检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Gong, Tierui Wei, Li Huang, Chongwen Yang, Zhijia He, Jiguang Debbah, Mérouane Yuen, Chau School of Electrical and Electronics Engineering Nanyang Technological University Singapore639798 Singapore College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Hangzhou310027 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Technology Innovation Institute Masdar City Abu Dhabi9639 United Arab Emirates KU 6G Research Center Khalifa University of Science and Technology P O Box 127788 Abu Dhabi United Arab Emirates CentraleSupelec University Paris-Saclay Gif-sur-Yvette91192 France

Envisioned as one of the most promising technologies, holographic multiple-input multiple-output (H-MIMO) recently attracts notable research interests for its great potential in expanding wireless possibilities and achieving fundamental wireless limits. Empowered by the nearly continuous, large and energy-efficient surfaces with powerful electromagnetic (EM) wave control capabilities, H-MIMO opens up the opportunity for signal processing in a more fundamental EM-domain, paving the way for realizing holographic imaging level communications in supporting the extremely high spectral efficiency and energy efficiency in future networks. In this article, we propose a generalized EM-domain near-field channel modeling and study its capacity limit of point-to-point H-MIMO systems that equips arbitrarily placed surfaces in a line-of-sight (LoS) environment. Two effective and computational-efficient channel models are established from their integral counterpart, where one is with a sophisticated formula but showcases more accurate, and another is concise with a slight precision sacrifice. Furthermore, we unveil the capacity limit using our channel model, and derive a tight upper bound based upon an elaborately built analytical framework. Our result reveals that the capacity limit grows logarithmically with the product of transmit element area, receive element area, and the combined effects of 1/d2mn, 1/d4mn, and 1/d6mn over all transmit and receive antenna elements, where dmn indicates the distance between each transmit element n and receive element m. Particularly, 1/d6mn dominates in the near-field region whereas 1/d2mn dominates in the far-field region. Numerical evaluations validate the effectiveness of our channel models, and showcase the slight disparity between the upper bound and the exact capacity, which is beneficial for predicting practical system performance. Copyright © 2023, The Authors. All rights reserved.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Research on PMSM Vector Control System Based on Fuzzy PI Parameter Self-Tuning 10

Research on PMSM Vector Control System Based on Fuzzy PI Par...

引用

10th International Conference on Power and Energy systems, ICPES 2020

作者： Ding, Jianhua Zhang, Tao Tao, Ran Wang, Anna Northeastern University College of Information Science and Engineering Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China School of Electrical Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9781665404945

Based on the analysis of the permanent magnet synchronous motor (PMSM) mathematical model, a PMSM rotor field-oriented double closed-loop vector control system is constructed. Aiming at the defects of slow speed response, large overshoot, severe torque ripple, and poor anti-disturbance ability in the traditional PI controller used in the system speed loop, a fuzzy PI parameter self-tuning controller is proposed. The controller can set the two parameters of proportional and integral online according to fuzzy control rules. The system simulation model is built based on Matlab/Simulink. The simulation results show that the fuzzy PI parameter self-tuning controller has the advantages of fast dynamic response, high steady-state precision and strong anti-disturbance capability. © 2020 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Short-Term Photovoltaic Power Prediction Modeling Based on AdaBoost Algorithm and Elman 10

Short-Term Photovoltaic Power Prediction Modeling Based on A...

