检索结果-内蒙古大学图书馆

IEEE Conference on Decision and control

作者： Dominik Baumann Krzysztof Kowalczyk Koen Tiels Paweł Wachel Department of Electrical Engineering and Automation Aalto University Espoo Finland Department of Information Technology Uppsala University Uppsala Sweden Department of Control Systems and Mechatronics Wrocław University of Science and Technology Wrocław Poland Department of Mechanical Engineering Eindhoven University of Technology Eindhoven The Netherlands

Safety is an essential asset when learning control policies for physical systems, as violating safety constraints during training can lead to expensive hardware damage. In response to this need, the field of safe learning has emerged with algorithms that can provide probabilistic safety guarantees without knowledge of the underlying system dynamics. Those algorithms often rely on Gaussian process inference. Unfortunately, Gaussian process inference scales cubically with the number of data points, limiting applicability to high-dimensional and embedded systems. In this paper, we propose a safe learning algorithm that provides probabilistic safety guarantees but leverages the Nadaraya-Watson estimator instead of Gaussian processes. For the Nadaraya-Watson estimator, we can reach logarithmic scaling with the number of data points. We provide theoretical guarantees for the estimates, embed them into a safe learning algorithm, and show numerical experiments on a simulated seven-degrees-of-freedom robot manipulator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-beam photothermal material trace detection method based on self-mixing interference

引用

Applied Optics 2025年第16期64卷 4549-4558页

作者： Zhao, Yan Zhi, Yunlong Zhao, Hui Dong, Daming Tong, Jigang Tu, Chunling School of Electrical Engineering and Automation Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin300384 China National Engineering Research Center for Intelligent Agricultural Equipment Beijing Academy of Agriculture and Forestry Sciences Beijing100097 China Department of Computer Systems Engineering Faculty of ICT Tshwane University of Technology Pretoria0188 South Africa

In this paper, a dual-beam photothermal self-mixing substance trace detection system is proposed. The crystal violet (CV) solution of the sample undergoes a thermal lens effect under the action of pump photoperiod excitation, and the refractive index changes cause the deviation of the probe beam, and the self-mixing interference (SMI) effect occurs when the modulated light returns to the cavity. By combining theoretical and experimental results, the power fluctuation of the SMI signal caused by the thermo-optic effect is linearly related to CV concentration and other parameters. At an excitation power of 24 mW, the detection limit can reach 8.0 × 10−8 mol/L. This method does not require labeling or complex CV pretreatment and has high sensitivity and flexibility, providing a guide for CV characterization in biological, environmental, and pharmaceutical research. © 2025 Optica Publishing Group.

关键词： Gaussian beams Laser beams Optical fields Phase shift Refractive index Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

Long-Term Time Series Anomaly Detection with Transformer and Variational Autoencoder for Water Quality

SSRN

引用

SSRN 2024年

作者： Lin, Yongze Qiao, Junfei Bi, Jing Yuan, Haitao Zhou, MengChu Beijing Laboratory of Smart Environmental Protection Beijing University of Technology Beijing100124 China Faculty of Information Technology Beijing University of Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

In many fields, time series anomaly detection is gaining more and more attention, \textit{e.g.}, air pollution, geological hazards, and network traffic detection. Time series anomaly detection in water quality aims to identify anomalous samples. However, there are several challenges in anomaly detection of water quality time series: 1) Difficulty in obtaining local and global temporal dependencies of time series;2) Difficulty in learning a representation map from time series that enables effective discrimination of anomalies;and 3) Complex nonlinear relationship in water quality time series, making it difficult to detect long-term anomalies. To solve these problems, this work proposes a time series anomaly detection model called Transformer with Variational Autoencoder (TransVAE). First, this work integrates local and global temporal position embedding to improve temporally dependent representation. Second, It adopts a Variational Autoencoder (VAE) to fuse signals and reconstruct their expected distribution. Third, we use a Transformer to process nonlinear relationships in the time series and use residual mechanisms to improve long-term series anomaly detection accuracy. This work adopts two real-world datasets to evaluate the proposed TransVAE, and experiments demonstrate that TransVAE outperforms several state-of-the-art methods in terms of time series anomaly detection accuracy. © 2024, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Model-Based Reinforcement Learning for Robotic Arm control with Limited Environment Interaction

Model-Based Reinforcement Learning for Robotic Arm Control w...

引用

IEEE International Conference on Cyber technology in automation, control, and Intelligent Systems

作者： Yi Chen Xiao Sun Song Zheng Weibing Huang Sheng Zeng Dan Chen Zhezhuang Xu Education Department of Fujian Province Key Laboratory of Industrial Automation Control Technology and Information Processing College of Electrical Engineering and Automation Fuzhou University Fuzhou China Evomotion Co. Ltd. Guangdong Shenzhen China

Reinforcement Learning (RL) has been applied to robotic arm control, which enables the agent to learn an effective policy to solve complex tasks. However, it requires constant interaction with the environment leading to low sample efficiency. In this paper, we propose a robotic arm control approach based on planning via lookahead search, which is a model-based RL algorithm to improve the sample efficiency. The approach builds an environment model in order to obtain the dynamics of the environment. Thus the model can be used to plan future actions by a tree-based search. The experiments show that our approach can solve the task of robotic arm control with less environmental samples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

System Identification and Position control of Pneumatic Actuator

System Identification and Position Control of Pneumatic Actu...

