorithm discovery framework called tnGPS. The proposed framework is an elaborate prompting pipeline that instruct LLMs to generate new TN-SS algorithms through iterative refinement and enhancement. The experimental results demonstrate that the algorithms discovered by tnGPS exhibit superior performance in benchmarks compared to the current state-of-the-art methods. Our code is available at https://***/ChaoLiAtRIKEN/tngps.

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：