检索结果-内蒙古大学图书馆

Innovative Research in Applied science, Engineering and Technology (IRASET),Conference on

作者： Abdeljabar Aboulkassim Said Kririm Naoual Armi Bensalem Boukili El Hanafi Arjdal Materials Signals Systems and Physical Modeling Laboratory Faculty of Sciences Ibnou Zohr University Agadir Morocco Department of Physics Faculty of Sciences Dhar El Mahraz Computer Science Signal Automation and Cognitivism Laboratory Sidi Mohamed Ben Abdellah University Fez Morocco

ISBN: (数字)9798331532970

ISBN: (纸本)9798331532987

This paper presents a novel approach to develop a fuzzy maximum power point tracking (MPPT) controller that performs well in variable weather photovoltaic (PV) systems. The photovoltaic output voltage can be adjusted using a DC-DC boost converter. The last step is controlled by the duty cycle, which is essentially bounded between 0 and 1 . Using the Lyapunov approach and Descriptor Takagi-Sugeno (DT-S) fuzzy modelling, we establish the stabilisation conditions with H∞ performance represented as linear matrix inequalities (LMIs). Finally, we apply the proposed control to a solar system and the results of our simulation validate the efficiency of the presented methods.

关键词： Maximum power point trackers Photovoltaic systems Simulation Stability criteria Takagi-Sugeno model Solar system Linear matrix inequalities Meteorology Lyapunov methods Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Coordinated Virtual Inertial Control of DFIG with BESS for Frequency Support

Coordinated Virtual Inertial Control of DFIG with BESS for F...

引用

International Conference on Intelligent System and Knowledge Engineering, ISKE

作者： Shengyu Chen Guidong Zhang Samson Shenglong Yu Yun Zhang Zhong Li School of Automation Guangdong University of Technology Guangzhou China School of Engineering Deakin University Melbourne Australia Faculty of Mathematics and Computer Science FernUniversitaet in Hagen Hagen Germany

As the installed capacity of wind turbines increases, the overall inertia of the system decreases, which reduces the ability of the system to support the frequency. Due to the tendency to operate in a maximum power tracking state and the lack of an active power reserve, doubly-fed induction generator (DFIG), a type of the current popular wind turbine, are unable to efficiently utilize the rotor kinetic energy to engage in frequency regulation in the face of grid frequency variations. To address this issue, virtual inertia control (VIC) is introduced to release the kinetic energy of the DFIG provide dynamic frequency support to the grid. In addition, a properly designed control strategy for the battery energy storage system (BESS) can store the excess energy of the DFIG system and release it as needed to assist frequency regulation. In this paper, we propose a coordinated control strategy for virtual inertial regulation with BESS for DFIG frequency support. We design a charge-discharge switching control strategy for the BESS. Time-domain simulations are conducted to verify the effectiveness of the proposed method in suppressing frequency disturbances.

关键词：

来源：评论

学校读者我要写书评

暂无评论

KUKA Robot Language Parser for Product Adaptive Manufacturing

KUKA Robot Language Parser for Product Adaptive Manufacturin...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Robert Rosenstock Tim Wrütz Rolf Biesenbach Faculty of Electrical Engineering and Computer Science Bochum University of Applied Sciences Bochum Germany Institute for Automation and Industry 4.0 Bochum University of Applied Sciences Bochum Germany

The work reported in this paper enables to upload and activation of new programs to KUKA industrial robots during active operation, which would not be possible normally. By doing this it is possible to program those robots offline resulting in increased flexibility for modern manufacturing. The programs could be placed on work pieces to form a work-piece-driven production. Comparable projects increased the capabilities of robot programming by avoiding the KUKA Robot Language using high-level programming languages. Those approaches have proven themselves in the field of research. Nevertheless, this work tries a completely different approach by enabling offline programming and switching between programs while maintaining KRL the most used robot programming language for KUKA robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integral Reinforcement Learning-Based Angular Acceleration Autopilot for High Dynamic Flight Vehicles

SSRN

引用

SSRN 2023年

作者： Liu, Yingxin Hu, Yuhui Shen, Kai Qiu, Jiatai Neusypin, Konstantin A. School of Automation Beijing Institute of Technology Beijing100081 China Faculty of Computer Science and Control Systems Bauman Moscow State Technical University Moscow105005 Russia

