检索结果-内蒙古大学图书馆

39th IEEE Power Electronics Specialists Conference (PESC 2008), vol.2

作者： Damien Coutellier Vassilios G. Agelidis Sewan Choi Department of Electrical and Control System Engineering University of Belfort Montbeliard France School of Electrical and Information Engineering University of Sydney NSW Australia Department of Control and Instrumentation Engineering Seoul National University of Technology South Korea

In transformer-less fuel-cell energy conversion systems the voltage-gain is required to be as high as possible. Although component parasitic elements limit the practically realizable voltage-gain of any converter topology, this becomes a critical issue in the case of the basic step-up converter. In this paper, a comparative evaluation of two high-voltage-gain interleaved step-up derived converter topologies suitable for fuel-cell applications is documented. Both converter topologies offer lower input-current/output-voltage ripple and lower voltage/current ratings of the various circuit elements when compared to the basic step-up topology. Analysis and simulation results are provided and experimental results taken from low power laboratory prototypes are presented.

关键词： Converters Topology Gain Transistors Capacitance Inductance Capacitors

来源：评论

学校读者我要写书评

暂无评论

Enhancing Traffic Flow Forecasting with Spatio-Temporal Information: A Case Study on Highway Networks in Belgium

Enhancing Traffic Flow Forecasting with Spatio-Temporal Info...

引用

International Conference on instrumentation control and Automation (ICA)

作者： Muhammad Farhan Fathurrahman Arne Catteeuw Sidharta Gautama Angel Lopez Aguirre Endra Joelianto Herman Y. Sutarto Department Of Industrial Systems Engineering and Product Design Ghent University Ghent Belgium Department of Intelligent System PT. Pusat Riset Energi (PRE) Bandung Indonesia FlandersMake@UGent–Corelab ISyE Lommel Belgium Instrumentation and Control Research Group Faculty of Industrial Technology Institut Teknologi Bandung Bandung Indonesia

As the number of vehicles continues to increase every year, it is crucial to monitor traffic conditions effectively. Traffic forecasting serves as a valuable method in traffic management to support decision making. This study investigates the impact of utilizing spatio-temporal data for traffic flow forecasting, as opposed to forecasting each location individually. We compare spatio-temporal Long Short-Term Memory (LSTM), a machine-learning technique that utilizes spatially correlated sensor data in a network, and compare this to conventional LSTM and Seasonal ARIMA (SARIMA). Experiments have been conducted on counting loop data of a highway network in Belgium. We have investigated the performances of the forecasting model for different prediction horizons. The results show that spatial information improves the performance of the forecasting model and reduces the training time required. Further analysis show that the spatio-temporal LSTM improves majorities of detectors while the minorities detectors are degraded which imply the importances of network selection. The computational load of the spatio-temporal LSTM model is minimally impacted by the number of sensors in the network thus making it scalable. The results show that longer prediction horizons degrade the forecasting performance but the impact up to a 12 hour-horizon is not significant.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Traffic Flow Estimation using Graph Neural Network with Aggregation of Traffic Features

Traffic Flow Estimation using Graph Neural Network with Aggr...

引用

International Conference on control, Automation, Robotics and Vision (ICARCV)

作者： Adiyana Putri Ferio Brahmana Endra Joelianto Herman Y. Sutarto Engineering Physics Doctoral Program Faculty of Industrial Technology Institut Teknologi Bandung Indonesia Artificial Intelligence Control and Automation Laboratory Faculty of Industrial Technology Institut Teknologi Bandung Indonesia Instrumentation and Control Research Group Faculty of Industrial Technology Institut Teknologi Bandung Indonesia Department of Intelligent System PT. Pusat Riset Energi (PRE) Bandung Indonesia

ISBN: (纸本)9781665476881

The increasing vehicle volume every year affects the prediction of the traffic system. The purpose of predicting traffic flow is to estimate the lost data caused by sensor malfunctions due to connection disruptions or ages. In estimating traffic flow, obtaining and explaining the historical data from the nearest segment sensor is necessary. The graph model can describe the spatial relationship between segments by connecting nodes with edges. Graph Neural Network (GNN) has been used as a learning method to predict the traffic flow in the segment sensor. GNN gets input in the form of spatial data built through a graph model, and the features are traffic density, average vehicle speed, and delay time on the road network. This paper shows that GNN's capability performs better in extracting spatial features and predicting the traffic flow by aggregating the features through connectivity nodes and edges.

