检索结果-内蒙古大学图书馆

Multilayer adaptive critic design with digital twin for data-driven optimal tracking control and industrial applications

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartB期133卷

作者： Wang, Ding Ma, Hongyu Qiao, Junfei Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Univ Technol Key Lab Computat Intelligence & Intelligent Syst Beijing 100124 Peoples R China Beijing Univ Technol Lab Smart Environm Protect Beijing 100124 Peoples R China Beijing Univ Technol Inst Artificial Intelligence Beijing 100124 Peoples R China

In this paper, an optimal trajectory tracking control problem for general nonlinear systems is investigated. An adaptive critic control method with the digital twin (DT) theory is developed. Divergent from the existing tracking control methods, the advantages of adaptive dynamic programming (ADP) and the theory of DT are combined in this paper, and the novel multilayer artificial system structure is constructed. The actioncritic structure is employed by each artificial system to obtain an approximate optimal control policy. The model network (MN) is built by using the actual input and output data sets of the controlled system, which means the dependence on the dynamics of the system is overcame. Then, the weights of the trained action network (AN) and MN are passed to the real system to realize the optimal tracking control. The feasibility of the algorithm is proved by theoretical analysis. Finally, the algorithm is applied to a simple nonlinear torsional pendulum system and an industrial wastewater treatment system (WWTS), and the effectiveness of the algorithm is verified. The algorithm effectively realizes the tracking control of nonlinear systems.

关键词： adaptive dynamic programming Data-driven control Digital twin theory Neural networks Tracking control Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Optimized intelligent tracking control for a quadrotor unmanned aerial vehicle with actuator failures

引用

AEROSPACE SCIENCE AND TECHNOLOGY 2024年 144卷

作者： Li, Bo Liu, Hui Ahn, Choon Ki Gong, Wenquan Shanghai Maritime Univ Inst Logist Sci & Engn Shanghai 201306 Peoples R China Korea Univ Sch Elect Engn Seoul 136701 South Korea

This work investigates the implementation of tracking control for a quadrotor unmanned aerial vehicle exposed to disturbances and actuator failures. Cost reduction in control processes is not usually considered in conventional control methods. To overcome this limitation, this work proposes an optimized intelligent control scheme that utilizes adaptive dynamic programming. Firstly, a critic-only structure is employed to learn the nominal control strategies, including two critic neural network update laws, lifting the persistent excitation condition. Subsequently, two specifically designed observers are developed on the radial basis function neural network (RBFNN) to reconstruct the disturbances and actuator failures and compensate for the nominal strategies. The observers achieve fixed-time convergence by employing the fixed-time update laws of the RBFNNs. Moreover, two variable vectors using the Gaussian error function are introduced to reduce the impact caused by the observation errors. Additionally, the superior performance of the proposed control scheme is validated through numerical simulations.

关键词： Quadrotor adaptive dynamic programming Fault-tolerant control Radial basis function neural network

来源：评论

学校读者我要写书评

暂无评论

dynamic compensator-based near-optimal control for unknown nonaffine systems via integral reinforcement learning

引用

NEUROCOMPUTING 2024年 564卷

作者： Lin, Jinquan Zhao, Bo Liu, Derong Wang, Yonghua Guangdong Univ Technol Sch Automat Guangzhou 510006 Peoples R China Beijing Normal Univ Sch Syst Sci Beijing 100875 Peoples R China Southern Univ Sci & Technol Sch Syst Design & Intelligent Mfg Shenzhen 518055 Peoples R China Univ Illinois Dept Elect & Comp Engn Chicago IL 60607 USA

In this paper, a dynamic compensator-based near-optimal control approach for unknown nonaffine nonlinear systems is developed by using integral reinforcement learning. Since system dynamics is unknown, it is difficult to obtain the optimal control policy via neuro-dynamic programming. To address this problem, a general dynamic compensator is introduced as the virtual control input to augment the unknown nonaffine nonlinear system as a partially unknown affine system. For the augmented system, a novel quadratic value function is designed with the system states, the actual control input and the virtual control input. The optimal control of the augmented system can be regarded as the near-optimal control for the original system since the novel optimal value function is an upper bound of the original optimal value function. In order to avoid the identification of system dynamics, the integral reinforcement learning framework is utilized to derive the optimal control based on the solution of Hamilton-Jacobi-Bellman equation via the critic-only structure. Meanwhile, the weight learning rule of the critic neural network is presented with the experience replay technique to relax the persistence of excitation condition. Moreover, the uniform ultimate boundedness of weight estimation errors and the stability of the closed-loop system are guaranteed by using the Lyapunov's direct method. Finally, simulation results of two examples demonstrate the effectiveness of the developed dynamic compensator-based near-optimal control method.

