检索结果-内蒙古大学图书馆

International Conference on Autonomous Robots and Agents, ICARA

作者： Renzo Acosta Julio Tafur Ruth Canahuire Enginnering Department Control and Automation Engineering Master Degree Program Pontificia Universidad Catolica del Peru Lima Peru Department of Electrical and Mechatronics Engineering Universidad de Ingenieria y Tecnologia - UTEC Lima Peru

ISBN: (数字)9798350394245

ISBN: (纸本)9798350394252

This paper presents the dynamic modelling and end effector position control of a soft endoscope. Soft endoscope system under study consists mainly of a pneumatic driven soft actuator (PDSA) with four independently chambers. Recurrent neural network (RNN) and dynamic back propagation (DBP) training algorithm are used to obtain PDSA dynamic model. PDSA position controller is based on a feedforward neural network (FNN) and it is trained using PDSA closed loop system (CLS) and DBP training algorithm. CLS stability analysis concludes that it is not possible control PDSA end effector position using one position controller for different end effector initial and desired positions. Fuzzy logic methodology is used to integrate several positions controllers in a one controller valid for all operation range. The controller implementation and close loop system simulation are performed in MATLAB for different end effector desired position to validate system performance in all range of operation.

关键词： Training Fuzzy logic Backpropagation Recurrent neural networks Endoscopes Heuristic algorithms Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Online Residual Learning from Offline Experts for Pedestrian Tracking

Online Residual Learning from Offline Experts for Pedestrian...

引用

IEEE Conference on Decision and control

作者： Anastasios Vlachos Anastasios Tsiamis Aren Karapetyan Efe C. Balta John Lygeros Department of Information Technology and Electrical Engineering Automatic Control Laboratory ETH Zürich Zürich Switzerland Control and Automation Group inspire AG 8005 Zürich Switzerland and with the Automatic Control Laboratory

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In this paper, we consider the problem of predicting unknown targets from data. We propose Online Residual Learning (ORL), a method that combines online adaptation with offline-trained predictions. At a lower level, we employ multiple offline predictions generated before or at the beginning of the prediction horizon. We augment every offline prediction by learning their respective residual error concerning the true target state online, using the recursive least squares algorithm. At a higher level, we treat the augmented lower-level predictors as experts, adopting the Prediction with Expert Advice framework. We utilize an adaptive softmax weighting scheme to form an aggregate prediction and provide guarantees for ORL in terms of regret. We employ ORL to boost performance in the setting of online pedestrian trajectory prediction. Based on data from the Stanford Drone Dataset, we show that ORL can demonstrate best-of-both-worlds performance.

关键词： Pedestrians Aggregates Prediction algorithms Trajectory Drones

来源：评论

学校读者我要写书评

暂无评论

Novel Voltage Support Strategies for DGs in Hybrid ACDC Distribution Networks under Faults

引用

IEEE Transactions on Sustainable Energy 2025年

作者： Li, Yuze Guo, Peng Xu, Qianming Shuai, Zhikang Guerrero, Josep M. School of Electrical Engineering and Automation Xiamen University of Technology China Xiamen Key Laboratory of Frontier Electric Power Equipment and Intelligent Control Xiamen361012 China Hunan University College of Electrical and Information Engineering Changsha410082 China University of Aalborg Department of Energy Technology Aalborg9220 Denmark

According to the grid codes, the higher the voltage at the point of common coupling (PCC), the longer duration that the voltage-source converters (VSC) can stay connected to the grid. In hybrid ACDC distribution networks (HADNs), owing to the low capacity, VSC-based distributed generator (DG) closest to the fault point may fail to significantly support the voltage at the PCC through current injection. Therefore, other large-capacity converters such as flexible ACDC converters (FACs) should also inject currents to help it. However, in resistive-inductive HADNs, the voltage support effect is related to the current phases of converters, and the fault conditions. In this paper, circumstances under two fault position categories (upstream and downstream fault positions of DG) for double line-to-ground fault and three-phase short-circuit fault are analyzed. The interconnected sequence networks of HADNs under these two fault positions are proposed. Based on the proposed networks, the optimal current phase angles of DG and FAC for maximumly supporting voltages at the PCC of the DG are proposed. Moreover, the line sequence impedance calculation method is proposed. The simulation results verify the proposed strategy. The proposed strategy is suitable for low-capacity DGs in resistive-inductive HADNs to achieve voltage support and fault ride-through. © 2025 IEEE.