关键词： Learning systems Roads Estimation Feature extraction Robot sensing systems Graph neural networks Spatial databases

来源：评论

学校读者我要写书评

暂无评论

Automated Design and Implementation of Resonant controllers for Current control of Shunt Active Filters

Automated Design and Implementation of Resonant Controllers ...

引用

2007 International Conference on Power Electronics and Drive systems (PEDS 2007), vol.1

作者： W. Lenwari M. Sumner P. Zanchetta Department of Control System and Instrumentation Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand School of Electrical and Electronic Engineering University of Nottingham Nottingham UK

This paper presents the automated design of resonant controllers for current control of three phase shunt active filters. The design methods employs a Genetic Algorithm (GA) based routine. The resonant control compensator is introduced in order to improve the control accuracy and performance for ac input signals. An accurate harmonic current control for shunt active filters can be achieved using resonant compensators. In this paper, the current control system is designed to operate with a single dq reference frame, synchronous with the 50 Hz supply voltage, for the compensation of all main harmonic currents, 5th, 7th, 11th and 13th. The design procedure and the principle of the proposed control method are presented. Experimental results confirm the accuracy and effectiveness of the GA-designed compensators, showing excellent harmonic current tracking performance.

关键词： Power Quality Harmonic Current control Shunt Active Filter Resonant controller

来源：评论

学校读者我要写书评

暂无评论

Drowsy Driver Detection system For Poor Light Conditions

Drowsy Driver Detection System For Poor Light Conditions

引用

2023 IEEE International Conference on Mechatronics (ICM)

作者： Ahmed Ibnouf Ayman Fadlallah Muaiz Ali Abdelmalek Zidouri Control & Instrumentation Engineering Department King Fahd University of Petroleum and Minerals (KFUPM) Dhahran Saudi Arabia Information & Computer Science Department King Fahd University of Petroleum and Minerals (KFUPM) Dhahran Saudi Arabia Electrical Engineering Department King Fahd University of Petroleum and Minerals (KFUPM) Dhahran Saudi Arabia Electrical Engineering Department Interdisciplinary Research Center for Intelligent Secure System King Fahd University of Petroleum and Minerals (KFUPM) Dhahran Saudi Arabia

In recent years, the number of car accidents has been gradually increasing. A major factor in this increase is the drowsiness of drivers. There are many image recognition research studies on drowsiness detection but tend to neglect the case of low-light conditions. This paper focuses on detecting drowsy drivers in low-light conditions. In this paper, a behavioralbased drowsy driver detection system (DDDS) was proposed. The proposed DDDS applies a preprocessing algorithm that improves illumination and then focuses on detecting the driver’s face and eyes to calculate eye blink duration. A deep neural network model was used for facial recognition, and Haar Cascade classifiers were used for eyes detection. Every single eye was based to a Convolutional Neural Network (CNN) model to predict its state as either ‘‘Open’’ or ‘‘Closed’’. The proposed CNN was developed using a dataset of 1452 samples and gave an accuracy of 97.92% on the testing dataset, 15% of the 1452 samples. Different case scenarios in poor light conditions were implemented to evaluate the proposed DDDS. The system was able to identify the state of the driver even in harsh and severe poor light conditions.

关键词： Deep learning Face recognition Transportation industry Lighting Safety Convolutional neural networks Standards

来源：评论

学校读者我要写书评

暂无评论

Human Following Robot Based on Object Detection for Aerospace Application

Human Following Robot Based on Object Detection for Aerospac...

引用

Aerospace Electrical engineering and Informatics (ICAAEEI), International Conference of Adisutjipto on

作者： Arwin Datumava Wahvudi Sumari Ahnaf Bagus Aryandika Ndaru Atmi Purnami Denny Dermawan Ika Noer Syamsiana Department of Electrical Engineering Cognitive Artificial Intelligence Research Group State Polytechnic of Malang Malang Indonesia Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Navigation Instrumentation Control Automation and Robotics System Research Group Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Digital System Microprocessor Microcontroller and Programmable Logic Devices Research Group Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia

ISBN: (数字)9798331507930

ISBN: (纸本)9798331507947

In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraft technicians by bringing maintenance tool kits to aircraft shelters. Rewang's movement is based on a camera as a vision sensor following the movement of human entities. Image input is processed by YOLO v3-Tiny through the determination of the bounding box, the calculation of Euclidean Distance, and the determination of the pixel value of the camera as the basis of Rewang's movement which is regulated by an L298N driver motor that controls two Direct Current (DC) motors for the left and right wheels. The test results show that Rewang can move at an average speed of 0.18 m/s at 2 m with a travel time of 11 seconds with a light intensity of more than 250 lux. The minimum and maximum distance of object detection is as far as 120 cm and 400 cm, with an object detection accuracy of 95.8%. Rewang allows the HFR to have a larger carrying capacity to bring more complete aircraft maintenance tools and is prospective for other aerospace and general applications.

关键词： YOLO Tensors Accuracy Prototypes Wheels Cameras Hardware Maintenance Aircraft Aerospace industry

来源：评论

学校读者我要写书评

暂无评论

Optimized Design of Modified Proportional-Resonant controller for Current control of Active Filters

Optimized Design of Modified Proportional-Resonant Controlle...

引用

IEEE International Conference on Industrial Technology

作者： Wanchak Lenwari Department of Control System and Instrumentation Engineering King Mongkut's University of Technology Thonburi(KMUTT) 126 Prachauthid Rd Bangmod Tungkru Bangkok Thailand

ISBN: (纸本)9781467345675

With the recent advances in power electronic technology, the increase of non-linear loads such as power converters has deteriorated power quality and sparked the research in power quality issue. Shunt Active filter(SAF) is a power electronic device developed to improve power quality. Proportional-resonant(PR) type controller appears to be appropriate for the control system in active filters, where the precise tracking performance of harmonic currents is required. However, due to the complexity of the controller structure, to obtain suitable controller parameters, it requires considerable design effort in particular for a non-expert. This paper presents an automated design procedure to optimize a modified proportional-multiple resonant controller for the compensation of all main order harmonics, the 5th,7th,11th,13th,17th and 19th harmonics. The principle of the proposed control method and the optimization procedure based on genetic algorithms are described in detail The excellent control performance has been carried out by simulations.

关键词： optimization modified proportional-resonant controller shunt active filters current control active filters Current control Optimal design Power quality controllers Optimization Procedure design effort control Methods current harmonics visual tracking control systems power conversion unit design process

来源：评论

学校读者我要写书评

暂无评论

High-Performance Nonlinear control for Three-Phase Two-Level Boost PFC Rectifier

High-Performance Nonlinear Control for Three-Phase Two-Level...

引用

2024 International Conference on Materials and Energy: Energy in Electrical engineering, ICOME-EE 2024

作者： Sriprang, Songklod Nahid-Mobarakeh, Babak Takorabet, Noureddine Pierfederici, Serge Siangsanoh, Apinya Yodmanee, Kanapot Mungporn, Pongsiri Thounthong, Phatiphat Poonnoy, Nitchamon Bizon, Nicu Suyata, Thong-In Noosawang, Sakrit Université de Lorraine GREEN-ENSEM Laboratory 54505 France Rajamangala University of Technology Rattanakosin Wang Klai Kangwon Campus Petchkasem RD Prachuap Khiri Khan77110 Thailand Université de Lorraine LEMTA Laboratory 54505 France Thailand Thai-French Innovation Institute King Mongkut's University of Technology North Bangkok Bangkok10800 Thailand Faculty of Technical Education Dept. Teacher Training in Electrical Engineering Thailand University of Pitesti Faculty of Electronics Communication and Computers Pitesti110040 Romania University of Technology Faculty of Rajamangala Department of Electrical Engineering Thanyaburi 39 Moo 1 Rangsit-Nakhonnayok Road Pathum Thani 12110 Thailand King Mongkut's University of Technology Thonburi Faculty of Engineering Dept. of Control System and Instrumentation Engineering Bangkok10140 Thailand

ISBN: (纸本)9798331531577

This paper presents a high-performance nonlinear control strategy for a three-phase, two-level boost Power Factor Correction (PFC) rectifier. The proposed control method aims to achieve superior performance in terms of power factor correction, output voltage regulation, and dynamic response under various operating conditions. Utilizing advanced nonlinear control techniques, the system ensures optimal tracking of the reference signals, minimizing total harmonic distortion (THD) and improving overall efficiency. The effectiveness of the control strategy is validated through extensive simulations and experimental results, demonstrating significant improvements in the transient and steady-state performance of the rectifier. This approach provides a robust and efficient solution for PFC applications in modern power electronics systems. © 2024 IEEE.

