检索结果-内蒙古大学图书馆

Theory and experiment for autonomous quadrotor flight via bounded robust finite-time homogeneous sliding mode control: A roadmap to search and rescue

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF systems AND control ENGINEERING 2025年第4期239卷 674-699页

作者： Messaoui, Aimen Abdelhak Mechali, Omar Louali, Rabah Nemra, Abdelkrim Ecole Mil Polytech Bordj El Bahri 16046 Algiers Algeria Ecole Super Ali CHABATI Reghaia Algeria Univ Elect Sci & Technol China Sch Aeronaut & Astronaut Chengdu Peoples R China

This paper introduces a new saturated robust control technique for quadrotor aircraft modeled by second-order Ordinary Differential Equations (ODEs), considering disturbances in the control channel (matched disturbances). The control design employs a Sliding Mode control (SMC) approach, featuring in: (i) a novel saturated homogeneous sliding manifold, (ii) a novel tracking controller, namely, Bounded Robust Finite-Time Homogeneous Sliding Mode control (BRFTHSMC). An Improved Fixed-time Convergent Extended State Observer (IFCESO) is incorporated into the control scheme to handle disturbances. Together the BRFTHSMC and the IFCESO establish a reliable Active Disturbance Rejection control (ADRC) framework. The latter ensures finite-time convergence of the errors quantities to the origin along with effective disturbance rejection. Rigorous stability analysis is conducted based on Lyapunov theory. Beside control design, another distinguishing theoretical outcome of this paper in the form of Corollary is the extension of the present results to integrator-type systems (higher-order systems). The study is substantiated through MATLAB (R)/Simulink simulations and Robot Operating System (ROS)/Gazebo implementation, validating the theoretical foundation. Extensive experimental tests on real hardware, including attitude and Cartesian trajectory tracking under various disturbances, further affirm the theoretical findings. The synthesized control system surpasses alternative methods in terms of control signal's boundedness, finite-time tracking stability, transient response performance, and steady-state precision. Notably, the control input circumvents singularity challenges observed in conventional SMC approaches. In addition to trajectory tracking experiments, the controller's effectiveness is demonstrated in real-world search and rescue scenarios. Therefore, a Deep Neural network (DNN) algorithm, based on a MS COCO-pretrained Single Shot Detector (SSD-Mobilenet-v2), is employed

关键词： Quadrotor system bounded/saturated control finite-time convergence homogeneous sliding mode control extended state observer active disturbance rejection control search and rescue

来源：评论

学校读者我要写书评

暂无评论

CNN-based Application Recognition to Enhance network Governance for Financial networks

CNN-based Application Recognition to Enhance Network Governa...

引用

12th IEEE International conference on Computer, Information and Telecommunication systems (CITS)

作者： Gadhiya, Urmil Faldu, Preet Darji, Krisha Obaidiat, Mohammad S. Gupta, Rajesh Tanwar, Sudeep Nirma Univ Inst Technol Dept Comp Sci & Engn Ahmadabad Gujarat India Univ Jordan King Abdullah II Sch Informat Tech Amman 11942 Jordan Univ Sci & Technol Beijing Sch Comp & Commun Engn Beijing 100083 Peoples R China SRM Univ Sch Comp Dept Computat Intelligence Kattankulathur 603203 TN India Amity Univ Sch Engn Noida 201301 UP India

ISBN: (纸本)9798350359107;9798350359091

Effective network governance is essential to guarantee optimal performance, security, and resource allocation in the increasing variety of network applications and the growing complexity of network environments. In this study, we used convolutional neural network (CNN)-based application recognition which uses deep learning techniques to identify network applications and classify them accurately. We designed and evaluated a customized CNN architecture for a recognition application, using raw data as input to capture unique patterns and features. We demonstrate the efficiency of our method in accurately identifying the variety of network applications through an experiment performed on real-world network datasets, that includes web browsing, video streaming, file transfer, and more. We then evaluate the performance of our system using various performance evaluating measures, which include accuracy, precision, recall, and F1-score, and then compare it with the traditional methods to emphasize its superiority in accuracy and efficiency. Lastly, our research on this comes up with the advancement of network governance by providing powerful and scalable solutions for application network management which makes a way to improve network performance, security, and resource development.

