检索结果-内蒙古大学图书馆

9th International Congress of Mechatronics engineering and automation, CIIMA 2020

作者： Castellanos, Duby Castrillon, Fabio Camacho, Oscar Gutierrez, Sergio Posada, Norha L. Faculty of Engineering Universidad de Medellin Medellín Colombia School of Engineering Universidad Pontificia Bolivariana Medellín Colombia Escuela Politécnica Nacional Automation and Industrial Control Department Quito Ecuador

ISBN: (纸本)9781728194967

In this work, we present a set of rules that transforms the model of Inverse Response Second Order Plus Dead Time Process (IRSODT) and reduces it to a First Order Plus Dead Time (FOPDT) model. We describe the design process for the proposed rules, where we use Dimensional Analysis Techniques and Design of Experiments (DOE). We analyze and compare our rules with those proposed by Taylor, and those proposed by Skogestad. Finally, we use our rules to tune a Sliding Mode control (SMC) that uses a FOPDT model and we presented some performance indexes. © 2020 IEEE.

关键词： Design of experiments

来源：评论

学校读者我要写书评

暂无评论

DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing

DeepRicci: Self-supervised Graph Structure-Feature Co-Refine...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Li Sun Zhenhao Huang Hua Wu Junda Ye Hao Peng Zhengtao Yu Philip S. Yu School of Control and Computer Engineering North China Electric Power University Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Department of Computer Science University of Illinois at Chicago IL USA

Graph Neural Networks (GNNs) have shown great power for learning and mining on graphs, and Graph Structure Learning (GSL) plays an important role in boosting GNNs with a refined graph. In the literature, most GSL solutions either primarily focus on structure refinement with task-specific supervision (i.e., node classification), or overlook the inherent weakness of GNNs themselves (e.g., over-squashing), resulting in suboptimal performance despite sophisticated designs. In light of these limitations, we propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs. In this paper, we take a fundamentally different perspective of the Ricci curvature in Riemannian geometry, in which we encounter the challenges of modeling, utilizing and computing Ricci curvature. To tackle these challenges, we present a self-supervised Riemannian model, DeepRicci. Specifically, we introduce a latent Riemannian space of heterogeneous curvatures to model various Ricci curvatures, and propose a gyrovector feature mapping to utilize Ricci curvature for typical GNNs. Thereafter, we refine node features by geometric contrastive learning among different geometric views, and simultaneously refine graph structure by backward Ricci flow based on a novel formulation of differentiable Ricci curvature. Finally, extensive experiments on public datasets show the superiority of DeepRicci, and the connection between backward Ricci flow and over-squashing. Codes of our work are given in https://***/RiemanGraph/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-Saving Practice of Variable Frequency Drive Technology in Data Center HVAC System

Energy-Saving Practice of Variable Frequency Drive Technolog...

引用

International Conference on Power and Energy Technology (ICPET)

作者： Chuanxian Ai Jinpeng Yang Rui Chen Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Branch The National Computer Network Emergency Response Technical Team/Coordination Center of China Kunming China Power Dispatch Control Center Guizhou Power Grid Co. Ltd. China Southern Power Grid Co. Ltd Guiyang China

The variable-frequency drive technology (VFD) can modify the motor speed or torque by varying the frequency and voltage of the AC motor input power according to the load demand as a way to save energy. To analyse the energy saving effect of variable-frequency drive technology applied to data centre heating, ventilation, and air conditioning (HVAC) systems, this paper applies VFD technology to data centre fluorine pump-compressor composite air conditioning systems, implements monitoring and analysis of the operational energy efficiency of this system before and after retrofit, and combines the actual application of this technology. The findings indicate that the VFD technology can substantially reduce the number of compressor starts and stops, reduce the compressor start-up inrush current, and improve the power system’s stability. Furthermore, utilising this technology, the HVAC system can effectively synchronise with the load and fluctuations in outdoor temperature and humidity, resulting in accurate temperature regulation and optimal utilisation of outdoor cooling resources. This approach can lead to significant energy conservation of up to 42.95% when compared to extreme hot and cold weather conditions. The findings of the study indicate that the utilisation of VFD technology exhibits commendable adaptability and yields favourable outcomes in regions with varying temperature ranges. The minimum PUE value recorded was 1.228.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Prototype of High-Efficiency Wind Turbine Based on Magnus Effect 27

Experimental Prototype of High-Efficiency Wind Turbine Based...