引用

10th International Conference on Power and Energy systems, ICPES 2020

作者： Sun, Wenxuan Zhang, Tao Tao, Ran Wang, Anna Northeastern University College of Information Science and Engineering Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China School of Electrical Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9781665404945

In recent years, with the rapid expansion of the installed capacity of renewable energy systems, the availability, stability and quality of smart grids have become increasingly important[1]. The application of renewable energy production forecasting has also been rapidly developed, especially in the field of solar photovoltaic (PV)[2][3]. In the example of solar PV output prediction, machine learning and hybrid technologies have been implemented for many applications. In this paper, a high-precision PV system output power prediction model based on improved AdaBoost and Elman is proposed. Multiple model using integrated AdaBoost algorithm fusion with the bat algorithm for the parameters of optimized combination of weak Elman neural network predictor to become a higher prediction precision, the method of strong predictor of the model can according to the weather information, such as temperature, solar radiation and the history of the output of the PV system data, the probability of photovoltaic power generation for 12 hours and deterministic prediction. The prediction accuracy of the model is determined by Root Mean Squared Error (RMSE). Experimental results show that the prediction accuracy of this algorithm is better than that of other benchmark models, and the algorithm can effectively predict the volatility and irregularity of complex time series. © 2020 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

A C Code Generator for Fast Inference and Simple Deployment of Convolutional Neural Networks on Resource Constrained systems

A C Code Generator for Fast Inference and Simple Deployment ...

引用

IOT, Electronics and Mechatronics Conference (IEMTRONICS), IEEE International

作者： Oliver Urbann Simon Camphausen Arne Moos Ingmar Schwarz Sören Kerner Maximilian Otten Automation and Embedded Systems Fraunhofer IML Dortmund Germany Robotics Research Institute TU Dortmund University Dortmund Germany Software and Information Engineering Fraunhofer IML Dortmund Germany

ISBN: (数字)9781728196152

ISBN: (纸本)9781728196169

Inference of Convolutional Neural Networks in time critical applications usually requires a GPU. In robotics or embedded devices these are often not available due to energy, space and cost constraints. Furthermore, installation of a deep learning framework or even a native compiler on the target platform is not possible. This paper presents a neural network code generator (NNCG) that generates from a trained CNN a plain ANSI C code file that encapsulates the inference in single a function. It can easily be included in existing projects and due to lack of dependencies, cross compilation is usually possible. Additionally, the code generation is optimized based on the known trained CNN and target platform following four design principles. The system is evaluated utilizing small CNN designed for this application. Compared to TensorFlow XLA and Glow speed-ups of up to 11.81 can be shown and even GPUs are outperformed regarding latency.

关键词： Robots Artificial neural networks Machine learning Libraries Generators Embedded systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Joint Task Offloading and Uav Trajectory Optimization in Dynamic Edge Computing systems: A Deep Reinforcement Learning Approach

SSRN

引用

SSRN 2025年

作者： Wang, Yitian Wang, Hui Ding, Jingfang Yu, Haibin School of Information Engineering Shenyang University of Chemical Technology Shenyang110142 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China

This paper addresses latency challenges in cloud-based task offloading caused by geographical server-user disparities by integrating Unmanned Aerial Vehicles (UAVs) with Mobile Edge Computing (MEC). We propose a dynamic UAV-assisted framework that optimizes real-time parameter adjustments to minimize system latency. Key challenges include joint task offloading, UAV trajectory optimization, and User Equipment (UE) occlusion detection under mobility constraints. To resolve these, we transform the problem into a Markov Decision Process (MDP) and develop an enhanced Adaptive Delayed Deep Deterministic Policy Gradient (AD3PG) algorithm, which improves upon DDPG by incorporating delayed updates and neural network tuning. The algorithm dynamically optimizes three critical aspects: UAV-UE connectivity establishment, occlusion-aware dual noise power configuration, and adaptive task offloading ratios. Extensive simulations demonstrate AD3PG’s superiority over baseline methods such as DDPG and Twin-Delayed DDPG (TD3) in reducing total system latency by 13.2–35.3% under dynamic scenarios. These results validate the framework’s efficacy for latency-sensitive applications in UAV-MEC systems. © 2025, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Based on Multi-scale LSTM-FCNs for Industrial Process

Fault Diagnosis Based on Multi-scale LSTM-FCNs for Industria...

