检索结果-内蒙古大学图书馆

63rd IEEE conference on Decision and control, CDC 2024

作者： Hirt, Sebastian Pfefferkorn, Maik Findeisen, Rolf Technical University of Darmstadt Control and Cyber-Physical Systems Laboratory Germany

ISBN: (纸本)9798350316339

Safe learning of control policies remains challenging, both in optimal control and reinforcement learning. In this article, we consider safe learning of parametrized predictive controllers that operate with incomplete information about the underlying process. To this end, we employ Bayesian optimization for learning the best parameters from closed-loop data. Our method focuses on the system's overall long-term performance in closed-loop while keeping it safe and stable. Specifically, we parametrize the stage cost function of an MPC using a feedforward neural network. This allows for a high degree of flexibility, enabling the system to achieve a better closed-loop performance with respect to a superordinate measure. However, this flexibility also necessitates safety measures, especially with respect to closed-loop stability. To this end, we explicitly incorporated stability information in the Bayesian-optimization-based learning procedure, thereby achieving rigorous probabilistic safety guarantees. The proposed approach is illustrated using a numeric example. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Observation and Backstepping control of Single-Phase Shunt Active Power Filter Connected to photovoltaic System 12

Observation and Backstepping Control of Single-Phase Shunt A...

引用

12th IFAC Symposium on control of Power and Energy systems (CPES)

作者： Khentaoui, O. Mchaouar, Y. Abouelmahjoub, Y. Abouobaida, H. Giri, F. Chakiri, S. Univ Chouaib Doukkali Natl Sch Appl Sci LabSIPE El Jadida 24002 Morocco Univ Caen Basse Normandie LAC LAB EA 7478 Caen France

The present paper concentrates on the improvement of power quality using a single-phase active power filter (APF) connected to the photovoltaic (PV) array operating in the presence of a non-linear load. A novel controller design, based on the energy stored in the half-bridge shunt APF is proposed to ensure two main objectives at the same time: (i) the transfer of active power to the electrical network by extracting the maximum of active power from the PV panels and regulating the PV voltage to a reference value provided by the MPPT;(ii) the improvement of power factor correction (PFC) by compensating for the harmonic current and reactive power produced by the non-linear load using the backstepping technique and Lyapunov tools. The nonlinear controller is developed in two loops. An inner loop is constituted of a PFC regulator based on the energy stored in the APF to minimize the total harmonic distortion (THD). An outer loop uses a linear PI regulator to regulate PV array voltage. The controller also comprised an observer to estimate the voltage network, which is not accessible to measurements. The performance of the proposed controller is validated by simulation using MATLAB/Simulink Copyright (c) 2024 The Authors.

关键词： Shunt active powerfilter PV arrays powerfactor correction network observer nonlinear control Backstepping technique Lyapunov tools

来源：评论

学校读者我要写书评

暂无评论

Arbitrary Convergence Time control for Aerial Manipulator with TSK Estimator

Arbitrary Convergence Time Control for Aerial Manipulator wi...

引用

IEEE International conference on Fuzzy systems (FUZZ-IEEE)

作者： Chen, Yanjie Liu, Xincheng Shang, Changjing Chen, Jianhui Chang, Xiang Chao, Fei Wang, Yaonan Fuzhou Univ Sch Mech Engn & Automat Fuzhou Peoples R China Aberystwyth Univ Dept Comp Sci Aberystwyth Wales Hunan Univ Coll Elect & Informat Engn Changsha Peoples R China

