检索结果-内蒙古大学图书馆

2024 IEEE Global Energy Conference, GEC 2024

作者： Cakmak, Fevzi Aykat, Sukru Kazanbaş, Mehmet Cemil Akgul, Sabahattin Department of Electricity and Energy Mardin Atuklu University Mardin Turkey Department of Computer Engineering Mardin Atuklu University Mardin Turkey Department of Control and Automation Engineering Yildiz Technical University Istanbul Turkey Department of Handicrafts Mardin Atuklu University Mardin Turkey

ISBN: (纸本)9798331532611

The connection of large-scale RES (renewable energy source) to the grid and the increase in the efficiency of energy production also causes different power quality problems. It has become mandatory for these inverter-based systems to participate in load frequency control. For this purpose, the design and simulation of a virtual synchronous generator (VSG), which enables RES to operate like synchronous generators, has been carried out in Matlab/Simulink environment. It is observed that the VSG keeps the load frequency stable according to different load conditions. ©2024 IEEE.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

Analysis of the PV Energy Potential in the Bulgarian Danube River Region between Ruse and Silistra 5

Analysis of the PV Energy Potential in the Bulgarian Danube ...

引用

5th IEEE International Conference on Communications, Information, Electronic and Energy Systems, CIEES 2024

作者： Gabrovska-Evstatieva, Katerina Stoyanov, Ivaylo Kaneva, Tsvetelina Valov, Nikolay Tsankov, Vladimir Evstatiev, Boris Mihailov, Nicolay University of Ruse Dept. of Computer Science Ruse Bulgaria University of Ruse Dept. of Electric Power Engineering Ruse Bulgaria University of Ruse Dept. of Computer Systems and Technologies Ruse Bulgaria University of Ruse Dept. of Automation and Electronics Ruse Bulgaria

ISBN: (纸本)9798350352863

The goal of the study is to assess and compare the photovoltaic energy potential in the central-eastern part of the Bulgarian Danube region between the cities of Ruse and Silistra. To achieve this the solar radiation and the temperature of the environment should be obtained and analyzed. The goal of the study is to assess and compare the photovoltaic energy potential in the central-eastern part of the Bulgarian Danube region between the cities of Ruse and Silistra. To achieve this the solar radiation and the temperature of the environment should be obtained and analyzed. The goal of the study is to assess and compare the photovoltaic energy potential in the central-eastern part of the Bulgarian Danube region between the cities of Ruse and Silistra. To achieve this the solar radiation and the temperature of the environment should be obtained and analyzed. © 2024 IEEE.

关键词： Solar irradiance

来源：评论

学校读者我要写书评

暂无评论

Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners 41

Planning, Fast and Slow: Online Reinforcement Learning with ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wu, Chengjie Hu, Hao Yang, Yiqin Zhang, Ning Zhang, Chongjie Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China Institute of Automation Chinese Academy of Sciences China Department of Computer Science & Engineering Washington University St. LouisMO United States

The surge in volumes of video data offers unprecedented opportunities for advancing reinforcement learning (RL). This growth has motivated the development of passive RL, seeking to convert passive observations into actionable insights. This paper explores the prerequisites and mechanisms through which passive data can be utilized to improve online RL. We show that, in identifiable dynamics, where action impact can be distinguished from stochasticity, learning on passive data is statistically beneficial. Building upon the theoretical insights, we propose a novel algorithm named Multiscale State-Centric Planners (MSCP) that leverages two planners at distinct scales to offer guidance across varying levels of abstraction. The algorithm's fast planner targets immediate objectives, while the slow planner focuses on achieving longer-term goals. Notably, the fast planner incorporates pessimistic regularization to address the distributional shift between offline and online data. MSCP effectively handles the practical challenges involving imperfect pretraining and limited dataset coverage. Our empirical evaluations across multiple benchmarks demonstrate that MSCP significantly outperforms existing approaches, underscoring its proficiency in addressing complex, long-horizon tasks through the strategic use of passive data. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Model-Driven Approach for Consistent Building automation Control Logic Design and Deployment

A Model-Driven Approach for Consistent Building Automation C...