引用

Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Shaojie Yang Peng Li Shuai Li Xiaofeng Zhou Shanghong Jiang Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Information Center of Ansteel Mining Limited Company Anshan China

ISBN: (纸本)9781665401166

Aiming at the characteristics of multi-scale, time series and nonlinear of the complex industrial process data, in order to extract process information more efficiently for improving the diagnosibility, a novel fault diagnosis method based on multi-scale long short term memory- fully convolutional networks (LSTM-FCNs) for industrial process is proposed. Firstly, variational mode decomposition (VMD) is used to obtain the multi-scale components of the process data. Then a parallel LSTM and FCNs optimized by batch normalization and random inactivation is built to extract features for each component. Finally, based on the fusion of multi-scale features, a fully connected layer is used for diagnosis. The LSTM-FCNs method is evaluated by the Tennessee Eastman (TE) benchmark industrial process, and compared with other methods, its effectiveness and superiority are verified.

关键词： Fault diagnosis Fault detection Time series analysis Benchmark testing Feature extraction Safety Data mining

来源：评论

学校读者我要写书评

暂无评论

An Accelerated Iterative Learning Control Approach for X-Y precision plane motion stage

An Accelerated Iterative Learning Control Approach for X-Y p...

引用

作者： Tao Zhang Hongyu Yan Danping Jia Hualiang Zhang Bingjie Zhao Xu Lu Yang Liu Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences School of Electrical Engineering Dalian University of Technology School of Artificial Intelligence Shenyang University of Technology School of Information Science and Engineering Shenyang University of Technology

X-Y precision plane motion stage is widely used in precision motion control fields such as lithography machine workpiece stage,CNC machine tool,Laser measuring system,etc.,which requires high accuracy of the position *** X-Y precision plane motion stage uses two permanent magnet linear synchronous motors(PMLSM) as drivers to drive the motion table to perform XY two-degree-of-freedom *** open-closedloop PD-type iterative learning controller(ILC) approach based on accelerated convergence was proposed to improve trajectory tracking performance of *** interval was changed by real-time correction of the exponential gain matrix in the interval to accelerate the convergence *** to the λ norm,the monotone convergence of the proportion differentiation(PD) was developed for the *** controller consists of two terms:a PID controller which enhances robustness to disturbances and system parameter variability and an ILC which generally improves the performance in the repetitive tasks by using the information from previous *** experimental results show that tracking precision and convergence speed of PMLSM can be effectively improved by the scheme.

关键词： X-Y precision plane motion stage Iterative learning control tracking precision convergence rate

来源：评论

学校读者我要写书评

暂无评论

On the Robustness of Power IOT against Attack Based on General Framework

On the Robustness of Power IOT against Attack Based on Gener...

引用

Power and Energy Engineering (ICPEE), International Conference on

作者： Tianyu Wang Weiwei Miao Jianming Zhao Bowen Zhang Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China State Grid Jiangsu Electric Power Co. Ltd Information & Telecommunication Branch Nanjing China

ISBN: (纸本)9781665420471

Power Internet of Things (IOT) is the application of Internet of things in smart grid and the result of the development of information and communication technology to a certain stage. It will effectively integrate communication infrastructure resources and power system infrastructure resources, and improve the informationize level of power system. However, real-world complex systems are often vulnerable under disruptions. Power IOT is facing with different types of attack, which contains natural disasters and human intentional attacks. Motivated by this point, we propose a general framework of Power IOT robustness with different structures against diverse attacks. Evaluation on example IOT networks shows the effectiveness of our framework, and the characteristics of different structure against attacks. Our study contributes to a better understanding of Power IOT robustness, and reveals the designation of the Power IOT network improves the robustness of the network.