ISBN: (纸本)9798350319552;9798350319545

This paper investigates the stable control problem of unmanned aerial manipulator (UAM) in the presence of lumped disturbance, including modelling uncertainties and external inferences. These disturbances typically involve limited prior knowledge and change rapidly, presenting considerable challenges to real-time control accuracy. To address this issue, a Takagi-Sugeno-Kang estimator (TSKE) with K-closest fuzzy rules interpolation (K-FRI) is proposed to derive an approximation for the uncertain disturbances. The incorporation of K-FRI enhances the accuracy and convergence rate of the estimation under the conditions of a sparse fuzzy rule base with an incomplete fuzzy quantity space. Subsequently, a backstepping controller with arbitrary convergence time is introduced to guarantee the rapid and precise control of the UAM. The stability of both the TSKE and the controller with arbitrary convergence time is analysed through Lyapunov theory. The feasibility and performance of the proposed control strategy are validated via comparative experimental simulations, demonstrating its ability for robust estimation capability with stable control performance, at any convergence time of the UAM working under lumped disturbance.

关键词： Unmanned aerial manipulator fuzzy rule interpolation arbitrary convergence time control TSK estimator

来源：评论

学校读者我要写书评

暂无评论

Adaptive Nonsingular Terminal Sliding Mode control of Underwater Manipulator Based on Neural network and Combined Reaching Law 7

Adaptive Nonsingular Terminal Sliding Mode Control of Underw...

引用

7th IEEE International conference on Information systems and Computer Aided Education, ICISCAE 2024

作者： Xiong, Yujing Wang, Mei Wang, Qixuan School of Mechatronic and Automation Engineering Shanghai University Shanghai China

ISBN: (纸本)9798350350760

To address the trajectory tracking control of underwater manipulators with the interference of complex underwater environment, this paper proposes a nonsingular fast terminal sliding mode (NFTSM) control strategy based on an RBF neural network (RBFNN) and constructs a combined reaching law. The suggested NFTSM control strategy has the advantages of rapid convergence speed and finite convergence time. The constructed composite approaching law can accelerate the stabilization of the system. The neural network is chosen to maximally approximate the uncertain disturbances, including the model uncertainty error term and external disturbance term, which could reduce the chattering problem of the control system. Furthermore, the adaptive law is designed based on the Lyapunov theorem to make the entire system stable. This method is simulated on a 4-DOF manipulator for trajectory tracking, and its superior performance under random disturbances is demonstrated compared with the conventional sliding mode control (CSMC). ©2024 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

A Wireless Detection System that Utilizes an Artificial Neural network to Enhance Energy Efficiency and Prolong the Lifespan of the network 2

A Wireless Detection System that Utilizes an Artificial Neur...

引用

2nd International conference on Sustainable Computing and Smart systems (ICSCSS)

作者： Filicionus, J. Deivapraba, T. Samuvel, Sam Gilvine Sangeetha, Glory R. Niranjan, L. Vageesh, Vachana Sacred Heart Coll Arts & Sci Dept CSE Sci Dindigul India KGiSL Inst Technol Dept CSBS Coimbatore Tamil Nadu India CMR Inst Technol Dept AI & DS Bengaluru India Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala E Dept IT Chennai Tamil Nadu India CMR Inst Technol Dept ECE Bengaluru India

ISBN: (纸本)9798350391558;9798350379990

Nano-electro-mechanical designs (NEMD), wireless technology, additionally, digital electronics can make it possible to create small, inexpensive, and low-powered detection units that can communicate over short and multi-hop distances. The main issue for Cellular Detector systems (CDS) is to maximize battery power abstraction to increase network lifespan while reducing power consumption from regular input signals and operational expenses between access points and detector networks. Packet expenses, retransmissions, and control signal overhead fees add energy challenges. We suggest using random sampling and correct routing to conserve power and transport data quickly in the network significantly reducing the overhead of the control signal. Using neural network-based backpropagation, energy-efficient and nearby modules are predicted along with the information-promoting path to the endpoint for increasing the efficiency of packet transmission. This study illustrates the ways to optimize battery energy consumption without sacrificing data connection speed at low cost using simulations. This strategy improves detection system efficiency, network longevity, performance, and energy consumption to 76%, 68%, 79%, 82% respectively.

