检索结果-内蒙古大学图书馆

27th International conference on Electrical Machines and systems, ICEMS 2024

作者： Ran, Ji-Hoon Choi, Eui-Jin Park, Jong-Hoon Hong, Sun-Ki Hoseo University Department of System and Control Engineering Asan Korea Republic of Hoseo University Department of Information Control Engineering Asan Korea Republic of

ISBN: (纸本)9784886864406

The use of the reinforcement learning algorithm DQN(Deep Q-network) can increase the design variables and offers the advantage of enabling more versatile motor optimization design. This paper evaluates the potential and advantages of reinforcement learning-based motor optimization design, which is still in its early stages globally. To demonstrate the performance of the proposed method, the geometry and drive conditions for reducing torque ripple of a FWSM(Field-Wound Synchronous Motor) using DQN were optimized. The proposed method exhibited excellent optimization performance, and it is expected that a more versatile optimization model can be developed by increasing the number of analysis cases. © 2024 The Institute of Electrical Engineers of Japan.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant control of Hypersonic Flight Vehicle Attitude Tracking Based on Adaptive Dynamic Programming

Fault-Tolerant Control of Hypersonic Flight Vehicle Attitude...

引用

2024 International Annual conference on Complex systems and Intelligent Science, CSIS-IAC 2024

作者： Liu, Hao Zhou, Chuan Guo, Jian Lu, Dong Cao, Xiaolei Jia, Zhiqiang Nanjing University of Science and Technology School of Automation Nanjing China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (纸本)9798331504755

The attitude control problem of hypersonic flight vehicles (HFV) in the presence of bias faults is addressed in this paper, and an intelligent fault-tolerant control strategy using Adaptive Dynamic Programming (ADP) is proposed. A new performance index function is adopted for the fault-tolerant controller design to deal with bias faults. The fault-tolerant control problem is transformed as an optimized control problem based on the improved performance index function. Utilizing policy iteration, a critic neural network is constructed to solve the Hamilton-Jacobi-Bellman equation and the approximate optimal controller is obtained. The uniform ultimate boundedness of the closed-loop system is proved by the Lyapunov stability theorem. Theoretical derivation and simulation verification demonstrate the effectiveness of the proposed fault-tolerant control strategy. © 2024 IEEE.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

A Way to Implement network Services in a Data Center

A Way to Implement Network Services in a Data Center

引用

2024 Wave Electronics and its Application in Information and Telecommunication systems, WECONF 2024

作者： Buzhin, I.G. Antonova, V.M. Gnezdilov, V.S. Mironov, Yu.B. Gayfutdinov, E.A. Moscow Technical University Of Communications And Informatics Moscow Russia

ISBN: (纸本)9798350364989

In recent years, IP-fabric has often been used in data center networks, which is a set of network equipment (usually switches) interacting via control protocols, which provides unified addressing, security, etc. services, as well as data delivery along the optimal route. With such an organization, the implementation of some services is transferred to the virtualization of network functions. This article suggests an effective way to implement virtualization of network functions and deliver traffic to it in the IP fabric of a data center. The method is based on VPP (Vector Packet Processing platform) and FRR (Free Range Routing), VxLAN (Virtual extensible local area network), EVPN (Ethernet VPN) and ICMP (Internet control Message Protocol) technologies. The results of test measurements of the processing of various traffic on the data plane are shown. The results of experimental tests show that on Xeon Cascade Lake core, VPP technology produces a performance of about 20 Mpps with IPv4 traffic. Combinations of IPv4 lookup, VxLAN, Encap/Decap, and ACL (Access control List) lookup processing show lower performance. © 2024 IEEE.

关键词： Internet protocols

来源：评论

学校读者我要写书评

暂无评论

Adaptive Robotic Arm control with a Spiking Recurrent Neural network on a Digital Accelerator 31

Adaptive Robotic Arm Control with a Spiking Recurrent Neural...