引用

27th International Workshop on Electric Drives: MPEI Department of Electric Drives 90th Anniversary, IWED 2020

作者： Lukin, Aleksandr Demidova, Galina L. Lukichev, Dmitry V. Rassolkin, Anton Kallaste, Ants Vaimann, Toomas Belahcen, Anouar ITMO University Faculty of Control System and Robotics Saint Petersburg Russia Tallinn University of Technology Department of Electrical Power Engineering and Mechatronics Tallin Estonia Aalto University Department of Electrical Engineering and Automation Helsinki Finland

ISBN: (纸本)9781728141589

The main feature of Magnus wind turbine is the ability to produce energy at low wind speed. This benefit lets to use such types of turbines in smart homes, which are an important part of the development of distributed energy systems, growth of blockchain electricity technology and needs for duplication of the solar energy system in the private buildings. This paper presents topology of two cylinders Magnus wind turbine in order to ensure the highest values of power coefficient and the Magnus force. The optimal ratio of wind speed and cylinder rotation speed were detected to eliminate the oscillations caused by the Von Karman vortex street phenomenon. © 2020 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Nonlinear superfluidity and time-delay based chaotic spin-down in pulsars

arXiv

引用

arXiv 2021年

作者： Gügercinoglu, Erbil Dogan, Mustafa Ekşi, K. Yavuz Faculty of Engineering and Natural Sciences Sabancı University Orhanlı Istanbul34956 Turkey Faculty of Electrical-Electronics Engineering Department of Control and Automation Engineering Istanbul Technical University MaslakIstanbul34469 Turkey Faculty of Science and Letters Physics Engineering Department Istanbul Technical University MaslakIstanbul34469 Turkey

We investigate the chaotic spin-down behavior seen from some pulsars in terms of the nonlinear superfluid dynamics. To this end, we numerically solve the set of equations for the superfluid-normal matter system whose coupling is mediated by creep of the vortex lines. We show that glitch perturbations which introduce a time-delay to the steady-state dynamics leave behind a remnant in the third time derivative of the rotational phase. This time-delay induces a hyper-chaotic spin-down for pulsars. We find that glitch-induced changes in the rotational parameters lead to non-closing cyclic patterns in the time-delayed phase difference diagram. We observe that the number of cycles, N, in the diagram results from N + 1 glitches occurred in total observation time. Copyright © 2021, The Authors. All rights reserved.

关键词： Pulsars

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multi-stream Information Fusion for Trajectory Prediction in Low-illumination Scenarios: A Multi-channel Graph Convolutional Approach

arXiv

引用

arXiv 2022年

作者： Gong, Hailong Li, Zirui Lu, Chao Du, Guodong Gong, Jianwei School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China Chair of Traffic Process Automation "Friedrich List" Faculty of Transport and Traffic Sciences TU Dresden Germany Institute of Dynamic System and Control ETH Zurich Sonneggstrasse 3 Zurich8092 Switzerland

Trajectory prediction is a fundamental problem and challenge for autonomous vehicles. Early works mainly focused on designing complicated architectures for deep-learning-based prediction models in normal-illumination environments, which fail in dealing with low-light conditions. This paper proposes a novel approach for trajectory prediction in low-illumination scenarios by leveraging multi-stream information fusion, which flexibly integrates image, optical flow, and object trajectory information. The image channel employs Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) networks to extract temporal information from the camera. The optical flow channel is applied to capture the pattern of relative motion between adjacent camera frames and modelled by Spatial-Temporal Graph Convolutional Network (ST-GCN). The trajectory channel is used to recognize high-level interactions between vehicles. Finally, information from all the three channels is effectively fused in the prediction module to generate future trajectories of surrounding vehicles in low-illumination conditions. The proposed multi-channel graph convolutional approach is validated on HEV-I and newly generated Dark-HEV-I, egocentric vision datasets that primarily focus on urban intersection scenarios. The results demonstrate that our method outperforms the baselines, in standard and low-illumination scenarios. Additionally, our approach is generic and applicable to scenarios with different types of perception data. The source code of the proposed approach is available at https://***/TommyGong08/MSIF. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Textile-Based Thermally Driven Actuators for Soft Robotic Mechanotherapy Applications

Textile-Based Thermally Driven Actuators for Soft Robotic Me...

引用

International Conference on control, Decision and Information Technologies (CoDIT)

作者： Mehmet Fatih Ç elebi Zeynep Beler Elif Dede Emine Dilara Koç ak Ö zgü r Atalay Aslı Tunç ay Atalay Veysel Gazi Department of Electrical and Electronics Engineering Department of Mechatronics Engineering Faculty of Technology Institute of Pure and Applied Sciences Marmara University Istanbul Turkey Department of Polymer Science and Technology Institute of Pure and Applied Sciences Marmara University Istanbul Turkey Department of Metallurgy and Materials The University of Birmingham Birmingham United Kingdom Department of Textile Engineering Faculty of Technology Marmara University Istanbul Turkey Faculty of Textile Technology and Design Istanbul TechnicalDepartment of Textile EngineeringIstanbulTurkey Veysel Gazi is with the Department of Control and Automation Engi-neering Faculty of Electrical and Electronics Engineering Yildiz Technical University Istanbul Turkey

