检索结果-内蒙古大学图书馆

8th International Conference on engineering, Applied Sciences, and Technology, ICEAST 2022

作者： Srinangyam, Chissanupong Pannil, Pittaya Thungsook, Kittisak Promwong, Sathaporn Nimsanong, Phethai Pattanadech, Norasage School of Engineering King Mongkut's Institute of Technology Ladkrabang Electrical Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Instrumentation and Control Engineering Dept. Bangkok Thailand School of Engineering Rajamangala University of Technology Rattanakosin Electrical Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Telecommunication Engineering Dept. Bangkok Thailand Power System Operation and Control Section 2 Power System Control Dept. Metropolitan Electricity Authority Bangkok Thailand

ISBN: (数字)9781665459198

ISBN: (纸本)9781665459198

This paper discusses signal transmission in the grounding system. During online partial discharge (PD) measurement for the high voltage (HV) apparatus, various PD pulse currents recharge the dielectric of HV apparatus when a PD occurs. One of the noise typologies that affects PD patterns is called the cross-talk, that is, discharges that appear in the measured point due to coupling from another point. In order to study the cross-talk signal, the two PD measuring circuits which are circuit no.1 and circuit no.2, on the same grounding system in the HV laboratory were performed. The distance between two PD measuring circuits is about 20 meters. The artificial PD models were utilized to generate the PD signal injecting to the test circuit no.1, while the cross-talk signals were investigated in circuit no.2. The HFCT sensors were used to measure the PD signal in circuit 1 and the cross-talk signal in circuit 2. The measurement results found that the cross-talk signal transmission in grounding systems provides a bipolar PRPD pattern, and the pulse waveform shows an oscillation shape. Moreover, onsite PD measurements of the generator steam turbine were studied. It is noticeable that the knowledge about cross-talk phenomena in grounding systems can help the PD verification and location for online PD measurement. © 2022 IEEE.

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

Failure Detection from the Knocking Sounds Using Convolutional Neural Network

Failure Detection from the Knocking Sounds Using Convolution...

引用

IEEE Region 10 International Conference TENCON

作者： Punyapat Areerob Rithea Sum Chanon Khongprasongsiri Sudchai Boonto Department of Control System and Instrumentation Engineering King Mongkut's University of Technology Thonburi Bangkok Thailand National Astronomical Research Institute Thailand

Toilet quality assurance is a crucial process in ensuring lavatories meet rigorous performance, durability, and hygiene standards. The current standard of Maximum Performance (MaP) testing faces challenges, leading researchers to explore innovative approaches such as sound source classification for quality assurance. This approach involves collecting a diverse dataset of lavatory sounds and extracting relevant acoustic features. Deep learning models, particularly convolutional neural networks (CNNs), are trained on these features to accurately classify sound sources. The trained models were evaluated and compared by considering metrics such as classification accuracy, computational complexity, and model parameters. This paper performs these tests and chooses the most effective model to enhance the quality assurance process for toilets. Incorporating sound source classification techniques has several benefits, including the optimization of testing processes, non-intrusive performance assessment, and efficient resource utilization through targeted testing and troubleshooting. By improving the standards of lavatory quality, this approach ensures enhanced performance, durability, and hygiene of lavatories.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarially Robust Reinforcement Learning for Urban Traffic Signal control

Adversarially Robust Reinforcement Learning for Urban Traffi...

引用

International Conference on Technology, Informatics, Management, engineering, and Environment (TIME-E)

作者： Muhammad Shafly Hamzah Endra Joelianto Herman Yoseph Sutarto Adiyana Putri Instrumentation and Control Master Program Institut Teknologi Bandung Bandung Indonesia Instrumentation Control and Automation Research Group Institut Teknologi Bandung Bandung Indonesia Department of Intelligent System PT. Pusat Riset Energi Bandung Indonesia Doctoral Program of Engineering Physics Institut Teknologi Bandung Bandung Indonesia

ISBN: (数字)9798350364750

ISBN: (纸本)9798350364767

Urban traffic congestion presents critical challenges, resulting in delays, environmental pollution, and significant economic costs. While traditional traffic control methods, such as fixed-time and adaptive systems, have been widely implemented, they often fail in unpredictable conditions, particularly when confronted with noisy or inaccurate data. This research proposes a robust reinforcement learning (RL) solution for traffic signal control using the RADIAL-DQN (Robust Adversarial Loss DQN) algorithm. Integrating adversarial training enhances the system's robustness to real-world uncertainties. Evaluations conducted using a SUMO traffic simulation show that the robust agent produced an increase of only 60.71% in queue length under a projected gradient descent (PGD) adversarial attack, outperforming standard RL agents, which experienced an 89% increase. These results demonstrate the potential of robust RL to improve both the reliability and scalability of urban traffic control systems.