引用

31st conference on Electronics Circuits and systems

作者： Linares-Barranco, Alejandro Prono, Luciano Lengenstein, Robert Indiveri, Giacomo Frenkel, Charlotte Univ Seville Robot & Comp Tech Lab Seville Spain Politecn Torino Dept Elect & Telecom Turin Italy Graz Univ Technol Inst Theoret Comp Sci Graz Austria Univ Zurich Inst Neuroinformat Zurich Switzerland Delft Univ Technol Dept Microelect Delft Netherlands

ISBN: (纸本)9798350377217;9798350377200

With the rise of artificial intelligence, neural network simulations of biological neuron models are being explored to reduce the footprint of learning and inference in resource-constrained task scenarios. A mainstream type of such networks are spiking neural networks (SNNs) based on simplified Integrate and Fire models for which several hardware accelerators have emerged. Among them, the "ReckOn" chip was introduced as a recurrent SNN allowing for both online training and execution of tasks based on arbitrary sensory modalities, demonstrated for vision, audition, and navigation. As a fully digital and open-source chip, we adapted ReckOn to be implemented on a Xilinx Multiprocessor System on Chip system (MPSoC), facilitating its deployment in embedded systems and increasing the setup flexibility. We present an overview of the system, and a Python framework to use it on a Pynq ZU platform. We validate the architecture and implementation in the new scenario of robotic arm control, and show how the simulated accuracy is preserved with a peak performance of 3.8M events processed per second.

关键词： Recurrent SNN online learning neuromorphic engineering FPGA MPSoC Python

来源：评论

学校读者我要写书评

暂无评论

Actor-Critic Model Predictive control

Actor-Critic Model Predictive Control

引用

IEEE International conference on Robotics and Automation (ICRA)

作者： Romero, Angel Song, Yunlong Scaramuzza, Davide Univ Zurich Dept Informat Percept Grp Zurich Switzerland Univ Zurich Dept Neuroinformat Zurich Switzerland Swiss Fed Inst Technol Zurich Switzerland

ISBN: (纸本)9798350384581;9798350384574

An open research question in robotics is how to combine the benefits of model-free reinforcement learning (RL)-known for its strong task performance and flexibility in optimizing general reward formulations-with the robustness and online replanning capabilities of model predictive control (MPC). This paper provides an answer by introducing a new framework called Actor-Critic Model Predictive control. The key idea is to embed a differentiable MPC within an actor-critic RL framework. The proposed approach leverages the short-term predictive optimization capabilities of MPC with the exploratory and end-to-end training properties of RL. The resulting policy effectively manages both short-term decisions through the MPC-based actor and long-term prediction via the critic network, unifying the benefits of both model-based control and end-to-end learning. We validate our method in both simulation and the real world with a quadcopter platform across various high-level tasks. We show that the proposed architecture can achieve real-time control performance, learn complex behaviors via trial and error, and retain the predictive properties of the MPC to better handle out of distribution behaviour.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

A Study on RANC Technique for Server-Based control Filter Optimization 13

A Study on RANC Technique for Server-Based Control Filter Op...

引用

13th International Styrian Noise, Vibration and Harshness Congress: The European Automotive Noise conference, SNVH 2024

作者： Oh, Chisung Ih, Kang-Duck Kim, Hyounsuk Hyundai Motor Company ARE Inc.

Active noise control systems use multi-channel references to increase coherence. Additionally, multiple speakers are used to control multiple control positions and broad band frequency. Because of this, even though the control filter update operation is performed in the frequency domain, the amount of calculation is very large, so an expensive and high-performance DSP must be used. If the control filter update operation, which is performed by the controller mounted on the vehicle, is calculated on the server, low-specification DSP can be used in the local vehicle, thereby reducing costs. Moreover, it has the advantage of being able to freely apply performance improvement algorithms using the server's abundant computing power. In this study, considering a wireless network real-time control system, the maximum delay time is analyzed to maintain control performance. When network speed is low and data errors occurred, we studied countermeasures to correct data errors at the receiving location. Accelerometer and microphone sensor signals are transmitted from the local controller to the server using a commercial wireless network service, and the server receives them and generates an updated control filter through a control algorithm. The generated control filter is transmitted from the server to the local controller and can be applied to the control sound generation algorithm to increase control performance. In addition, we developed a system that allows tuning of control variables and analysis of convergence performance when creating a control filter in the server. In this study, we developed a server-based active noise control system that updates control filters on a server based on wireless network, thereby reducing the cost of in-vehicle controllers, expanding control flexibility, and securing a foundation for performance improvement, thereby establishing a foundation for expanding application of active noise control technology to other vehicles which is limited due t