引用

IEEE International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA)

作者： Sami Ibad Lababidi Shafishuhaza Sahlan Mohamed Naji Muftah Ahmad ‘Athif Mohd Faudzi Fuead Ali Control Mechatronics & Engineering Department Faculty of Electrical Engineering Universiti Teknologi Malaysia Skudai. Johor Malaysia Malaysian Institute of Information Technology University Kuala Lumpur Kuala Lumpur

In this paper, to improve the system's performance for precise control of the developed pneumatic cylinder model, a proportional-integral-derivative (PID) controller is designed. The paper demonstrates that by using the obtained mathematical model and implementing the PID controller through the developed human-machine interface (HMI) in MATLAB, precise position control of the pneumatic actuator can be achieved, overcoming the challenges posed by the nonlinear behaviour of pneumatic actuators and leading to improved system performance in various industrial industrial applications. The PID model was optimized using both the Auto tuning and Ziegler-Nichols tuning methods, resulting in the best performance with response times of 0.534 seconds (T s ), 0.375 seconds (T r ), and an overshoot of 0.0799% (OS%).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable and Multiband Graphene THz Antenna Design Optimized Using Machine Learning

Reconfigurable and Multiband Graphene THz Antenna Design Opt...

引用

International Conference on Advanced Technologies for Communications, ATC

作者： Shobhit K. Patel Dhruvik Agravat Tien Dung Nguyen Thi Thanh Kieu Nguyen Truong Khang Nguyen Department of Computer Engineering Marwadi University Rajkot Gujrat India Department of Physics Marwadi University Rajkot Gujrat India Faculty of Control and Automation Electric Power University Ha Noi Vietnam Faculty of Engineering Binh Thuan College Binh Thuan VietNam Faculty of Information Technology School of Technology Van Lang University Ho Chi Minh City Vietnam

ISBN: (数字)9798350353983

ISBN: (纸本)9798350353990

This study investigates the concept of multiband graphene THz antennas. We investigate the advantages of graphene in THz antenna applications with standard materials. Using a graphene strip, we built a multiband GSSPlp-MIMO antenna in this study that achieves triple operating frequencies of 7.64 THz, 9.57 THz, and 10.90 THz. The reflection response (S 11 ) of -29.2135 dB, which shows excellent signal confinement within the antenna, was greatly improved upon the inclusion of graphene. Superior impedance matching was the trade-off for this, even if the gain decreased slightly (10.41 dB) in comparison to the antenna without graphene (12.30 dB). The parameters are optimized using machine learning, yielding a maximum accuracy (R2) of 0.996622 and a mean square error of 5.3934 ×10 -5 . This indicates that high-performance terahertz antennas that balance gain and effective signal transmission can be designed using graphene. The antenna's capacity to handle multiple bands makes it ideal for future ultra-broadband wireless communication systems. This results in higher data transfer rates and supports emerging technologies such as 6G and beyond.

关键词： Design methodology Graphene Terahertz radiation Machine learning Mean square error methods Data transfer Reflection Antennas Gain Terahertz communications

来源：评论

学校读者我要写书评

暂无评论

Enhanced shear strength and microstructure of Cu–Cu interconnection by low-temperature sintering of Cu nanoparticles

引用

Journal of Materials Science: Materials in Electronics 2024年第11期35卷 743-743页

作者： Cui, Ze Jia, Qiang Wang, Yishu Li, Dan Wang, Chien-Ping Zhang, Hongqiang Lu, Ziyi Ma, Limin Zou, Guisheng Guo, Fu Faculty of Materials and Manufacturing Beijing University of Technology Beijing100124 China Department of Mechanical Engineering National Taipei University of Technology Taipei Taiwan School of Mechanical Engineering and Automation Beihang University Beijing100191 China Department of Mechanical Engineering State Key Laboratory of Tribology Tsinghua University Beijing100084 China School of Mechanical Electrical Engineering Beijing Information Science and Technology University Beijing100192 China

Sintering of Cu nanoparticles at low temperature is a promising material for advanced power electronic packaging;while its sintering quality is significantly inhibited by oxides. In this work, the Pt-catalyzed formic acid and decomposition of mixtures of organic compounds and copper formate were utilized to eliminate Cu nanoparticles from oxidation to promote Cu atomic diffusion and form strong bonding. The results indicated that the sintered neck length was longer in the Pt-catalyzed formic acid environment, and the stronger atomic diffusion and interparticle bonding was formed. The shear strength of the sintered Cu–Cu joint reached 49 MPa at 180 °C. Furthermore, the effects of temperature and pressure on the formation and growth of sintered necks, pore eliminations, densification, and bonding strength were discussed. This work could provide industrial insights from realizing low-temperature sintering used in the field of power electronics. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Sintering