关键词： Training Adaptive systems Uncertainty Scalability Urban areas Traffic control Robustness Standards Traffic congestion Testing

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Several pH control Laws Implemented to a Smart Hydroponics Farm

A Comparative Study of Several pH Control Laws Implemented t...

引用

International Conference on control, Automation and systems ( ICCAS)

作者： Thienrawit Tongskulroongruang Tanagorn Jennawasin Department of Control System and Instrumentation Engineering King Mongkut’s University of Technology Thonburi Bangkok Thailand

In this work, we built the hydroponic farm to collect data for creating mathematical models such as transfer functions, state space and ARX models. After that, we create a plant model and design 3 controllers including PID, MPC and adaptive MPC (AMPC). In addition, we create a disturbance model with a transfer function from individual data. Afterward, we defined 2 scenarios for the experiment, including a nominal system and a system with noise and disturbance scenarios. In order to evaluate these performances of controller, we consider integral of absolute error (IAE), integral of square error (ISE), integral of absolute control input (IACI) and integral of square control input (ISCI) score.

关键词： Adaptation models Automation Hydroponics Transfer functions Aerospace electronics control systems Mathematical models

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 1

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

引用

1st International Conference of Adisutjipto on Aerospace Electrical engineering and Informatics, ICAAEEI 2024

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

ISBN: (纸本)9798331507930

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. © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Embedded Device Development and Real-Time Analysis for Unexpected Operations of Motors

IoT-Based Embedded Device Development and Real-Time Analysis...

引用

Measurement instrumentation and Electronics (ICMIE), International Conference on

作者： Teerapat Riyota Panuthat Boonpramuk Santi Nuratch Department of Control System and Instrumentation Engineering King Mongkut’s University of Technology Thonburi KMUTT Bangkok Thailand

ISBN: (纸本)9781665468442

In most industrial automation systems, all machines and equipment must operate smoothly and continuously to maintain the system performance. Therefore, all kinds of unexpected failures of the system cannot be accepted. For this reason, the maintenance processes are the essential operations performed periodically to avoid system failures. Of course, this operation takes time and resources, but it cannot be avoided. It is known that most automation systems compose of electrical motors. They are the core devices for robots and other movable machines. Each motor produces meaningful parameters such as temperature, vibration, speed, noise, and power consumption. This paper presents the design and development techniques of the IoT-based embedded device that can be used for real-time monitoring and analysis of the unexpected operations of motors. The proposed device continuously senses and analyzes motor parameters to monitor and predict unexpected operations. We focus on temperature and unbalanced phenomenal measurement of the motors. The unbalanced parameter is implicitly measured from the speed changes using the time measurement of the sensing signals. The proposed device also supports wireless real-time data exchange to the server. The device and server exchange their data using the WebSockets protocol. The data sent to the server can be used for storage, processing, and monitoring. In this work, we also develop a web-based application that allows users to control and monitor the parameters of motors in real-time. The experimental results show that the proposed method can detect the unbalance operations and temperature of the motors at different operations. Therefore, the proposed system can be used in real-world applications that require abnormality detection, abnormal condition warning, and prediction of mechanical devices.

关键词： Temperature measurement Temperature sensors Wireless communication Wireless sensor networks Automation Microcontrollers Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Parallel Byzantine fault tolerance method for blockchain

Parallel Byzantine fault tolerance method for blockchain

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Dubey, Kumar Pradyot Gnanaprakasam, C.N. Khan, Ihtiram Raza Sadik, Md Shibli Al-Farhani, Liwa H. Ray, Samrat Department of Computer and Information Science Jagadguru Ram Bhadracharya Divyanga University UP Chitrakoot India Department of Electronics and Instrumentation Engineering St. Joseph’s College of Engineering Tamilnadu Chennai India Computer Science Department Jamia Hamdard Delhi India University of Portsmouth Portsmouth United Kingdom System Analysis Control and Information Processing Dep Academy of Engineering RUDN University Moscow Russia The Institute of Industrial Management Economics and Trade Peter The Great Saint Petersburg Polytechnic University Russia

ISBN: (纸本)9781032669663

Enterprise-focused blockchain applications that offer safe, anonymous, and immutable transactions are growing as blockchain technology matures. Traditional blockchain architecture has low performance and scalability, making it unsuitable for enterpriselevel applications with high concurrency and massive data. This paper studies and proposes a simplified Byzantine fault-tolerant (SBFT) consensus algorithm to improve consensus stage efficiency, a Task parallel smart contract model to maximise multi-core system parallel efficiency, and an improved blockchain system architecture to reflect the lightweight, low coupling nature of blockchain technology. It facilitates corporate application secondary development and the ParaChain blockchain and smart contract technology. Experimental verification compares the parallelization - based ParaChain blockchain’s TPS and scalability. PBFT-based blockchain systems have been greatly improved. © 2024 The Author(s).