In the synthesis of acceleration autopilot for high dynamic flight vehicle (HDFV), the full perception of system states, such as the angle of attack, is usually unavailable. Autopilots with feedback of angular acceleration (AFAA) have become more perspective for HDFV with stringent requirements on response speed and high maneuverability, compared with autopilot with feedback of angular rate (AFAR). Although classical optimal control methodology has validated its great vitality during the synthesis of autopilots both in theory and practice while this approach requires complete knowledge of the system dynamics. Reinforcement learning (RL) method has now proved to be an effective technique for adaptive optimal control of partially unknown nonlinear systems. In this paper, a novel data-driven integral RL algorithm with feedback of angular acceleration was proposed for the synthesis of HDFV’s autopilot. And numerical simulation was carried out to validate the effectiveness of proposed online integral RL-based angular acceleration autopilot for HDFVs. Besides, the tracking performance under different wave commands, the robustness against parameter uncertainties and the noise attenuation capacity between classical optimal tracking approach and proposed integral RL method were analyzed for AFAR and AFAA, respectively. Simulation results showed, angular acceleration autopilot with proposed integral RL algorithm possessed better tracking performance against various disturbances. © 2023, 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

A New Configuration for Waveguide Filters With Parallel Coupling Paths

A New Configuration for Waveguide Filters With Parallel Coup...

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Weijun Wu Zai-Cheng Guo Lei Zhu School of Electrical and Automation Engineering Nanjing Normal University Nanjing China Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macau SAR China

A new configuration is proposed for filters with parallel coupling paths between the source and load in this paper. The proposed fourth-order waveguide bandpass filter (BPF) with two parallel coupled paths is formally designed through this structure. The filter is working at 6.5 GHz and with 300 MHz bandwidth. Due to the two parallel coupling paths, a pair of transmission zeros (TZs) are generated out of passband. Compared with previous waveguide filters, the coupling paths are connected to the source and load in different sides of input/output waveguide. In this way, the waveguide cavity of the resonator can be increased and the insertion loss of the filter can be greatly reduced. The effectiveness of the fourth-order waveguide bandpass filter is verified by simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Static Feature Extraction in Dynamic Scenes: An Advanced RGBD Visual SLAM Framework Leveraging YOLOv9

Robust Static Feature Extraction in Dynamic Scenes: An Advan...

引用

2025 2nd International Conference on Algorithms, Software Engineering and Network Security (ASENS)

作者： Bo Wang Sen Zhang Qifeng Jiang Lu Lu Zongren Chen Computer Engineering Technical College (Artificial Intelligence College) Guangdong Polytechnic of Science and Technology Zhuhai China School of Automation Harbin University of Science and Technology Harbin China Faculty of Science and Technology Beijing Normal University Hong Kong Baptist University United International College Zhuhai China

ISBN: (数字)9798331520298

ISBN: (纸本)9798331520304

Dynamic elements in dynamic environment are important factors that affect the localization accuracy of visual Simultaneous Localization and Mapping (vSLAM), and may even lead to tracking failures. To address this issue, we propose an enhanced dense visual SLAM method specifically designed for dynamic environments. The whole framework of our approach is based on ORB-SLAM2, while integrating the YOLOv9 network to detect dynamic objects. By transmitting the detection results of YOLOv9 to the SLAM module, dynamic feature elements are then removed from the dense map construction thread. Finally, the dense map that only contains static information is created. The experimental results show that the filtering of dynamic objects not only can reduce the average root mean square error (RMSE), but also help and then improve the robustness of the SLAM system in dynamic environment.

关键词： Point cloud compression Visualization Simultaneous localization and mapping Accuracy Three-dimensional displays Target tracking Target recognition Heuristic algorithms Feature extraction Software engineering

来源：评论

学校读者我要写书评

暂无评论

First Order Features Extraction from Thermal Images for Human State Recognition

First Order Features Extraction from Thermal Images for Huma...

引用

International Symposium on Electrical and Electronics Engineering (ISEEE)

作者： Simona Moldovanu Sorin Pavel Dorel Aiordachioaie Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati Galati Romania Department of Electronics and Telecommunications Faculty of Automation Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati Galati Romania