关键词： Robustness Power systems Smart grids information and communication technology Internet of Things Complex systems

来源：评论

学校读者我要写书评

暂无评论

Multi-hop reasoning over sparse knowledge graphs with deep reinforcement learning

引用

Expert systems with Applications 2025年 290卷

作者： Liu, Yiyang Fu, Lejun Fu, Yukai Wu, Tianxing Bai, Hongfei State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China College of Information Engineering Shenyang University of Chemical Technology Shenyang110142 China School of Computer Science and Engineering Southeast University Nanjing211189 China

In recent years, knowledge reasoning has demonstrated substantial progress in inferring missing information, effectively alleviating the limitations caused by the incompleteness of knowledge graphs (KGs). Dealing with entities that have sufficient paths between them, multi-hop reasoning methods have achieved notable success and demonstrated interpretability, but they still exhibit deficiencies when dealing with sparse KGs. To overcome the insufficiency of edges in sparse KGs and the absence of effective guidance in multi-hop reasoning methods, a hybrid multi-hop collaborative Multi-Agent Sparse Knowledge Graph Reasoning model (MASKGR) is proposed. Attention-based dynamic completion (ADC) and variable rule guidance(VRG) are used to enhance the reasoning capability of deep reinforcement learning (RL) in sparse KGs. ADC focuses on high-value relations based on attention weights and combines embedding-based methods to predict the tail entities of these relations, expanding the original action space and improving the exploration capability of agents. Moreover, VRG greatly improves the ability of MASKGR to use rule-guided agent learning by utilizing the variable rule ratio and the variable loss reshaping. ADC can be applied to both single-agent and multi-agent in other models, while VRG is specifically designed for multi-agent. Comprehensive experiments have been conducted on four datasets: FB15K-237-10 %, FB15K-237-50 %, NELL23K, and WD-singer. Specifically, MASKGR achieves relative improvements of 1.3 % in Mean Reciprocal Rank (MRR) and 1.1 % in the proportion of correct tail entity rankings in the top 3 (Hit@3) on the FB15K-237-10 %, 2.4 % in MRR and 1.3 % in Hit@3 on the NELL23K, and 2.7 % in MRR and 3.6 % in Hit@3 on the WD-singer. The results indicate that MASKGR outperforms state-of-the-art multi-hop reasoning models based on reinforcement learning. © 2025

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The Method of Neural Network Control over the Process of Manufacturing Foil Solar Panels 2

The Method of Neural Network Control over the Process of Man...

引用

2nd IEEE International Conference on System Analysis and Intelligent Computing, SAIC 2020

作者： Sachenko, Anatoliy Ivakhiv, Orest Vyshnia, Volodymyr Grzeszczyk, Konrad Osolinskyi, Oleksandr Novosad, Stanislav Kochan, Volodymyr Nakonechnyi, Markiyan Kochan, Orest Kopania, Lukasz Kazimierz Pulaski University of Technology and Humanities in Radom Department of Informatics Radom Poland Lviv Polytechnic National University Department of Intelligent Mechatronics and Robotics Lviv Ukraine Dnipropetrovsk State University of Internal Affairs Department of Economic and Information Security Dnipro Ukraine International Vision Machinery VISORT Sp. J Radom Poland Ternopil National Economic University Department for Information Computer Systems and Control Ternopil Ukraine Ternopil National Economic University Research Institute for Intelligent Computer Systems Ternopil Ukraine Lviv Polytechnic National University Department of Computerized Automation Systems Lviv Ukraine Lviv Polytechnic National University Department of Measuring Information Technologies Lviv Ukraine

ISBN: (纸本)9781728190822

Authors have developed a method of control over one of the main technological processes of manufacturing foil solar panels, i.e., burning tracks in the layers of semiconductor material and insulation. The proposed method is based on neural networks trained directly on the control object. This eliminates the laborious process of identifying the parameters of the control object mathematical model and the impact of its error on the training outcomes. To clarify the conditions for optimizing a certain law for generating the control action by neural networks various laws of control have been simulated. It's established that laws of control can be changed according to the current situation of the control object. Simulation outcomes proofed that the most efficient is the system with the PI- controller. © 2020 IEEE.

关键词： Process control

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：