检索结果-内蒙古大学图书馆

Reliable control of cyber-physical systems under sensor and actuator attacks: An identifier-critic based integral sliding-mode control approach

引用

NEUROCOMPUTING 2019年 361卷 229-242页

作者： Huang, Xin Dong, Jiuxiang Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110819 Liaoning Peoples R China Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Liaoning Peoples R China Northeastern Univ Shenyang Minist Educ Key Lab Vibrat & Control Aeroprop Syst Shenyang 110819 Liaoning Peoples R China

This study focuses on reliable control problems for cyber-physical systems (CPSs), described by linear continuous time-invariant systems, under a class of time-varying state-dependent sensor and actuator attacks. According to the state-dependent property of sensor attacks, the original reliable control problem is converted into a problem to stabilise a completely unknown time-varying system with the actuator attacks. Firstly, a dynamic neural network (NN) identifier with an indicator-function term is developed to model the unknown system dynamics. Due to the indicator term, the input distribution matrix of the identifier is guaranteed to be of full column rank. It provides a technical condition for designing an effective identifier-based integral sliding-mode (I-SM) attack compensator. It is shown that, under the proposed adaptive law, the identification errors and NN weight estimation errors are uniformly ultimately bounded. Furthermore, an identifier-critic based I-SM controller, which consists of an ADP-based controller and an adaptive I-SM attack compensator, is online learned using real-time control input and compromised sensor data, such that the unknown dynamics with the actuator attacks is stable with a nearly optimal performance. Meanwhile, it is shown that, the developed control approach ensures that the states in CPSs under sensor and actuator attacks converge to a compact set around zero. Finally, the effectiveness of the proposed one is verified by two illustrative examples. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Cyber-physical systems Cyber security Reliable control Sensor and actuator attacks Integral sliding-mode control adaptive dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Approximate Optimal Stabilization Control of Servo Mechanisms based on Reinforcement Learning Scheme

引用

INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS 2019年第10期17卷 2655-2665页

作者： Lv, Yongfeng Ren, Xuemei Hu, Shuangyi Xu, Hao Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China

A reinforcement learning (RL) based adaptive dynamic programming (ADP) is developed to learn the approximate optimal stabilization input of the servo mechanisms, where the unknown system dynamics are approximated with a three-layer neural network (NN) identifier. First, the servo mechanism model is constructed and a three-layer NN identifier is used to approximate the unknown servo system. The NN weights of both the hidden layer and output layer are synchronously tuned with an adaptive gradient law. An RL-based critic three-layer NN is then used to learn the optimal cost function, where NN weights of the first layer are set as constants, NN weights of the second layer are updated by minimizing the squared Hamilton-Jacobi-Bellman (HJB) error. The optimal stabilization input of the servomechanism is obtained based on the three-layer NN identifier and RL-based critic NN scheme, which can stabilize the motor speed from its initial value to the given value. Moreover, the convergence analysis of the identifier and RL-based critic NN is proved, the stability of the cost function with the proposed optimal input is analyzed. Finally, a servo mechanism model and a complex system are provided to verify the correctness of the proposed methods.

关键词： adaptive dynamic programming neural networks optimal control reinforcement learning servomechanisms

来源：评论

学校读者我要写书评

暂无评论

Neural-network-based output-feedback control with stochastic communication protocols

引用

AUTOMATICA 2019年 106卷 221-229页

作者： Ding, Derui Wang, Zidong Han, Qing-Long Swinburne Univ Technol Sch Software & Elect Engn Melbourne Vic 3122 Australia Shandong Univ Sci & Technol Coll Elect Engn & Automat Qingdao 266590 Shandong Peoples R China Brunel Univ London Dept Comp Sci Uxbridge UB8 3PH Middx England

This paper is concerned with the neural-network-based (NN-based) output-feedback control issue for a class of nonlinear systems. For the purpose of effectively mitigating the phenomena of data congestion/collision, the stochastic communication protocols are favorably utilized to orchestrate the data transmissions, and the resultant closed-loop plant is represented by a so-called protocol-induced Markovian jump system with uncertain transition probability matrices. Taking such an uncertainty probability into account, a novel iterative adaptive dynamic programming (ADP) algorithm is developed to obtain the desired suboptimal solution with the help of auxiliary quasi-HJB equation, and the algorithm convergence is also investigated via the intensive use of the mathematical analysis. In this ADP framework, an NN-based observer with a novel adaptive tuning law is first adopted to reconstruct the system states. Then, based on the reconfigurable system, an actor-critic NN scheme with online learning is developed to realize the considered control strategy. Furthermore, in light of the Lyapunov theory, some sufficient conditions are derived to guarantee the stability of the zero equilibrium point of the closed-loop system as well as the boundedness of the estimation errors for critic and actor NN weights. Finally, a simulation example is employed to demonstrate the effectiveness of the developed suboptimal control scheme. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Output-feedback control Stochastic communication protocols adaptive dynamic programming Actor-critic structures