Rigid-body industrial robotic manipulators and pneumatic compression systems are widely used in mechano-therapeutic applications. However, rigid and bulky components reduce the wearability of the system in mobile environments. The current trend in wearable robotics tends to build such devices using textiles/silicone materials thanks to their lightness, compliancy, and comfort properties. In this study, thermally powered soft fluidic actuators that utilize liquid/gas phase transition property of low boiling point liquids are investigated. Proposed actuators generate desired pressure level and have great potential to free mechano-therapy devices from such bulky components. The developed structure incorporates textile-based heaters, thin film actuator shells, and low boiling point liquids. Here, two low boiling liquids with different boiling temperature are mixed successfully in order to obtain desired boiling point. Results a revealed that actuators constructed with PE/PA membrane did not show any deterioration even after 500 cycle actuation. In order to control the system, instantaneous temperature of the textile-based heater on the actuator device is used as feedback for the on-off controller.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph Reinforcement Learning Application to Co-operative Decision-Making in Mixed Autonomy Traffic: Framework, Survey, and Challenges

arXiv

引用

arXiv 2022年

作者： Liu, Qi Li, Xueyuan Li, Zirui Wu, Jingda Du, Guodong Gao, Xin Yang, Fan Yuan, Shihua School of Mechanical Engineering Beijing Institute of Technology Beijing China Chair of Traffic Process Automation "Friedrich List" Faculty of Transport and Traffic Sciences TU Dresden Germany School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore639798 Singapore Institute of Dynamic System and Control ETH Zurich Zurich Switzerland

Proper functioning of connected and automated vehicles (CAVs) is crucial for the safety and efficiency of future intelligent transport systems. Meanwhile, transitioning to fully autonomous driving requires a long period of mixed autonomy traffic, including both CAVs and human-driven vehicles. Thus, collaboration decision-making for CAVs is essential to generate appropriate driving behaviors to enhance the safety and efficiency of mixed autonomy traffic. In recent years, deep reinforcement learning (DRL) has been widely used in solving decision-making problems. However, the existing DRL-based methods have been mainly focused on solving the decision-making of a single CAV. Using the existing DRL-based methods in mixed autonomy traffic cannot accurately represent the mutual effects of vehicles and model dynamic traffic environments. To address these shortcomings, this article proposes a graph reinforcement learning (GRL) approach for multi-agent decision-making of CAVs in mixed autonomy traffic. First, a generic and modular GRL framework is designed. Then, a systematic review of DRL and GRL methods is presented, focusing on the problems addressed in recent research. Moreover, a comparative study on different GRL methods is further proposed based on the designed framework to verify the effectiveness of GRL methods. Results show that the GRL methods can well optimize the performance of multi-agent decision-making for CAVs in mixed autonomy traffic compared to the DRL methods. Finally, challenges and future research directions are summarized. This study can provide a valuable research reference for solving the multi-agent decision-making problems of CAVs in mixed autonomy traffic and can promote the implementation of GRL-based methods into intelligent transportation systems. The source code of our work can be found at https://***/Jacklinkk/Graph_CAVs. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

An Optimizing Method Based On Combining Edge Computer And Long Short-Term Memory Networks Applied To Solar Power Forecasting

An Optimizing Method Based On Combining Edge Computer And Lo...

引用

International Future Energy Electronics Conference (IFEEC)

作者： Minh-Ngoc Nguyen Manh-Hai Pham Yuan-Kang Wu Ngoc-Trung Nguyen Faculty of Electrical and Electronic Engineering Phenikaa University Hanoi Vietnam Faculty of Energy Technology Electric Power University Hanoi Vietnam National Chung-Cheng University Chiayi Taiwan Control and Automation Faculty Electric Power University Hanoi Vietnam

ISBN: (纸本)9781665434492

Along with the rapid development of solar energy sources on the global power system, the challenges related to the weather instability of this power type are also of increasing concern. Intending to solve these challenges, the study of solar power forecasting has become one of the most important problems in the power system field. Most of the published forecast algorithms aim to minimize prediction errors. However, in reality, convenience and data processing time are two necessary goals to commercialize a forecasting software. Recently, IoT is emerging as an effective solution to solve the above multi-objective problem. Especially, in the current trend of real-time forecasting, the application of Edge Computer in the IoT environment is bringing new opportunities for the goal of reducing data processing time while ensuring acceptable forecast errors. Moreover, Edge Computer also reduces the risk of network congestion due to its distributed processing characteristics. This paper introduces a new methodology using Edge Computer combined with the LSTM algorithm applied to the solar power forecasting problem. Real-time calculation results show that the accuracy can be improved by the good choice of the converted data type while the execution time is halved compared to without using Edge Computer.

关键词： Software algorithms Weather forecasting Solar energy Power system stability Data processing Prediction algorithms Real-time systems

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：