关键词： Voltage-source converters

来源：评论

学校读者我要写书评

暂无评论

Sewer Network Model of a City with a Medium-Sized Population

Sewer Network Model of a City with a Medium-Sized Population

引用

International Carpathian control Conference (ICCC)

作者： Iulian Vasiliev Laurentiu Luca Marian Barbu Ramon Vilanova Sergiu Caraman Department of Automation and Electrical Engineering Faculty of Automation Computers Electrical and Electronic Engineering Galati Romania Department of Automation Systems and Advanced Control Research Autonomous University of Barcelona Barcelona Spain

A model of a sewer network for a medium city located in Easter Romania with 250,000 inhabitants is presented in the paper. The model was developed using BSM Sewer software package. An influent was also determined considering the 5 collecting areas and defined on a time- horizon of 28 days. The influent has the following components: a domestic one calculated using the average wastewater production of each inhabitant with specific loads and considering daily, weekly and yearly variations, a pluviometric one proportional to the collecting area surface that includes a rain event and a storm one and an industrial influent (considered only for the 5 th collecting area). The model was tested in different operating conditions of the sewer network considering three operating points given by the values of the valve opening and pumps flows at the tank outlets. The results were analyzed based on 10 performance indicators implemented by researchers from Lund University for BSM Sewer. They showed the need for an optimization of the operating regime of the sewer network in terms of volume and quality of discharged water.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of bioinspired algorithms for tuning a flatness-based controller: A ball and beam case study

Comparative analysis of bioinspired algorithms for tuning a ...

引用

Latin America Congress on Computational Intelligence (LA-CCI)

作者： M. A. Pastrana José Oniram de A. Limaverde Filho Luiz Henrique Oliveira Jaider Bautista Eugênio Fortaleza Daniel M. Muñoz Department of Mechanical Engineering Automation and Control Group (GRACO) University of Brasília Brasília Brazil Department of Electrical Engineering University of Brasília Brasília Brazil Faculty of Engineering Systems Undergraduate Program University of the Amazonia Florencia Colombia

ISBN: (数字)9798350374575

ISBN: (纸本)9798350374582

This paper provides a comprehensive comparative analysis of the performance of four bioinspired algorithms (Differential Evolution, Grasshopper Optimization Algorithm, Moth-flame Optimization, and Particle Swarm Optimization) in designing a flatness-based controller for a ball and beam system simulated in MATLAB/Simulink environment. The assessment involves the tuning of feedback gains utilizing four distinct fitness functions: Integral Square Error, Integral Absolute Error, Integral Time Absolute Error, and an ad-hoc cost function. Hypothesis tests are employed to choose the optimal controllers from each combination for every bioinspired algorithm and a fitness function. Subsequently, a control performance analysis of these controllers for the ball and beam system is conducted, focusing on critical parameters such as overshoot, settling time, and steady-state error. This analysis demonstrates that all the controllers achieve a zero steady-state error. Noteworthy is the flatness-based controller tuned with the bioinspired Grasshopper Optimization Algorithm and utilizing the Integral Time Absolute Error fitness function, which stands out for achieving the fastest response with the lowest overshoot. This particular controller emerges as the most recommended choice for the specified application.

关键词： Particle beams Focusing Cost function MIMO Steady-state Performance analysis Particle swarm optimization MATLAB Tuning Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Day-ahead Unit Commitment Incorperating Deep Peak Regulation 3

Day-ahead Unit Commitment Incorperating Deep Peak Regulation

引用

3rd International Conference on Energy engineering and Power Systems, EEPS 2023

作者： Xiao, Yang Ding, Tao Liu, Yuzheng Zhang, Biyuan Su, Bo Guo, Xiaorui Xi'an Jiaotong University School of Electrical Engineering Xi'an China State Grid Ningxia Electric Power Co. Ltd Center of Electric Power Control Yinchuan China China Electric Power Research Institute Electric Power Automation Department Beijing China