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Designing of Delta Manipulator as Human-Robot Interaction for Collaborative Mobile Robot

Designing of Delta Manipulator as Human-Robot Interaction fo...

引用

SICE Annual Conference

作者： Siritakorn Sutthi Adul Phaiyakarn Suwapich Prueksakunnatam Issarapong Khuankrue Chettapong Janya-Anurak Department of production Engineering King Mongkut’s University of Technology Thonburi Bangkok Thailand Department of Control System and Instrumentation Engineering King Mongkut’s University of Technology Thonburi Bangkok Thailand

This research aims to develop an adaptable and advanced human-robot interaction system for collaborative mobile robots. A delta manipulator with a series elastic actuator is designed as a collaborative medium between humans and mobile robots. The design of the delta manipulator as a human-robot interaction interface and its kinematics are presented. Three control strategies for translational motion and two control strategies for rotational motion are studied and discussed based on their advantages and disadvantages, depending on specific application requirements. This design approach enables the creation of a comprehensive controller system that can effectively command the mobile robot to perform a wide range of movements and maneuvers, enhancing its overall performance and versatility. The resulting system efficiently accomplishes complex tasks in various scenarios, making it a valuable tool for a range of applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cooperation of Autonomous Mobile Robots with Different Maneuverability in Transportation

Cooperation of Autonomous Mobile Robots with Different Maneu...

引用

SICE Annual Conference

作者： Pete Rangsichamras Natchanon Wittayaarereekul Satjaban Tantinarasak Issarapong Khuankrue Chettapong Janya-Anurak Department of production Engineering King Mongkut’s University of Technology Thonburi Bangkok Thailand Department of Control System and Instrumentation Engineering King Mongkut’s University of Technology Thonburi Bangkok Thailand

This study proposes a cooperative transportation system, which uses multiple autonomous mobile robots with different maneuverability cooperating together to transport a rigid object. The system uses a leader-follower formation control strategy, by using the non-holonomic leading the way while the holonomic AMRs follow. The object is assumed as a constraint between the robots, and the cooperation is tested using a designed destination point, in which each follower robot receives commands from the leader sent through the laptop. To walk straight, all robots receive the same command, but for rotating, leader robot must evaluate the command for the follower robots by the designed method. The Robot Operating system (ROS) is used for the development of the robots and for standard communication. The proposed method is validated through simulation tasks using autonomous mobile robots with different wheel types. The results of the experiments have resulted and supported that holonomic and non-holonomic robots being able to cooperate with each other’s in transportation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PreAdaptFWI: Pretrained-Based Adaptive Residual Learning for Full-Waveform Inversion Without Dataset Dependency

arXiv

引用

arXiv 2025年

作者： Dong, Xintong Yuan, Zhengyi Lin, Jun Dong, Shiqi Tong, Xunqian Li, Yue College of Instrumentation and Electrical Engineering Jilin University Changchun130026 China Key Laboratory of Modern Power System Simulation and Control and Renewable Energy Technology Northeast Electric Power University Jilin132012 China College of Communication Engineering Jilin University Changchun130012 China

Full-waveform inversion (FWI) is a method that utilizes seismic data to invert the physical parameters of subsurface media by minimizing the difference between simulated and observed waveforms. Due to its ill-posed nature, FWI is susceptible to getting trapped in local minima. Consequently, various research efforts have attempted to combine neural networks with FWI to stabilize the inversion process. This study presents a simple yet effective training framework that is independent of dataset reliance and requires only moderate pre-training on a simple initial model to stabilize network outputs. During the transfer learning phase, the conventional FWI gradients will simultaneously update both the neural network and the proposed adaptive residual learning module, which learns the residual mapping of large-scale distribution features in the network’s output, rather than directly fitting the target mapping. Through this synergistic training paradigm, the proposed algorithm effectively infers the physically-informed prior knowledge into a global representation of stratigraphic distribution, as well as capturing subtle variations in inter-layer velocities within local details, thereby escaping local optima. Evaluating the method on two benchmark models under various conditions, including absent low-frequency data, noise interference, and differing initial models, along with corresponding ablation experiments, consistently demonstrates the superiority of the proposed approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Stratigraphy

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：