来源：评论

学校读者我要写书评

暂无评论

Wood Broken Defect Detection With 3D Laser Scanning

Wood Broken Defect Detection With 3D Laser Scanning

引用

Chinese automation Congress (CAC)

作者： Zhijie Ai Ye Lin Zhezhuang Xu Yuhang Zhu Lianxu Wu Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province School of Electrical Engineering and Automation Fuzhou University Fuzhou China

Wood broken defects, such as cracks, penetrating dead knots and wanes, will seriously weaken the strength of the wood and destroy the structral integrity of the wood. Therefore, these defects should be inspected and then cut during the production. Although vision-based detection methods have been proposed to detect wood defect regions, they can not detect the defects that change in depth. To solve this problem, this paper focuses on the defect detection by measuring depth difference through 3D laser data. First, the 3D laser data is preprocessed to remove the noise. Secondly, we construct a support profile by multiple mean filtering at the line-level. Next, the residual components are obtained by subtracting the support profile from the profile data and the defect is determined by comparing the residual components and the setting threshold. Finally, we perform merging and filtering operation to determine the final position of defects. The experimental results verify the effectiveness of the proposed method.

关键词： Three-dimensional displays automation Filtering Laser noise Merging Lasers Production

来源：评论

学校读者我要写书评

暂无评论

DiffRoad: Realistic and Diverse Road Scenario Generation for Autonomous Vehicle Testing

arXiv

引用

arXiv 2024年

作者： Zhou, Junjie Wang, Lin Meng, Qiang Wang, Xiaofan Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Department of Automation Shanghai Jiao Tong University School of Mechatronic Engineering and Automation Shanghai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Shanghai201418 China Department of Civil and Environmental Engineering National University of Singapore Singapore117576 Singapore

Generating realistic and diverse road scenarios is essential for autonomous vehicle testing and validation. Nevertheless, owing to the complexity and variability of real-world road environments, creating authentic and varied scenarios for intelligent driving testing is challenging. In this paper, we propose DiffRoad, a novel diffusion model designed to produce controllable and high-fidelity 3D road scenarios. DiffRoad leverages the generative capabilities of diffusion models to synthesize road layouts from white noise through an inverse denoising process, preserving real-world spatial features. To enhance the quality of generated scenarios, we design the Road-UNet architecture, optimizing the balance between backbone and skip connections for high-realism scenario generation. Furthermore, we introduce a road scenario evaluation module that screens adequate and reasonable scenarios for intelligent driving testing using two critical metrics: road continuity and road reasonableness. Experimental results on multiple real-world datasets demonstrate DiffRoad’s ability to generate realistic and smooth road structures while maintaining the original distribution. Additionally, the generated scenarios can be fully automated into the OpenDRIVE format, facilitating generalized autonomous vehicle simulation testing. DiffRoad provides a rich and diverse scenario library for large-scale autonomous vehicle testing and offers valuable insights for future infrastructure designs that are better suited for autonomous vehicles. Copyright © 2024, The Authors. All rights reserved.

关键词： Automobile testing

来源：评论

学校读者我要写书评

暂无评论

Influence of Reconstruction Algorithms on Harmonic Analysis in electrical Impedance Tomography

引用

IFAC-PapersOnLine 2023年第2期56卷 5615-5619页

作者： Erik Stein Rongqing Chen Alberto Battistel András Lovas Balazs Benyó Knut Möller Institute of Technical Medicine (ITeM) Furtwangen University (HFU) Villingen-Schwenningen Germany Faculty of Engineering University of Freiburg Freiburg Germany Department of Anaesthesiology and Intensive Therapy Kiskunhalas Semmelweis Hospital Kiskunhalas Hungary Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Control Engineering and Information Technology Budapest Hungary

electrical Impedance Tomography (EIT) is a commonly used imaging technique for monitoring respiration on the bedside and it might have the potential for monitoring lung perfusion. Several signal processing approaches have been developed to separate respiration and perfusion. In this contribution we investigated whether different image reconstruction algorithms influence the separation results provided by the harmonic analysis approach. We compared the algorithms used by Dräger, the Gauss-Newton method with different regularizers as well as the GREIT algorithm. The comparison was carried out using a retrospective EIT dataset from a COVID-19 patient. The results gave insight that the harmonic analysis separation approach is dependent on the reconstruction algorithms. Both, the separation of the perfusion and the separation of the respiration showed differences between the reconstruction algorithms when carried out pixel-wise. On the other hand, the separations carried out on the global impedance only showed marginal differences for the separated perfusion.

关键词： Medical imaging and processing Developments in measurement, signal processing Decision support and control

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：