Due to the common limitation of the human visual system, internal features of thermal images cannot be fully discovered. To overcome these drawbacks, a lot of studies analyzed the facial expressions corroborating the features extracted from thermal images with machine learning tools. This paper proposed the first-order features extracted from the image histogram and a binary classification performed by the k-nearest neighbor algorithm (K-NN). The proposed method tests separately the performance of different input data, firstly, the features were extracted from raw images and the robustness of the K-NN algorithm led to an accuracy of 92.6%. Secondly, the features were extracted sequentially from corrupted images with noise. The novelty of the proposed method consists of verifying the quality classification when the images have bad quality, in this case, the accuracy decreased to 70.7%, as a result, the classification of facial expressions is sensitive to the quality of images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constrained Multi-objective Optimization with Deep Reinforcement Learning Assisted Operator Selection

arXiv

引用

arXiv 2024年

作者： Ming, Fei Gong, Wenyin Wang, Ling Jin, Yaochu The School of Computer Science China University of Geosciences Wuhan430074 China The Department of Automation Tsinghua University Beijing100084 China The Faculty of Technology Bielefeld University North Rhine-Westphalia Bielefeld33619 Germany

Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable attention. Various constrained multi-objective optimization evolutionary algorithms (CMOEAs) have been developed with the use of different algorithmic strategies, evolutionary operators, and constraint-handling techniques. The performance of CMOEAs may be heavily dependent on the operators used, however, it is usually difficult to select suitable operators for the problem at hand. Hence, improving operator selection is promising and necessary for CMOEAs. This work proposes an online operator selection framework assisted by Deep Reinforcement Learning. The dynamics of the population, including convergence, diversity, and feasibility, are regarded as the state;the candidate operators are considered as actions;and the improvement of the population state is treated as the reward. By using a Q-Network to learn a policy to estimate the Q-values of all actions, the proposed approach can adaptively select an operator that maximizes the improvement of the population according to the current state and thereby improve the algorithmic performance. The framework is embedded into four popular CMOEAs and assessed on 42 benchmark problems. The experimental results reveal that the proposed Deep Reinforcement Learning-assisted operator selection significantly improves the performance of these CMOEAs and the resulting algorithm obtains better versatility compared to nine state-of-the-art CMOEAs. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Prediction of Resources and Workloads for Cloud Computing Systems with Attention-based and Hybrid LSTM

Adaptive Prediction of Resources and Workloads for Cloud Com...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Bi, Jing Ma, Haisen Yuan, Haitao Xu, Kangyuan Zhou, MengChu Beijing University of Technology Faculty of Information Technology Beijing100124 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China New Jersey Institute of Technology Department of Electrical and Computer Engineering Newark07102 United States

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Currently, cloud computing service providers face big challenges in predicting large-scale workload and resource usage time series. Due to the difficulty in capturing nonlinear features, traditional forecasting methods usually fail to achieve high performance in predicting resource usage and workload sequences. Much noise implicit in the original sequences of resources and workloads is another reason for their low performance. To address these problems, this work proposes a hybrid prediction model named SABG that integrates an adaptive Savitzky-Golay (SG) filter, Attention mechanism, Bidirectional and Grid versions of Long and Short Term Memory (LSTM) networks. SABG adopts an adaptive SG filter in the data pre-processing to eliminate noise and extreme points in the original time series. It uses bidirectional and grid LSTM networks to capture bidirectional features and dimension ones, respectively. Then, it utilizes an attention mechanism to explore importance of different data dimensions. SABG aims to predict resource usage and workloads in highly variable traces in cloud computing systems. Extensive experimental results demonstrate that SABG achieves higher-accuracy prediction than several benchmark prediction approaches with datasets from Google cluster traces. © 2022 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Method for Network Attack Prediction

A Hybrid Deep Learning Method for Network Attack Prediction

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Bi, Jing Xu, Kangyuan Yuan, Haitao Zhou, MengChu Beijing University of Technology Faculty of Information Technology Beijing100124 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China New Jersey Institute of Technology Department of Electrical and Computer Engineering Newark07102 United States

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Precise real-time prediction of the number of future network attacks cannot only prompt cloud infrastructures to fast respond to them and protect network security, but also prevents economic and business losses. In recent years, neural networks, e.g., Bi-direction Long and Short Term Memory (LSTM) and Temporal Convolutional Network (TCN), have been proven to be suitable for predicting time series data. Attention mechanisms are also widely used for the time series prediction. In this work, we propose a novel hybrid deep learning prediction method by combining the capabilities of a Savitzky-Golay (SG) filter, TCN, Multi-head self attention, and BiLSTM for the prediction of network attacks. This work first adopts a SG filter to eliminate noise in the raw data. It applies TCN to extract short-term features from the sequences. It then adopts multi-head self attention to capture intrinsic connections among features. Finally, this work adopts Bi-LSTM to extract bi-directional and long-term correlations in the sequences. Experimental results with a real-life dataset show that the proposed method outperforms several typical algorithms in terms of prediction accuracy. © 2022 IEEE.

关键词： Forecasting

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：