来源：评论

学校读者我要写书评

暂无评论

Actor-Critic-Identifier Structure-Based Decentralized Neuro-Optimal Control of Modular Robot Manipulators With Environmental Collisions

引用

IEEE ACCESS 2019年 7卷 96148-96165页

作者： Dong, Bo An, Tianjiao Zhou, Fan Liu, Keping Yu, Weibo Li, Yuanchun Changchun Univ Technol Dept Control Sci & Engn Changchun 130012 Jilin Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

This paper presents a decentralized zero-sum optimal control method for MRMs with environmental collisions via an actor-critic-identifier (ACI) structure-based adaptive dynamic programming (ADP) algorithm. The dynamic model of the MRMs is formulated via a novel collision identification method that is deployed for each joint module, in which the local position and torque information are used to design the model compensation controller. A neural network (NN) identifier is developed to compensate the model uncertainties and then, the optimal control problem of the MRMs with environmental collisions can be transformed into a two-player zero-sum optimal control one. Based on the ADP algorithm, the HamiltonJacobi-Isaacs (HJI) equation is solved by constructing the actor-critic NNs, thus making the derivation of the approximate optimal control policy feasible. Based on the Lyapunov theory, the closed-loop robotic system is proved to be asymptotically stable. Finally, the experiments are conducted to verify the effectiveness and advantages of the proposed method.

关键词： adaptive dynamic programming collision identification decentralized optimal control modular robot manipulators zero-sum game

来源：评论

学校读者我要写书评

暂无评论

Model-Free Optimal Consensus Control of Networked Euler-Lagrange Systems

引用

IEEE ACCESS 2019年 7卷 100771-100779页

作者： Zhang, Huaipin Park, Ju H. Zhao, Wei Nanjing Univ Posts & Telecommun Inst Adv Technol Nanjing 210023 Jiangsu Peoples R China Yeungnam Univ Dept Elect Engn Gyongsan 38541 South Korea Southeast Univ Sch Math Nanjing 210096 Jiangsu Peoples R China

This paper considers the model-free optimal consensus problem of networked Euler-Lagrange systems without velocity measurements. By employing the position information, a novel neural network-based velocity observer is built for each agent to estimate the unmeasurable velocity vector and unknown system model. Based on the estimated velocity information, we propose distributed optimal control policies depended on the solutions to the coupled Hamilton-Jacobi-Bellman (HJB) equations. Then, a model-free policy iteration (PI) algorithm is provided to learn the coupled HJB equations online. To implement the PI algorithm, the critic-action neural networks are built and their weights are updated based on the gradient descent method. The uniform ultimate boundedness of the integrated observer estimation errors, the integrated consensus errors, and the weight estimation errors for the observer-critic-action neural networks is demonstrated by the Lyapunov technique. Finally, the numerical simulation on a directed network with six nonlinear manipulators is presented to validate the theoretical results.

关键词： Euler-Lagrange systems adaptive dynamic programming consensus control adaptive observer

来源：评论

学校读者我要写书评

暂无评论

Data-driven optimal event-triggered consensus control for unknown nonlinear multiagent systems with control constraints

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL 2019年第14期29卷 4828-4844页

作者： Zhang, Huaipin Park, Ju H. Yue, Dong Dou, Chunxia Nanjing Univ Posts & Telecommun Inst Adv Technol Nanjing Jiangsu Peoples R China Yeungnam Univ Dept Elect Engn Gyongsan 38541 South Korea

This paper considers optimal consensus control problem for unknown nonlinear multiagent systems (MASs) subjected to control constraints by utilizing event-triggered adaptive dynamic programming (ETADP) technique. To deal with the control constraints, we introduce nonquadratic energy consumption functions into performance indices and formulate the Hamilton-Jacobi-Bellman (HJB) equations. Then, based on the Bellman's optimality principle, constrained optimal consensus control policies are designed from the HJB equations. In order to implement the ETADP algorithm, the critic networks and action networks are developed to approximate the value functions and consensus control policies respectively based on the measurable system data. Under the event-triggered control framework, the weights of the critic networks and action networks are only updated at the triggering instants which are decided by the designed adaptive triggered conditions. The Lyapunov method is used to prove that the local neighbor consensus errors and the weight estimation errors of the critic networks and action networks are ultimately bounded. Finally, a numerical example is provided to show the effectiveness of the proposed ETADP method.

关键词： adaptive dynamic programming control constraints event-triggered sampling multiagent systems

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking Control for Robotic Manipulator using Actor-Critic Network

Optimal Tracking Control for Robotic Manipulator using Actor...