ISBN: (纸本)9798350313857

To give the potential regulation capacity of the thermal power generator for renewable energy integration by peak regulation, this paper has investigated in developing a comprehensive model for day-ahead unit commitment, taking into account deep peak regulation. Specifically, the investigation entails dividing the peak regulation into distinct modes and establishing corresponding operational cost functions. Subsequently, a mixed-integer linear programming model is presented for power scheduling, leveraging the defined cost function. To validate the effectiveness of the proposed model and highlight the superiority of deep peak regulation in accommodating renewable energy sources, a modified IEEE-118 case has been conducted. © 2023 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Successive statistical iterative reconstruction, 3D-filtering and region growing methods for high-quality 3D visualization of cone-beam CT image 2022

Successive statistical iterative reconstruction, 3D-filterin...

引用

7th International Conference on Multimedia and Image processing, ICMIP 2022

作者： Dong, Jian Zhang, Siyuan Yang, Xiaoxia Zhang, Jingyu Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin University of Technology Tianjin300222 China Department of Automation and Electrical Engineering Tianjin University of Technology and Education Tianjin300222 China

ISBN: (纸本)9781450387408

Our study is to improve the accuracy of bone morphology depicted in dental cone-beam computed tomography (CBCT) images. First, successive statistical iterative reconstruction was used to reduce unavoidable streak artefacts. Then 3-dimentional filtering (Gaussian-Laplacian filter) and region growing methods were examined to present clear bone morphology. CBCT examinations were performed with the following principal exposure parameters: I-mode, FOV 10cm in diameter, 120 kV, 15 mA, 0.2 mm slice thickness, and exposure time of 10s. Ordered subset-expectation maximization (OS-EM) algorithm was applied for unavoidable streak artefact reduction. 3D Laplacian sharpening to images preprocessed by Gaussian smoothing was sequentially tested. Region growing method with dilation and erosion was used to segment maxillofacial tissue. Streak artefact induced by metallic prosthetic appliances was reduced by applying successive iterative OS-EM algorithm. Multi-planar reconstruction (MPR) images at left side molar plane and mid-sagittal plane were presented to validate effect of OS-EM algorithm and 3D Gaussian-Laplacian filter. Maxillofacial tissue was segmented and presented to show the effect of region growing method. Streak artefact reducing method, 3D filtering method for image smoothing and sharpening, and region growing method with dilation and erosion were effective to improve accuracy of bone morphology in dental CBCT images. © 2022 ACM.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Liquid Filling Quality control System for Beverage Industry Using Image processing (CNN)

Liquid Filling Quality Control System for Beverage Industry ...

引用

International Conference on control, automation and Systems ( ICCAS)

作者： B. Chatchapol W. Autanan W. Anan Department of Electrical Engineering Faculty of Electric Engineering Rajamangala University of Technology Lanna Chiang Mai Thailand Robotics Engineering and AI Faculty of Engineering Chiang Mai University Chiang Mai Thailand Department of Electronic Engineering and Automation Control System Faculty of Engineering Rajamangala University of Technology Lanna Chiang Mai Thailand

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

The beverage industry has been leveraging automation to enhance production efficiency. An essential advancement involves the use of AI and image processing to ensure the high quality of products. Image processing systems employ sophisticated algorithms to meticulously inspect specific aspects of the production process (liquid level, lid sealing, text print). The CNN algorithm is primarily utilized to scrutinize water bottle images to verify their quality. Maintaining consistent production speed poses a challenge, underscoring the importance of examining the image processing system from various perspectives. The research proposed implementing a system that oversees liquid filling quality through an image processing algorithm, a camera module, and conveyor belt speed control to address. This system monitors liquid levels and bottle capping while the production line is operational. On average, the system achieves a 98.89 percent accuracy rate in detecting liquid levels and a 100 percent accuracy rate in sealing the lids. Furthermore, the conveyor speed control can adjust automatically to detect variations in product movement speed.

关键词： Liquids Image processing Velocity control Production Quality control Inspection Belts Filling Beverage industry Monitoring

来源：评论

学校读者我要写书评

暂无评论

Dc Leakage Current in Isolated Grid-Connected dc Nanogrid - Origins and Elimination Methods

Dc Leakage Current in Isolated Grid-Connected dc Nanogrid - ...