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

20th Chinese Intelligent systems conference, CISC 2024

20th Chinese Intelligent Systems Conference, CISC 2024

引用

20th Chinese Intelligent systems conference, CISC 2024

ISBN: (纸本)9789819786572

The proceedings contain 202 papers. The special focus in this conference is on Chinese Intelligent systems. The topics include: Modeling of Interval Type-2 Fuzzy Logic System by Semi-tensor Product;Robust Adaptive control of Missiles Based on Fuzzy RBF Neural network;deep Reinforcement Learning of Physically Simulated Character control;the Game of Degree of Target-Attacker-Defender Game With Non-zero Capture Radius;Visual Inertial 3D Reconstruction System Based on KLT Optical Flow and Voxel Hash;analysis of Students’ Class Status Based on Deep Learning;fault-Tolerant Attitude control of Hypersonic Flight Vehicles Based on Extended Adaptive Iterative Learning;predefined-Time control of Robot systems with Prescribed performance Guarantees;dynamic Coverage of Unicycle Robots with Anisotropic Sensing for Time-Priority;method for Evaluating the Multi-factor Decision-Making Efficiency Based on Dynamic Bayesian network;submarine Cable Target Search Based on Improved Biological Neural network;end-to-End mmWave-Based Human Pose Estimation from Raw Signal;urban Sewage Treatment Plant Simulation System Based on Industrial Internet;Load Matching Design and Multi-objective Optimization of Helicopter EHA;Testability Design and Verification of Typical Functional Links of CNI System;adaptive Sliding Mode Tracking control for Multiple High-Speed Trains with Actuator Saturation and Parameter Uncertainties;Abnormal Data Detection Based on Dual-Factor Weighted SVDD for Multimode Batch Processes;dual-Branch Attention Dense Residual network Based on Negative Image for Image Denoising;Research on Testability Work Planning Technology for Aviation Equipment Based on DoDAF;aero Engine Instability Prediction and Detection Method Based on Gated Recurrent Neural networks;Seven-Degrees-of-Freedom Robotic Arm Path Planning Based on Improved RRT;dynamic Event-Triggered Based Coherent Formation control for Multi-robot systems;adaptive Prescribed Time Prescribed performance control for High-Order No

关键词：

来源：评论

学校读者我要写书评

暂无评论

Security Evaluation of Data Dissemination in Inter-Vehicle networks 4

Security Evaluation of Data Dissemination in Inter-Vehicle N...

引用

4th International conference on Computer, control and Robotics (ICCCR)

作者： Bayan, Samar Mohammad, Utayba Univ Detroit Mercy Detroit MI 48221 USA

ISBN: (纸本)9798350373141;9798350373158

In the past decade, Vehicular Communication (VC) has been a main subject of research in the Intelligent Transportation systems (ITSs);particularly, with many emerging communication technologies such as DSRC and cellular networks. Through the exchange of messages in a timely manner, these networks are anticipated to improve ITS functionality and driving experience on roads. Several dissemination algorithms have been created in order to achieve high accuracy and efficiency while minimizing redundant transmissions in VC networks. However, recent cyberattacks on automobiles have introduced cybersecurity as a new dimension in the performance of dissemination protocols. In this paper, delay-based, probability-based, and flooding-based dissemination algorithms are compared in terms of performance them evaluated against different types of cyberattacks using NS-3 and SUMO. According to the results, delay-based dissemination performs better than probability- and flooding-based dissemination in terms of network load, and hop count, for single and multiple packet transmissions. However, probability-based dissemination had superior performance over the delay-based dissemination by around 60% in terms of end-to-end delay. From security perspective, flooding, delay-, and probability-based algorithms had no defense against message falsification and Denial of Service (DoS) attacks, due to the lack of a content verification procedures. Yet, in position falsification attack, the number of relay nodes increased by 70% and the network load increased by 62.2% in both DBD and PBD.