关键词： Nonlinear control systems

来源：评论

学校读者我要写书评

暂无评论

Quarry of modal information from environment for advanced motion control

引用

IEEJ Transactions on Industry Applications 2006年第4期126卷 372-378+1页

作者： Katsura, Seiichiro Ohnishi, Kouhei Department of Electrical Engineering Nagaoka University of Technology 1603-1 Kamitomiokamachi Nagaoka Niigata 940-2188 Japan Department of System Design Engineering Keio University 3-14-1 Hiyoshi Kohoku-ku Yokohama 223-8522 Japan Nagaoka University of Technology Nagaoka Niigata Japan IEEJ Japan IEEE Industrial Electronics Society Japan Society of Instrumentation and Control Engineers Japan Robotics Society of Japan Japan Keio University Yokohama Japan Nagaoka University of Technology Japan Keio University Japan

Motion control in open environment will be more and more important. The recent machines are required to have an ability to contact unknown environment. The environmental information is a key to be compliant to unknown environment. It is obtained from the modal decomposition. The environment may have infinite modes. On the contrary, motion control systems have finite number of degree-of-freedom (DOF) for their motion. It is necessary for motion controller to quarry information from the environment at least to the extents of DOF. This paper develops a novel viewpoint of motion control based on quarry of environmental information. A quarry process of information from the environment using Hadamard matrix has been proposed. An extension method of the Hadamard matrix is proposed and quarry matrix is generalized in this paper. This paper shows a quarry of the planar environmental modes using the third-order quarry matrix. The motion of a robot with three supporting points has three modes, which are heaving, rolling and pitching modes. As a result, compliant motion control to unknown environment is attained in each mode. The modal system design method based on the quarry matrix will be a fundamental technique of design of decentralized system.

关键词： Motion control

来源：评论

学校读者我要写书评

暂无评论

Biosignal-Based Attention Monitoring for Evaluating Train Driver Safety-Relevant Tasks

SSRN

引用

SSRN 2024年

作者： Kim, Jung Hwan Kim, Yeongjun Cho, Younggeol Kim, Tae Kyun Jang, Tongil Park, Chanwoo Kang, Seongkeun Advanced Instrumentation & Control Research Section Korea Atomic Energy Research Institute Daejeon Korea Republic of Department of Nuclear & Quantum Engineering Korea Advanced Institute of Science and Technology Daejeon Korea Republic of School of Computing Korea Advanced Institute of Science and Technology Daejeon Korea Republic of Department of Railroad Electrical & Electronic Engineering Korea National University of Transportation Uiwang Korea Republic of System Safety Research Department Korea Railroad Research Institute Uiwang Korea Republic of

This study explores the impact of phone usage on train driver performance, a critical aspect influencing the safety of railroad operations. The persistent problem of phone distractions, which severely impair situational awareness and contribute to accidents, necessitates innovative solutions to enhance operational safety. Leveraging advancements in technology, this study introduces a novel approach combining electroencephalogram (EEG)-based analysis with deep learning algorithms to assess the effects of phone usage on the attention states of train drivers. Utilizing a full-type train simulator to replicate real-life scenarios, this study conducts an experimental design involving scenarios with and without phone engagement, aiming to provide a comprehensive assessment of phone usage on performance in critical situations. The deep learning model employed achieved an impressive classification accuracy of approximately 85.6% in distinguishing attention states among 25 participants, with high precision and recall values indicating its efficacy in detecting phone interaction. Moreover, findings reveal that phone usage leads to a 1.4 times increase in response time to situational awareness, significantly affecting driver performance. These findings highlight the significant impact of phone usage on train driver attention and underscore the potential of EEG-based analysis and deep learning in improving railroad safety measures. This study contributes to the growing body of safety literature by focusing on train drivers, offering fresh insights and practical implications for enhancing the safety and efficiency of railroad operations. © 2024, The Authors. All rights reserved.

关键词： Railroads

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：