引用

International Conference on Control, automation and Diagnosis (ICCAD)

作者： Felix Knorr Jürgen Pannosch Gernot Steindl Institute of Computer Engineering Research Unit of Automation Systems TU Wien Vienna Austria

ISBN: (数字)9798350361025

ISBN: (纸本)9798350361032

This paper introduces an innovative model-driven approach for seamlessly integrating control logic into the building planning phase, ensuring consistency throughout deployment. Leveraging an open building information model (BIM), the approach enables model engineers to embed control logic directly into the BIM using an open language. The integrated model facilitates automatic extraction of control logic information, supporting efficient modifications. A proof-of-concept implementation using SIMULTAN, IEC 61131-3 Structured Text, and IDA ICE demonstrates successful deployment in a Heating, Ventilation, and Air Conditioning (HVAC) use case.

关键词： Heating systems HVAC Atmospheric modeling Buildings Ventilation Logic design Planning

来源：评论

学校读者我要写书评

暂无评论

Deep Transmission Estimation Based on Dark Channel Prior for Low-light Image Enhancement

Deep Transmission Estimation Based on Dark Channel Prior for...

引用

International Conference on computer engineering and Applications (ICCEA)

作者： Caiju Wang Fei Li Nianyi Pan Xiaomao Li School of Computer Engineering and Science Shanghai University China School of Mechatronic Engineering and Automation Shanghai University China Research Institute of USV Engineering & School of Mechatronic Engineering and Automation Shanghai University China

ISBN: (数字)9798350386776

ISBN: (纸本)9798350386783

This paper proposes a novel method, transmission parameter estimation network (TPENet), which aims to address the lack of adaptivity in luminance improvement when applying the dark channel defogging model for low-light image enhancement. TPENet studies a parameter mapping which adaptively adjusts the enhancement degree of each pixel in the image. In addition, a self-regularization mechanism (SRM) is introduced to weight the parameter mapping according to the average luminance level of the input image to achieve macro-adaptive adjustment. Finally, a series of meticulously constructed non-reference loss functions optimizes luminance, chromaticity, and spatial coherence. Extensive experimental data show that the TPENet has excellent performance in terms of luminance, chroma, and naturalness, as well as good generalization and robustness over multiple datasets.

关键词： Adaptation models Parameter estimation Computational modeling Channel estimation Spatial coherence Light scattering Estimation

来源：评论

学校读者我要写书评

暂无评论

An Image-Based Imitation Learning Framework for Robotic Writing Tasks 30

An Image-Based Imitation Learning Framework for Robotic Writ...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Xu, Wenjin Li, Xiaolong Li, Qingmin Yang, Chenguang School of Automation Science and Engineering South China University of Technology Guangzhou China University of Liverpool Department of Computer Science Liverpool United Kingdom Chuangze Intelligent Robot Group Co. Ltd China

ISBN: (纸本)9798350391916

Robotic writing, particularly in the realm of traditional Chinese calligraphy, poses unique challenges due to the intricate nature of stroke patterns and the high precision required. This paper presents an innovative image-based imitation learning framework designed to address these challenges by enabling robots to acquire and generalize writing skills from static images. By transforming static images into dynamic formats and incorporating a novel deviation analysis method, the framework enhances the learning of stroke thickness and allows for skill generalization across different writing scenarios. The proposed framework's effectiveness is demonstrated through extensive simulations and real-world experiments. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Delay-Guaranteed Path Selection and Scheduling in IAB Networks

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Eftetahi, Pooria Seyed Cai, Lin Ren, Xiangyu Department of Electrical and Computer Engineering University of Victoria VictoriaBC Canada Department of Electrical & Computer Engineering the University of Victoria Canada Department of Automation Engineering University of Electronic Science and Technology of China Chengdu China

Integrated access and backhaul (IAB) is a promising solution to improve coverage at low deployment costs. In IAB networks, due to wireless channel variations, guaranteeing delay for delay-sensitive applications is a major challenge. Given the random traffic arrivals and channel variations, using a central controller for packet-level delay management becomes infeasible due to the added delay from the central controller. In this paper, we propose a distributed cross-layer method to provide delay-guaranteed path selection and scheduling for the IAB network where priority queues and weighted round robin are adopted to deliver differentiated services. Our goal is to determine the optimal path and scheduling decisions to maximize the total utility of the IAB network. We deploy an iterative approach in a distributed manner to solve the maximization problem at each IAB-node. Through simulation, we show that our proposed solution guarantees the delay at the packet-level while achieving considerable gains in terms of delay and packet delivery ratio compared to the state-of-the-art. © 2015 IEEE.