关键词： Data Dissemination Delay-based dissemination DBD,Probability-Based dissemination PBD Vehicular Ad-hoc network (VANET) Vehicular Communication (VC)

来源：评论

学校读者我要写书评

暂无评论

A Green Multi-Attribute Client Selection for Over-The-Air Federated Learning: A Grey-Wolf-Optimizer Approach

引用

ACM TRANSACTIONS ON MODELING AND performance EVALUATION OF COMPUTING systems 2025年第1期10卷 1-24页

作者： BEN Driss, Maryam Sabir, Essaid Elbiaze, Halima Diallo, Abdoulaye Sadik, Mohamed Univ Quebec & Montreal Informat Montreal PQ Canada Univ Hassan II Casablanca NEST Res Grp LRI Casablanca Morocco Univ Quebec Sci & technol TELUQ Montreal PQ Canada Univ Quebec Montreal Montreal PQ Canada Univ Hassan II Casablanca Casablanca Morocco

Federated Learning (FL) has gained attention across various industries for its capability to train machine learning models without centralizing sensitive data. While this approach offers significant benefits such as privacy preservation and decreased communication overhead, it presents several challenges, including deployment complexity and interoperability issues, particularly in heterogeneous scenarios or resource-constrained environments. Over-the-air (OTA) FL was introduced to tackle these challenges by disseminating model updates without necessitating direct device-to-device connections or centralized servers. However, OTA-FL brought forth limitations associated with heightened energy consumption and network latency. In this article, we propose a multi-attribute client selection framework employing the grey wolf optimizer (GWO) to strategically control the number of participants in each round and optimize the OTA-FL process while considering accuracy, energy, delay, reliability, and fairness constraints of participating devices. We evaluate the performance of our multi-attribute client selection approach in terms of model loss minimization, convergence time reduction, and energy efficiency. In our experimental evaluation, we assessed and compared the performance of our approach against the existing state-of-the-art methods. Our results demonstrate that the proposed GWO-based client selection outperforms these baselines across various metrics. Specifically, our approach achieves a notable reduction in model loss, accelerates convergence time, and enhances energy efficiency while maintaining high fairness and reliability indicators.

关键词： Over-the-air federated learning client selection grey wolf optimizer convergence speed energy efficiency reliability fairness

来源：评论

学校读者我要写书评

暂无评论

Intelligent Auxiliary control System Interoperability Test Framework for Smart Substation with Communication Interference 4th

Intelligent Auxiliary Control System Interoperability Test F...

引用

4th International conference on Power and Electrical Engineering, ICPEE 2023

作者： Zhan, Xiaodong Feng, Fuyong Zheng, Ai Chang’an Communication Technology Co. Beijing China College of Computer Science and Cyber Security Chengdu University of Technology Chengdu China Smart Network Innovation Center China United Network Communications Limited Beijing China

ISBN: (纸本)9789819716739

At present, the intelligent auxiliary control system of smart substations lacks a unified and clear technical specification for entering the network, and the quality of products from various manufacturers varies, which adversely affects the operation and maintenance of smart substations. This paper proposes an interoperability test framework based on information simulation and considers the impact of perturbations caused by fluctuations in the substation communication network on the interoperability of the auxiliary control system. A schematic diagram of substation network communication interference is proposed. A network communication interference simulator can emulate false data interference (FDA), denial of service interference also known as network jamming interference (NJA), and device damage interference depending on the cause of the network simulation (DDA) for the test process. It carries out research on relevant function, performance, and protocol consistency test methods and develops a performance test system for the auxiliary control system of smart substations. The results show that the new test framework improves the interoperability of the Intelligent Auxiliary control System. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： control 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：