关键词： Cellular detector Neural systems Reliable routing Smart sampling Energy Efficient systems

来源：评论

学校读者我要写书评

暂无评论

Image Encryption Using Neural network Based Chaotic systems 3

Image Encryption Using Neural Network Based Chaotic Systems

引用

3rd International conference on Communication, control, and Intelligent systems, CCIS 2024

作者： Hoysala, A Sanath Aneesh, C.D. Venkatesh, Ananya Khambete, Neelank Deb, Susmita Pes University Department of Eee Bengaluru India

ISBN: (纸本)9798331528201

This paper introduces a unique image encryption methodology using the chaotic signals generated by a neural network for enhanced security. The proposed system employs a master-slave configuration where a Multi-Layer Perceptron (MLP) neural network acts as the master system for encryption, while the Hopfield neural network serves as the slave system generating the chaotic signal for decryption. The process of encryption involves the XOR operation between the input image and the chaotic signal generated by the master system. To ensure accurate synchronisation between the master-slave systems for decrypting the image, an Active Sliding Mode controller (ASMC) is used which ensures robust convergence and minimal synchronisation error. performance evaluation through histogram analysis shows that the proposed encryption method is more secure and efficient compared to the Advanced Encryption Standard (AES) method. © 2024 IEEE.

关键词： Hopfield neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-Optimizing control of Stochastic systems

Self-Optimizing Control of Stochastic Systems

引用

2024 IEEE International conference on systems, Man, and Cybernetics, SMC 2024

作者： Su, Hongxin Zhou, Chenchen Cao, Yi Zhang, Xuefeng Yang, Shuang-Hua College of Science Northeastern University Shenyang110819 China College of Chemical and Biological Engineering Zhejiang University Hangzhou310027 China Institute of Zhejiang University-Quzhou Quzhou324000 China University of Reading Department of Computer Science United Kingdom

ISBN: (纸本)9781665410205

Optimal control of stochastic systems involves finding control strategies that optimize certain performance criteria while accounting for the parametric uncertainties and stochastic additive disturbances involved in the system dynamics. Model predictive control (MPC) solves an open-loop constrained stochastic optimal control problem repeatedly in a receding-horizon manner, resulting in large computation sometimes. Alternatively, the proposed stochastic self-optimizing control (SOC) selects optimal nonlinear controlled variables (CVs) offline by minimizing the expectation of the weighted closed-loop loss function based on neural network training. The nonlinear self-optimizing CVs are simply kept constant online so that the satisfactory control performance can be achieved. The proposed stochastic SOC requires much less online computation time compared with MPC, which is demonstrated by a two-mass spring simulation model. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Advanced sensorless nonlinear control and stability analysis of single-stage PV systems connected to the grid via a 3L-NPC inverter

引用

EUROPEAN JOURNAL OF control 2024年 75卷

作者： Mchaouar, Youssef Abouelmahjoub, Youness Abouloifa, Abdelmajid Abouobaida, Hassan Lachkar, Ibtissam Giri, Fouad Taghzaoui, Chaimaa Elallali, Aicha Guerrero, Josep M. Univ Chouaib Doukkali LabSIPE Natl Sch Appl Sci El Jadida 24002 Morocco Hassan II Univ CESE lab ENSEM Casablanca Casablanca Morocco Univ Caen Basse Normandie LAC LAB EA 7478 Caen France Aalborg Univ Dept Energy Technol Aalborg Denmark

