检索结果-内蒙古大学图书馆

Hybrid Deep Learning-Based Forecast of Weekly Power Demand Combining Attention-Mechanism

Transactions of the Korean Institute of Electrical Engineers 2024年第9期73卷 1507-1512页

作者： Yun, Sang-Cheol Kim, Byoungho Kim, Hongrae Dept. of Electronics and Information Engineering Soonchunhyang University Korea Republic of Dept. of Electrical and Robot Engineering Soonchunhyang University Korea Republic of

In the current situation of increasing power demand, research is needed for better electricity demand forecasting. This study presents a new approach to enhance the accuracy of electricity demand forecasting. The objective of this study is to facilitate more precise Load Forecasting by incorporating the Attention Mechanism into the existing deep learning models, LSTM and GRU. For this purpose, LSTM and GRU models combined with Attention Mechanism were applied to actual power demand data. The experimental results confirmed that the proposed model significantly improved the accuracy of power demand prediction compared to the existing models. These results show that the addition of Attention Mechanism can contribute to improving the performance of deep learning-based power demand prediction models. Copyright © The Korean Institute of Electrical Engineers.

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

Further Studies of A Proof of Utkin's Theorem for ITSMC of Second Order Uncertain Plants

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第10期72卷 1208-1220页

作者： Choi, Myeong-Soo Lee, Jung-Hoon Dept. of Control & Robot Engineering Gyeongsang National University Korea Republic of ERI Dept. of Control & Robot Engineering Gyeongsang National University Korea Republic of

In this paper, the two sliding surface part transformations are investigated for ITSMC (integral terminal sliding mode control) of second-order uncertain linear plants when the input gain uncertainty of the system is not zero i.e. ∆b≠0 as the further study of [33] and as the alternative methods of [33]. As highlighted in [33], the realm of designing ITSMCs encompasses five distinctive approaches: control input transformation, sliding surface full transformation, and three variations of sliding surface part transformations. While the discussion on the first three methods has been comprehensively covered in [33], this paper centers its focus on the previously unexplored last two transformations. These latter two transformations are presented as novel alternatives to the approaches detailed in [33]. The initial three transformations, as elucidated in [33], demonstrate a performance wherein the real output can be effectively predicted through the utilization of solutions derived from the ideal sliding dynamics. These solutions are thoughtfully pre-designed and predetermined through the application of the ideal sliding dynamics. This paper significantly contributes by presenting a comprehensive exploration of the last two transformation methods, achieving performance on par with the first three transformations described in [33]. These final two sliding surface part transformations stand as noteworthy design methodologies for ITSMCs with the same performance as in [33], offering alternative avenues in contrast to those laid out in [33]. The practical value of our key findings is effectively demonstrated through an illustrative example and an extensive simulation study, thereby underscoring the pertinence and applicability of our research outcomes. © The Korean Institute of Electrical Engineers.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

A Proof of Utkin's Theorem for ITSMC with Output Prediction of Second Order Uncertain Plants

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第5期72卷 628-642页

作者： Choi, Myeong-Soo Lee, Jung-Hoon Dept. of Control and Robot Engineering Gyeongsang National University Korea Republic of

In this paper, a complete proof of Utkin's theorem is presented for the ITSMC(integral terminal sliding mode control) of second order uncertain linear plants when ∆b≠0. The addition of integral action to the TSMCs so called the ITSMC enhances performance in both transient and steady states. Therefore, proof of Utkin's theorem is essential for ITSMC systems. There are five approaches to designing ITSMCs;control input transformation, sliding surface full transformation, and three sliding surface part transformations, which is for first time pointed out in this paper. The invariance property of the Utkin's theorem applies only to the first two transformations. Specifically, the sliding mode equation, i.e., the sliding surface, remains invariant for the first two transformations. However, the invariance property of Utkin's theorem can not apply to the three additional sliding surface part transformations, although they serve as design and stabilization approaches. The sliding surface full transformation first appears in the TSMCs, except in [32], while the three sliding surface part transformations appear for the first time in the TSMCs. This paper includes research on the first three transformations, and further studies will cover the last two sliding surface part transformations. This paper presents three transformation methods that achieve the same performances as those obtained through output prediction, predetermination, and predesign. Through an illustrative example and simulation study, the usefulness of the main results is verified. © The Korean Institute of Electrical Engineers This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://***/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Optimal Capacity of Electrolyzer and ESS connected Small Hydro Power Plant for Green Hydrogen Production