关键词： network Traffic Classification CNN-based application recognition network Governance

来源：评论

学校读者我要写书评

暂无评论

5G NSA performance: A Measurement Study 19

5G NSA Performance: A Measurement Study

引用

19th Wireless On-Demand network systems and Services conference (WONS)

作者： Moreno, Joao Contini, Marcello Aguiar, Ana Univ Porto Fac Engn Inst Telecomunicacoes Porto Portugal

ISBN: (纸本)9783903176614

5G cellular technology has been widely deployed in several countries by multiple operators in the form of non-standalone (NSA) networks. These networks rely on the 4G control plane and switch to 5G's New Radio (NR) technology for use plane traffic on the radio access, while the transport network is the same as 4G's. Several promising use cases have been showcased, some on top of these commercial networks. However, there is still limited understanding of NR performance in the wild. In this paper, we measure the 5G NR throughput on a 5G NSA base station on campus using a COTS mobile device instrumented with a radio access protocol analyzer. We show that 5G NR user throughput reaches almost 1 Gbps, meeting enhanced broadband expectations. We observe that throughput performance for 5G NR suffers strongly from non-line-of-sight conditions. Further, we analyze throughput differences when there is walking movement when compared to static measurements. We identify unexpected behavior in 5G NR at one location, similar to other 5G performance studies. our results also hint at potential 5G NR rate adaptation inefficiency.

关键词： 5G New Radio Application performance Mobile network Measurement Physical Layer Throughput

来源：评论

学校读者我要写书评

暂无评论

Safe reinforcement learning-based control using deep deterministic policy gradient algorithm and slime mould algorithm with experimental tower crane system validation

引用

INFORMATION SCIENCES 2025年 692卷

作者： Zamfirache, Iuliu Alexandru Precup, Radu-Emil Petriu, Emil M. Politehn Univ Timisoara Dept Automat & Appl Informat Bd V Parvan 2 Timisoara 300223 Romania Romanian Acad Ctr Fundamental & Adv Tech Res Timisoara Branch Bd Mihai Viteazu 24 Timisoara 300223 Romania Univ Ottawa Sch Elect Engn & Comp Sci 800 King Edward Ottawa ON K1N 6N5 Canada

This paper presents a novel optimal control approach resulting from the combination between the safe Reinforcement Learning (RL) framework represented by a Deep Deterministic Policy Gradient (DDPG) algorithm and a Slime Mould Algorithm (SMA) as a representative nature-inspired optimization algorithm. The main drawbacks of the traditional DDPG-based safe RL optimal control approach are the possible instability of the control system caused by randomly generated initial values of the controller parameters and the lack of state safety guarantees in the first iterations of the learning process due to (i) and (ii): (i) the safety constraints are considered only in the DDPG-based training process of the controller, which is usually implemented as a neural network (NN);(ii) the initial values of the weights and the biases of the NN-based controller are initialized with randomly generated values. The proposed approach mitigates these drawbacks by initializing the parameters of the NN-based controller using SMA. The fitness function of the SMA-based initialization process is designed to incorporate state safety constraints into the search process, resulting in an initial NN-based controller with embedded state safety constraints. The proposed approach is compared to the classical one using real-time experimental results and performance indices popular for optimal reference tracking control problems and based on a state safety score.

关键词： Deep deterministic policy gradient Optimal reference tracking control Safe reinforcement learning Slime mould algorithm Tower crane systems

来源：评论

学校读者我要写书评

暂无评论

Output tracking control of discrete network time-delay systems under input quantization and colored noise 35

Output tracking control of discrete network time-delay syste...