关键词： Delay-sensitive applications

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter Integration in Orientation Measurement Systems with MEMS Sensors Under Dynamic Conditions 34

Kalman Filter Integration in Orientation Measurement Systems...

引用

34th International Scientific Symposium Metrology and Metrology Assurance, MMA 2024

作者： Dichev, Dimitar Zhelezarov, Iliya Kupriyanov, Oleksandr Malakov, Ivo Georgiev, Borislav Pulov, Dimcho Dicheva, Ralitza Kovachev, Hristofor Technical University of Gabrovo Department of Machine and Precision Engineering Gabrovo Bulgaria Ukrainian Engineering Pedagogics Academy Department of Information Computer Technologies and Mathematics Kharkiv Ukraine Technical University of Sofia Department of Automation of Discrete Production Engineering Sofia Bulgaria Technical University of Sofia Department of Precision Engineering and Measurement Instruments Sofia Bulgaria

ISBN: (纸本)9798350352832

This paper examines the integration of Kalman filter and Fuzzy algorithm in orientation measurement systems with MEMS sensors under dynamic conditions. The presented methodology aims to improve the accuracy and reliability of measurements by combining the advantages of both methods. The Kalman filter provides optimal state estimation by combining information from various sources and models, which reduces the influence of inertial disturbances and noise in the measurements. The fuzzy algorithm further improves the control and correction of measurements, especially at high speeds and rapid changes in the direction of movement. The proposed methodology for determining the variances in the Q and R matrices, based on the analysis of data from the MEMS gyroscope and the measurement system, demonstrates practical applicability and efficiency. This makes it suitable for a wide range of applications such as aviation, marine navigation, robotics, and autonomous transport systems, providing a basis for future research and optimization of algorithms for data processing and orientation control of moving objects. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Uniform gradient magnetic field and spatial localization method based on Maxwell coils for virtual surgery simulation

Uniform gradient magnetic field and spatial localization met...

引用

作者： Huang, Yi Deng, Xutian Zhao, Xujie Xie, Wenxuan Yuan, Zhiyong Zhao, Jianhui School of Computer Science Wuhan University Wuhan China School of Computation Information and Technology Technical University of Munich Munich Germany School of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

With the development of virtual reality technology, simulation surgery has become a low-risk surgical training method and high-precision positioning of surgical instruments is required in virtual simulation surgery. In this paper we design and validate a novel electromagnetic positioning method based on a uniform gradient magnetic field. We employ Maxwell coils to generate the uniform gradient magnetic field and propose two positioning algorithms based on magnetic field, namely the linear equation positioning algorithm and the magnetic field fingerprint positioning algorithm. After validating the feasibility of proposed positioning system through simulation, we construct a prototype system and conduct practical experiments. The experimental results demonstrate that the positioning system exhibits excellent accuracy and speed in both simulation and real-world applications. The positioning accuracy remains consistent and high, showing no significant variation with changes in the positions of surgical instruments. © 2024 John Wiley & Sons Ltd.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Iterative Noisy-Target Approach: Speech Enhancement Without Clean Speech 18th

Iterative Noisy-Target Approach: Speech Enhancement Without ...

引用

18th National Conference on Man-Machine Speech Communication, NCMMSC 2023

作者： Zhang, Yifan Jiang, Wenbin Zhuo, Qing Yu, Kai MoE Key Lab of Artificial Intelligence X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Communication Engineering Hangzhou Dianzi University Hangzhou China Department of Automation Tsinghua University Beijing China

ISBN: (纸本)9789819706006

Traditional Deep Neural Network based speech enhancement usually requires clean speech as the target of training. However, limited access to ideal clean speech hinders its practical use. Meanwhile, existing self-supervised or unsupervised methods face both unsatisfactory performance and impractical source demand (e.g., various kinds of noises added to the same clean speech). Hence, there’s a significant need to either release the restriction of training data or improve the performance. In this paper, we propose a training strategy that only requires noisy speech and noise waveform. It primarily consists of two phases: 1) With a pair of input and target constructed by adding noise to noisy speech itself for the training of DNN, the first round of training uses noisier speech (noise added to noisy speech) and noisy speech 2) For the following training, using the model trained last time to refine the noisy speech, construct new noisier-noisy pairs for next turn of training. Moreover, to accelerate the process, we apply the iteration into epochs. To evaluate the efficiency, we utilized a dataset including 10 types of real-world noises and made a comparison with two classic supervised and unsupervised methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Speech enhancement

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：