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第2期72卷 176-182页

作者： Do, Gyeong-Taek Kim, Sung-Yul Yoo, Seong-Yeol Dept. of Electronic and Electrical Engineering Keimyung University Korea Republic of Dept. of Robot Engineering Keimyung University Korea Republic of Dept. of Electrical Energy Engineering Keimyung University Korea Republic of

As renewable energy has been rapidly increasing, as renewable power outgrows load demand, power system reliability becomes a major issue. The ultimate solution for this issue is to store surplus energy without curtailment. Among the energy storage technology, P2G(Power-to-Gas) that convert and store surplus energy into hydrogen in MES(Multi Energy System) is the most resonable solution. In addition, it is more economical feasible when using electrolyzer connected hydro power plant. For stable electrolyzer operation, In this paper, we derive scheduling by considering the operating characteristics of the electrolyzer. And we estimate the optimal capacity of ESS, electrolyzer connected hydro power usint optimization. As a result of the simulation, the NPV(Net Present Value) is maximum when the capacity of the electrolyzer is 265 kW. Copyright ©The Korean Institute of Electrical Engineers.

关键词： Hydroelectric power plants

来源：评论

学校读者我要写书评

暂无评论

Decentralized observer based output tracking for linear time-invariant interconnected systems 2

Decentralized observer based output tracking for linear time...

引用

2nd IEEE International Conference on Electrical engineering, Big Data and Algorithms, EEBDA 2023

作者： Mao, Zhengji Tseng, Yenming Putian University Dept. Robot Engineering Putian China

ISBN: (纸本)9781665462532

A decentralized observer based output tracking method for linear time-invariant interconnected systems with unmeasurable states is proposed. These interactions imposed on each subsystem are all the subsystem outputs and through all affected subsystem inputs. Since only the subsystem outputs is available, we develop observation models to obtain good estimations of states by optimal control techniques. For the output tracking, by introducing some extra states, the decentralized feedback law is solved by solving the optimal performance index subjected to the augmented subsystems. The interaction term from its own subsystem can be considered as some uncertainty of the subsystem. The overall system formed by the original states and reconstructional errors are conducted and proved exponentially stable. © 2023 IEEE.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

A Study on Training Data Mixing and Selection Methods for Detecting the Sounds of Faulty Machinery

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第7期73卷 1232-1238页

作者： Kim, Tae-Won Cho, Sang-Muk Kim, Dong-Hyeon Kim, Hyun-Don Kim, Do-Yoon WITHROBOT INC. Seoul Korea Republic of Dept. of Intelligent Mechatronics Engineering Sejong University Korea Republic of Korea Polytechnics University Robot Campus Korea Republic of

To train a classifier using a Deep Neural Network (DNN), a substantial amount of data sets is required. However, in cases where data acquisition is challenging or the environment undergoes changes, obtaining sufficient data for training can be problematic. Data augmentation and synthesis can be used to increase the quantity of data for training. The data generated through augmentation or synthesis should closely resemble real data and accurately reflect the environments and characteristics that users aim to model. Without this resemblance, using the generated data may not yield the desired results in the actual environment. In this paper, we propose an empirical method for selecting synthetic training data that enhances the performance of a belt conveyor fault classifier model in environments where data acquisition is challenging, without compromising the existing performance of the model. Copyright © The Korean Institute of Electrical Engineers.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Interactive robot-robot Reinforcement Learning for Object Balancing Task

Interactive Robot-Robot Reinforcement Learning for Object Ba...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Kim, Yewon Jeon, Haein Kang, Bo-Yeong Kyungpook National University Dept. of Artificial Intelligence Daegu41566 Korea Republic of Kyungpook National University Dept. of Robot and Smart System Engineering Daegu41566 Korea Republic of

ISBN: (纸本)9798350324136

robots with machine learning are expanding their application fields, such as serving robots and guiding robots, but applying machine learning to robots has a high labor cost due to human intervention. This paper proposes interactive robot-robot reinforcement learning technology to minimize human intervention in learning tasks that successfully balance objects between two robots. In this proposed technique, the teacher and student robot guide and learn object balancing based on reinforcement learning. Teacher robot teaches knowledge that has not been learned in advance to student robot, and teaches more effectively by providing various positive and negative text feedback on the training results. In virtual simulations, the training results of the student robot converge to the optimal policy as an evaluation result of the proposed method, and the trained student robot performs appropriate actions according to various table states by the teacher's random action. Through our experimental results, the application possibility of robot-robot learning is verified being as good as human-robot learning. Our proposed method could be utilized to seamlessly transfer the learned knowledge when it is challenging to apply the learning model to a heterogeneous robot or an agent in an IoT environment. © 2024 IEEE.