引用

35th Chinese control and Decision conference (CCDC)

作者： Du, Yang Yang, Qingsheng Zhan, Xisheng Wu, Jie Hubei Normal Univ Sch Elect Engn & Automat Huangshi 435002 Hubei Peoples R China

ISBN: (纸本)9798350334722

In this paper, we study the output tracking control (OTC) performance of multi-input-multi-output (MIMO) discrete network time-delay systems under input quantization and colored noise, at the same time, the effect of output channel energy limitation is considered. On the basis of the coprime decomposition, all-pass factorization, inner-outer factorization and Youla parameterization of two-degree-of-freedom (TDOF) compensator, a new performance index is proposed and the exact expression of the system OTC performance is derived by designing the compensator. The results show that the OTC performance is determined by the position and direction of the non-minimum phase (NMP) zeros and unstable poles (UPs) and time-delay of the controlled plant. In addition, the presence of quantization error, bandwidth constraints, coding and decoding and colored noise can also affect the tracking performance. Finally, a simulation example proves the accuracy of the theory.

关键词： network time-delay systems colored noise quantization error bandwidth constraints

来源：评论

学校读者我要写书评

暂无评论

Hybrid-Triggered H∞ control for networked control systems With Deception Attacks

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems ii-EXPRESS BRIEFS 2023年第9期70卷 3494-3498页

作者： Li, Hengqian Yang, Qingsheng Zhan, Xisheng Wu, Jie Yan, Huaicheng Hubei Normal Univ Coll Elect Engn & Automat Huangshi 435002 Peoples R China East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China

discrete networked control systems with decep-tion attacks, the problem of H-8 output feedback control based on hybrid event triggered is studied. Firstly, we propose a novel hybrid-triggered mechanism to save effect of network band -with. Secondly, considering the impact of deception attacks, a cooperative control method with hybrid event triggered and observer-based output feedback is obtained. We derive some new sufficient conditions for the stability and H-8 performance of the networked control systems by constructing a new type of Lyapunov function and using linear matrix inequality, etc. At the same time, we obtain observer and control gain matrix. Finally, we give the simulation example to prove feasibility and rationality of the control strategy.

关键词： networked control systems deception attacks hybrid-triggered mechanism observer-based and output control

来源：评论

学校读者我要写书评

暂无评论

Design of Neural network based control System for BLDC Motor 3

Design of Neural Network based Control System for BLDC Motor

引用

3rd International conference on Electronics and Renewable systems, ICEARS 2025

作者： Sunori, Sandeep Kumar Mittal, Amit Jain, Shilpa Juneja, Pradeep Graphic Era Hill University Department of Ece Bhimtal Campus Bhimtal India Graphic Era Hill University Department of Evs Bhimtal Campus Bhimtal India Graphic Era Hill University Department of Cse Bhimtal Campus Bhimtal India Graphic Era University Department of Ece Dehradun India

ISBN: (纸本)9798331509675

BLDC (Brushless DC) motors are well-known for their high reliability and smaller maintenance cost. For attaining optimal performance, accurate speed control is critical, especially in dynamic load conditions. This work proposes the designing of a neural-network based PI (Proportional-Integral) controller developed in MATLAB for improving the control performance of BLDC motor. Mathematical modelling approach has been employed for describing the dynamics of motor including current, voltage, back emf, and torque equations. The training data containing control voltages and speed errors for feedforward neural network is generated on the basis of a conventional PI controller used initially. It enables the dynamic adjustment of the gains of PI controller in real-time. A neural network is integrated in the proposed controller to overcome the shortcomings of conventional PI controller like fixed gain parameters and poor adaptability to fluctuating operating conditions. Simulations have been conducted for evaluating the performance of developed controller under various conditions. The results exhibit remarkable improvements in key performance parameters. © 2025 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

H∞ Optimal Distributed Tracking control of network Distributed systems over Directed networks via Off-Policy Reinforcement Learning

H∞ Optimal Distributed Tracking Control of Network Distribu...