引用

Compatibility in Power Electronics (CPE)

作者： Mohammadreza Azizi Oleksandr Husev Oleksandr Veligorskyi Marek Turzvński Ryszard Strzelecki Department of Radiotechnic and Embedded Systems Chernihiv Polytechnic National University Chernihiv Ukraine Department of Electric Electronic and Automation Engineering University of Extremadura Badajoz Spain Department of Electrical Power Engineering and Mechatronics Tallinn University of Technology Tallinn Estonia Faculty of Electrical and Control Engineering Gdansk University of Technology Gdansk Poland

ISBN: (数字)9798350318265

ISBN: (纸本)9798350318272

The LV dc system is a relatively new trend in the distribution sector, which seems to grow widely in the near future due to its promising advantages. In this context, LV dc protection and grounding are challenging issues. Although the galvanically isolated connection mode of dc nanogrid to the ac grid has high reliability, the leakage current can still be injected into the ac grid through the interwinding capacitors and the insulation resistance between the primary and secondary windings of the transformer. The way of grounding the dc nanogrid can also be a determining factor in the leakage current and its dc components. This study deals with the leakage current in the galvanically isolated dc nanogrid. Then, it examines the dc leakage current and its relationship with the dc nanogrid grounding and finally provides solutions to remove the dc components in the leakage current.

关键词： Resistance Insulation Grounding Simulation Windings Capacitors Leakage currents

来源：评论

学校读者我要写书评

暂无评论

The applied principles of EEG analysis methods in neuroscience and clinical neurology

引用

Military Medical Research 2024年第6期11卷 907-941页

作者： Hao Zhang Qing-Qi Zhou He Chen Xiao-Qing Hu Wei-Guang Li Yang Bai Jun-Xia Han Yao Wang Zhen-Hu Liang Dan Chen Feng-Yu Cong Jia-Qing Yan Xiao-Li Li School of Systems Science Beijing Normal UniversityBeijing 100875China College of Electrical and Control Engineering North China University of TechnologyBeijing 100041China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510641China Department of Psychology the State Key Laboratory of Brain and Cognitive Sciencesthe University of Hong KongHong Kong SAR 999077China HKU-Shenzhen Institute of Research and Innovation Shenzhen 518057GuangdongChina Department of Health Technology and Informatics the Hong Kong Polytechnic UniversityHong Kong SAR 999077China Department of Rehabilitation Medicine the First Afliated Hospital of Nanchang UniversityNanchang 330006China Rehabilitation Medicine Clinical Research Center of Jiangxi Province Nanchang 330006China Beijing Key Laboratory of Learning and Cognition School of PsychologyCapital Normal UniversityBeijing 100048China School of Communication Science Beijing Language and Culture UniversityBeijing 100083China Institute of Electrical Engineering Yanshan UniversityQinhuangdao 066004HebeiChina School of Computer Science Wuhan UniversityWuhan 430072China School of Biomedical Engineering Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalian 116081LiaoningChina Guangdong Artifcial Intelligence and Digital Economy Laboratory(Guangzhou) Guangzhou 510335China.

Electroencephalography(EEG)is a non-invasive measurement method for brain *** to its safety,high resolution,and hypersensitivity to dynamic changes in brain neural signals,EEG has aroused much interest in scientific research and medical *** article reviews the types of EEG signals,multiple EEG signal analysis methods,and the application of relevant methods in the neuroscience feld and for diagnosing neurological ***,3 types of EEG signals,including time-invariant EEG,accurate event-related EEG,and random event-related EEG,are ***,5 main directions for the methods of EEG analysis,including power spectrum analysis,time-frequency analysis,connectivity analysis,source localization methods,and machine learning methods,are described in the main section,along with diferent sub-methods and effect evaluations for solving the same ***,the application scenarios of different EEG analysis methods are emphasized,and the advantages and disadvantages of similar methods are *** article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives,provide references for subsequent research,and summarize current issues and prospects for the future.

关键词： Electroencephalogram analysis methods Applied principles Neuroscience Diagnosis Neurological diseases

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：