This paper proposes a novel control strategy for a single -stage photovoltaic (PV) system consisting of two PV panels connected to the grid via a three -level neutral point clamped converter topology with an LCL filter. This control method is based on a developed 5th order model containing sum and difference terms of the voltages of the two input capacitors. This allows decoupling the issues of maximum power point tracking and power factor correction from the issue of balancing the power exchange generated by the panels, which facilitates control design and improves system performances. The control problem under consideration is dealt with using a non-linear controller composed of three loops: (i) an inner loop is developed, based on backstepping and Lyapunov approaches, to correct the power factor by forcing the grid current to be sinusoidal and in phase with the grid voltage;(ii) an outer loop is designed, using a filtered proportional -integral controller, to regulate the DC bus voltage to a climate -dependent reference;(iii) a balancing loop is designed, using a proportional -integral controller, to cope with the neutral point voltage balancing problem. The proposed controller also includes a state observer that provides on-line estimation of the network state variables that are not accessible to measurements. Another important aspect of this work is the development of a formal, complete and rigorous analysis in order to describe the performance and analyse the stability of the closed -loop system using various analytical tools, including averaging theory, Routh criteria and indirect Lyapunov stability. A simulation in MATLAB/SIMULINK environment shows, on the one hand, the efficiency and robustness of the proposed nonlinear controller against changing climatic conditions and, on the other hand, the superiority of this control strategy compared to the one based on a PI linear inner loop controller for the studied system with an L - filter and an LCL filter. (c)

关键词： Photovoltaic system Neutral -point -clamped multilevel converter Backstepping MPPT Power factor correction Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Distributed Robust Time-Varying Formation control of Multi-Agent systems under Disturbances

Distributed Robust Time-Varying Formation Control of Multi-A...

引用

2024 Society of Instrument and control Engineers Festival with Annual conference

作者： Yang, Guang-Ze Yang, Zi-Jiang Ibaraki Univ Dept Mech Syst Engn Hitachi Ibaraki Japan

ISBN: (纸本)9798331544461;9784907764838

This work considers the problem of time-varying formation tracking control of second-order multi-agent systems under disturbances. A distributed robust time-varying formation control law is proposed including distributed finite-time estimators of the leader's states and sliding mode time-varying formation controllers. Firstly, each agent can quickly estimate the leader's states through the communication network in the distributed finite-time estimators based on the sliding mode estimation. Secondly, utilizing the estimates of the leader's states, a sliding mode time-varying formation controller is designed using the prescribed time modification function. Unlike traditional distributed control law relying on the exchanges of the agents' states, the proposed control design achieves great robustness and stability of the overall system by exchanging the estimates of the leader's states. According to Lyapunov stability analysis, we prove that the proposed approach enables the sliding variables to achieve fast finite-time convergence. Furthermore, simulation examples are provided to illustrate the performance.

关键词： multi-agent systems distributed control time-varying formation control sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Towards Effective network Intrusion Detection in Imbalanced Datasets: A Hierarchical Approach

Towards Effective Network Intrusion Detection in Imbalanced ...

引用

International conference on Computing, networking and Communications (ICNC)

作者： Towhid, Md Shamim Khan, Nasik Sami Hasan, Md Mahibul Shahriar, Nashid Univ Regina Dept Comp Sci Regina SK Canada

ISBN: (纸本)9798350371000;9798350370997

The transition from conventional networks to Software Defined networks (SDNs) has revolutionized network management and control, but it also creates a huge security risk, underscoring the significance of effective intrusion detection systems (IDS). Researchers have used deep learning for IDS due to its ability to capture complex patterns in data. Deep Learning techniques rely on ample balanced labeled data for effective intrusion detection, but acquiring such balanced data in real network scenarios is a formidable challenge, often resulting in suboptimal performance for existing methods when dealing with imbalanced datasets. This paper introduces a hierarchical approach that is capable of effectively detecting well-known network attacks in an SDN environment, even with minimal training data. Our model, leveraging a dataset collected from a real-world software-defined wide area network (SD-WAN) environment, showcases remarkable adaptability by maintaining strong performance even with highly imbalanced data, i.e., attack samples with as few as 8 or 16 instances to others with hundreds, thousands, or even millions of instances. It consistently achieves an overall average F1 score above 92%, with minority class average F1 score reaching more than 84%, marking a substantial 22.50% performance improvement compared to selected baselines in our evaluation.

关键词： intrusion detection deep learning flow-based classification SDN

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：