引用

European control conference (ECC)

作者： Kucuksayacigil, Gulnihal Uskudar Univ Fac Engn & Nat Sci Elect Elect Engn TR-34662 Istanbul Turkiye

ISBN: (纸本)9783907144084

In this work, an algorithm has been developed for heterogeneous network distributed systems (NDS) communicating over a directed network to solve H-infinity optimal distributed tracking control problem of continuous-time systems benefiting off-policy reinforcement learning. It should be noted that recent works on heterogeneous NDS have studied the tracking control problem with decentralized performance functions defined for each subsystem in the network, whereas a global performance function has been defined in this work for the whole NDS. The optimal distributed control problem has been defined as a sequential convex optimization problem benefiting off-policy reinforcement learning with sparsity constraints introduced on the state feedback controller gain. Finally, the efficacy of the proposed algorithm is shown by a numerical simulation on heterogeneous NDS.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Neuro Fuzzy network for Nonlinear Active Noise control systems 43

An Adaptive Neuro Fuzzy Network for Nonlinear Active Noise C...

引用

43rd Chinese control conference (CCC)

作者： Tin, Nguyen Thi Trung Na, Jing Le Thai, Nguyen Huang, Yingbo Li, Gengen Kunming Univ Sci Technol Fac Mech & Elect Engn Kunming 650500 Yunnan Peoples R China Kunming Univ Sci Technol Yunnan Key Lab Intelligent Control & Applicat Kunming 650500 Yunnan Peoples R China Nguyen Tat Thanh Univ Fac Engn & Technol Ho Chi Minh City 700000 Vietnam

ISBN: (纸本)9798350366907;9789887581581

This paper presents an Adaptive Neuro Fuzzy network (ANFN) for enhancing the performance of nonlinear feedforward active noise control systems. The proposed controller is a combination of the fuzzy logic technique and adaptive neural network. The Filtered-X Least Mean Square (FXLMS) algorithm is used to update the weights of the nonlinear ANFN controller. The convergence of the proposed control system is also proven by using a discrete Lyapunov function, and simulation results are given to demonstrate the effectiveness of the proposed method.

关键词： Nonlinear active noise control (NLANC) filtered-x least-mean-square (FXLMS) algorithm Adaptive Neuro-Fuzzy network (ANFN) nonlinear path

来源：评论

学校读者我要写书评

暂无评论

Input-to-State Stable Coupled Oscillator networks for Closed-form Model-based control in Latent Space 38

Input-to-State Stable Coupled Oscillator Networks for Closed...

引用

38th conference on Neural Information Processing systems, NeurIPS 2024

作者： Stölzle, Maximilian Della Santina, Cosimo Department of Cognitive Robotics Delft University of Technology Netherlands

Even though a variety of methods have been proposed in the literature, efficient and effective latent-space control (i.e., control in a learned low-dimensional space) of physical systems remains an open challenge. We argue that a promising avenue is to leverage powerful and well-understood closed-form strategies from control theory literature in combination with learned dynamics, such as potential-energy shaping. We identify three fundamental shortcomings in existing latent-space models that have so far prevented this powerful combination: (i) they lack the mathematical structure of a physical system, (ii) they do not inherently conserve the stability properties of the real systems, (iii) these methods do not have an invertible mapping between input and latent-space forcing. This work proposes a novel Coupled Oscillator network (CON) model that simultaneously tackles all these issues. More specifically, (i) we show analytically that CON is a Lagrangian system - i.e., it possesses well-defined potential and kinetic energy terms. Then, (ii) we provide formal proof of global Input-to-State stability using Lyapunov arguments. Moving to the experimental side, we demonstrate that CON reaches SoA performance when learning complex nonlinear dynamics of mechanical systems directly from images. An additional methodological innovation contributing to achieving this third goal is an approximated closed-form solution for efficient integration of network dynamics, which eases efficient training. We tackle (iii) by approximating the forcing-to-input mapping with a decoder that is trained to reconstruct the input based on the encoded latent space force. Finally, we leverage these three properties and show that they enable latent-space control. We use an integral-saturated PID with potential force compensation and demonstrate high-quality performance on a soft robot using raw pixels as the only feedback information. © 2024 Neural information processing systems foundation. All rights

关键词：

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：