引用

第40届中国控制会议

作者： Yong Hu Lingguo Cui Senchun Chai Beijing Institute of Technology

This paper proposed an optimal control scheme based on the actor-critic neural network(NN) for the complex mechanical manipulator system with dynamic disturbance. The actor's goal is to optimize control behavior, while the critic's goal is to evaluate control performance. The optimal control update law in the scheme can guarantee the system error and the weight estimation error SGUUB, and its stability and convergence are proved based on the direct Lyapunov method. Finally, the connecting rods on two degrees of freedom are tested to verify the effectiveness of the proposed optimal control scheme.

关键词： Optimized tracking control neural network(NN) adaptive dynamic programming actor-critic

来源：评论

学校读者我要写书评

暂无评论

Robust adaptive Control of Maximum Power Point Tracking for Wind Power System

引用

IEEE ACCESS 2020年 8卷 214538-214550页

作者： Chen, Peng Han, Dezhi Li, Kuan-Ching Shanghai Maritime Univ Dept Comp Sci & Technol Shanghai 200120 Peoples R China Providence Univ Dept Comp Sci & Informat Engn CSIE Taichung 43301 Taiwan

A novel data-driven robust approximate optimal Maximum Power Point Tracking (MPPT) control method is proposed for the wind power generation system by using the adaptive dynamic programming (ADP) algorithm. First, a data-driven model is established by a recurrent neural network (NN) to reconstruct the wind power system dynamics using available input-output data. Then, in the design of the controller, based on the obtained data-driven model, the ADP algorithm is utilized to design the approximate optimal tracking controller, which consists of the steady-state controller and the optimal feedback controller. Ulteriorly, developing a robustifying term to compensate for the NN approximation errors introduced by implementing the ADP method. Based on the Lyapunov approach, it proves the stability of the designed model and controller to show that the proposed controller guarantees the system power asymptotically tracking the maximum power. Finally, the simulation results demonstrate that the control method stabilizes the tip speed ratio near the optimal value when the wind speed is lower than the rated wind speed. Moreover, the tracking response speed of the proposed method is fast, which enhances the stability and robustness of the system.

关键词： Wind power generation Wind energy Wind speed Mathematical model dynamic programming Wind turbines Recurrent neural networks adaptive dynamic programming maximum power point tracking neural network wind power system

来源：评论

学校读者我要写书评

暂无评论

Optimal trajectory tracking control based on reinforcement learning for the deployment process of space tether system

引用

IFAC-PapersOnLine 2020年第1期53卷 679-684页

作者： Yiting Feng Changqing Wang Aijun Li School of Automation Northwestern Polytechinal University Xi’an 710072 China

Space tether system has a wide application prospect in space mission. Due to the characteristics of strong non-linearity and under-actuation, as well as the interference of complex space environment, it is difficult to model the tethered system accurately. Hence, the controller based on the parameters of the system model will cause large errors in the process of control. In this paper, an adaptive dynamic programming algorithm based on reinforcement learning theory is adopted. By training two Back Propagation (BP) neural networks, namely critic neural network (NN) and actor NN, the performance index function and control law of the system approach approximate optimal values respectively. The controller design is independent of the system model, so model-free control of the system is realized by implementing this control method. First, assuming that the out-of-plane motion of the system is stable, the optimal deployment trajectory of the tethered system is obtained by parameter optimization based on Nelder-Mead method. The optimal trajectory is taken as the nominal trajectory and the trajectory tracking is carried out by reinforcement learning controller. The simulation results show that the reinforcement learning algorithm has a good control effect on the in-plane trajectory tracking of the tethered system, which proves the feasibility and robustness of the control method.

关键词： space tether system deployment trajectory tracking neural network adaptive dynamic programming reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Structured Online Learning-based Control of Continuous-time Nonlinear Systems ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 8142-8149页

作者： Milad Farsi Jun Liu Applied Mathematics Department University of Waterloo Canada

Model-based reinforcement learning techniques accelerate the learning task by employing a transition model to make predictions. In this paper, a model-based learning approach is presented that iteratively computes the optimal value function based on the most recent update of the model. Assuming a structured continuous-time model of the system in terms of a set of bases, we formulate an infinite horizon optimal control problem addressing a given control objective. The structure of the system along with a value function parameterized in the quadratic form provides a flexibility in analytically calculating an update rule for the parameters. Hence, a matrix differential equation of the parameters is obtained, where the solution is used to characterize the optimal feedback control in terms of the bases, at any time step. Moreover, the quadratic form of the value function suggests a compact way of updating the parameters that considerably decreases the computational complexity. Considering the state-dependency of the differential equation, we exploit the obtained framework as an online learning-based algorithm. In the numerical results, the presented algorithm is implemented on four nonlinear benchmark examples, where the regulation problem is successfully solved while an identified model of the system is obtained with a bounded prediction error.

关键词： Reinforcement learning Model-based learning Optimal control Feedback control Continuous-time control adaptive dynamic programming Sparse identification

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：