关键词： cooperative robot interactive reinforcement learning reinforcement learning robot-robot learning

来源：评论

学校读者我要写书评

暂无评论

Robust Decentralized Regulation for Linear Time-varying Interconnected Systems via Time-varying Riccati Equations 3

Robust Decentralized Regulation for Linear Time-varying Inte...

引用

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing, AIAHPC 2023

作者： Mao, Zheng Ji Lin, Zhen Heng Dept. of Robot Engineering Putian University Putian351100 China School of New Engineering Industry Putian University China

ISBN: (数字)9781510666580

ISBN: (纸本)9781510666573

This paper introduces a robust decentralized regulation approach of linear interconnected time-varying systems. If the optimal optimization problems of time-varying systems are considered, the solution of time-varying Riccati differential equation should be involved and pre-calculated. The weighting parameters of the optimal performance index in this paper are all time-varying. The optimal solution relies on the initial conditions of the solutions of Riccati differential equations and these initial conditions are derived by the backward Euler’s method. Then the obtained optimal control gain is modified to accommodate the interactions among the subsystems. The overall system are mathematically proved to be exponentially stable with a prescribed degree of stability. Computer simulations of a time-varying example composed of three subsystems are conducted to demonstrate the feasibility of this approach. © 2023 SPIE.

关键词： Riccati equations

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis by Machine Learning of Waste Biodiesels in CI Engine 6

Comparative Analysis by Machine Learning of Waste Biodiesels...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Dhanumjaya, Mora Venkata Kocherla, Akhilesh Krishna, Jeripiti Rama Sethu, Mylavarapu Singh, Tripty Mandal, Adhirath Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Pai Chai University Dept. Drone-Robot Engineering Korea Republic of

ISBN: (纸本)9798350381689

The escalating worries regarding environmental sustainability and the exhaustion of fossil fuel resources have sparked concerns and extensive exploration for substitute fuels for internal combustion engines are being conducted alternative fuels for internal combustion engines are being conducted. In the current investigation prophecy of engine and emissions performance on a CI Engine using waste fry biofuel was carried out, by utilizing cutting-edge Machine Learning (ML) and Deep Learning (DL) techniques. Experimental records from engine tests under diverse RPM and load condition are scrutinized with these algorithms. Various algorithms and training functions were employed to educate the models. The analysis establishes that waste fry biofuel has a momentous influence on engine performance, encompassing brake thermal efficiency and specific fuel consumption, while also diminishing detrimental emissions such as NOx (Nitrogen Oxides), smoke, and CO (Carbon Monoxide). ML and DL models aid in foretelling engine operation and emission control strategies, accentuating the potential of waste fry biofuel as a sustainable and environmentally friendly alternative to traditional diesel fuel. © 2024 IEEE.

关键词： Biodiesel

来源：评论

学校读者我要写书评

暂无评论

Leg-Pattern Modeling for Swimming of Underwater Walking robot Considering Hydrodynamic Forces

Leg-Pattern Modeling for Swimming of Underwater Walking Robo...

引用

OCEANS 2024 - Halifax, OCEANS 2024

作者： Choi, Hyeonjung Jun, Bong-Huan Yoo, Seong-Yeol Keimyung University Dept. of Mechanical Engineering Daegu Korea Republic of Korea Research Institute of Ships & Ocean Engineering Ocean and Maritime Digital Technology Research Division Daejeon Korea Republic of Keimyung University Dept. of Robot Engineering Daegu Korea Republic of

ISBN: (纸本)9798331540081

The needs for underwater robots increased to explore and develop ocean resources safely and efficiently. Traditionally propeller-based ROVs(Remotely Operated Vehicles) and AUVs(Autonomous Unmanned Vehicles) have been used for ocean exploration and development. However, over the past decade, a new type of underwater robot that uses legs has emerged. These robots offer advantages such as stable movement over uneven or complex sea floor terrains and minimizing ecosystem disruption. However, due to legged locomotion, they have slower movement speeds compared to traditional underwater robots. To overcome this limitation, a swimming function using legs has been introduced. This paper aims to discuss the design of the swimming motion for underwater legged robots. Additionally, we define the hydrodynamic resistance that occurs due to swimming with legs underwater and calculate it to determine the thrust generated during swimming. © 2024 IEEE.

关键词： Remotely operated vehicles

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：