关键词： Neuro-dynamic programming adaptive dynamic programming Reinforcement learning Optimal control Neural networks dynamic compensator

来源：评论

学校读者我要写书评

暂无评论

Neural network-based adaptive critic control for saturated nonlinear systems with full state constraints via a novel event-triggered mechanism

引用

INFORMATION SCIENCES 2024年 675卷

作者： Zhao, Heng Wang, Huanqing Chang, Xiaoheng Ahmad, Adil M. Zhao, Xudong Bohai Univ Coll Control Sci & Engn Jinzhou 121013 Liaoning Peoples R China Bohai Univ Coll Math Sci Jinzhou 121013 Liaoning Peoples R China King Abdulaziz Univ Fac Comp & Informat Technol Dept Informat Technol Commun Syst & Networks Res Grp Jeddah Saudi Arabia Dalian Univ Technol Fac Elect Informat & Elect Engn Dalian 116024 Liaoning Peoples R China

This paper investigates the issue of event-triggered optimal control for saturated nonlinear systems with full state constraints. A smooth function is defined to map the constrained states, then the considered system can be transformed into a state unconstrained system with unknown approximate errors. In addition, a novel event-triggered mechanism is proposed via an adaptive dynamic programming algorithm, which can obtain the optimal control law without constructing the so-called event-triggered HJB equation. Moreover, in order to conquer the difficulty caused by the persistence of excitation conditions, the experience replay technique is utilized to design the critic update law. Meanwhile, it is demonstrated that all signals are uniformly ultimately bounded. Finally, two simulation examples are given to demonstrate the effectiveness of the control strategy.

关键词： Nonlinear systems Event-triggered control adaptive dynamic programming Full state constraints Optimal control

来源：评论

学校读者我要写书评

暂无评论

Optimal Impulsive Control for Discrete Stochastic Systems Through ADP 41

Optimal Impulsive Control for Discrete Stochastic Systems Th...

引用

第41届中国控制会议

作者： Mingming Liang Derong Liu School of Automation Guangdong University of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper constructs a novel general impulsive transition matrix in order to reveal the impulsive dynamics of the stochastic systems across the impulsive "events".On the foundation of this matrix,the policy iteration based impulsive adaptive dynamic programming(IADP) algorithm and its more efficient version,are developed to obtain the optimal impulsive controller design scheme for stochastic *** and optimality analysis are provided to show that both the IADP and the efficient IADP(EIADP) algorithms can find the global optimal performance index *** proposed EIADP algorithm updates the iterative policies partially at each iteration step according to the actual hardware constraints,enabling the ADP-based algorithms to run on computing devices with limited memory ***,a simulation experiment justifies the theoretical conjectures.

关键词： adaptive dynamic programming policy iteration stochastic systems transition matrix optimal control

来源：评论

学校读者我要写书评

暂无评论

adaptive Optimal Control of UAV Formation Based on Policy Iteration 34

Adaptive Optimal Control of UAV Formation Based on Policy It...

引用

34th Chinese Control and Decision Conference (CCDC)

作者： Xu, Guangyan Zhang, Shugang Lin, Hao Shenyang Aerosp Univ Sch Automat Shenyang 110136 Peoples R China

ISBN: (纸本)9781665478960

In this paper, aiming at the problem of UAV formation control, a method based on policy iteration is proposed to study the optimal control policy of UAV formation. When the system model is unknown, this algorithm transforms the problem into online solving the Algebraic Riccati Equation. Through online iteration, the value function and the control policy can be updated at the same time. Finally, the optimal control policy is obtained and the nonlinear system is converged. Experimental results show that compared with the traditional control policy, the controller improves the stability of the UAV formation. The convergence speed and robustness of the system are also significantly enhanced, and the control performance is more optimized. At last, the simulation results verify the effectiveness of the proposed method.

关键词： Policy iteration adaptive dynamic programming Optimal control UAV formation

来源：评论

学校读者我要写书评

暂无评论

A Model-Free Resilient Tracking Control Scheme for Non-Affine Nonlinear Continuous Systems with Uncertainties 41

A Model-Free Resilient Tracking Control Scheme for Non-Affin...

引用

第41届中国控制会议

作者： Kun Zhang Wenchao Xue Ran Zhang Cui Wei School of Astronautics Beihang University Key Laboratory of Systems and Control Institute of Systems ScienceAcademy of Mathematics and Systems ScienceChinese Academy of Sciences Institute of Intelligent Manufacturing Nanjing Tech University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,a model-free integral reinforcement learning(IRL) resilient tracking control scheme has been proposed for a class of non-affine nonlinear systems with *** using the precompensation technique,the actual working control has been transformed into the state of compensator,and an augmented tracking system converts the optimal tracking control problem into an optimal regulation *** applying the reinforcement learning(RL) technique,the designed method can avoid the dynamic information directly during the iteration learning process,and obtain the model-free resilient tracking ***,the developed algorithm overcomes the limitations and strict assumptions of conventional optimal tracking control in dealing with a non-affine nonlinear ***,with the use of polynomial approximation structure and the least square method,practicability in the implementing process has been guaranteed ***,two examples in the simulation are given to demonstrate the validity and feasibility of the proposed model-free IRL resilient tracking control.

关键词： adaptive dynamic programming Resilient control Nonlinear system Tracking control Integral reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Optimal Tracking Control for the Wastewater Treatment Plant via Generalized GDHP 34

Data-Driven Optimal Tracking Control for the Wastewater Trea...

引用

34th Chinese Control and Decision Conference (CCDC)

作者： Li, Xin Wang, Ding Zhao, Mingming Hu, Lingzhi Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Key Lab Computat Intelligence & Intellige Beijing 100124 Peoples R China Beijing Lab Smart Environm Protect Beijing 100124 Peoples R China Beijing Inst Artificial Intelligence Beijing 100124 Peoples R China

ISBN: (纸本)9781665478960

In order to implement the tracking control design of dissolved oxygen and nitrate nitrogen concentrations in a nonaffine wastewater treatment system, a globalized dual heuristic dynamic programming (GDHP) algorithm is established. First, the algorithm is initialized with a positive definite function to ensure that the sequence of cost functions is monotonically nonincreasing. Then, the updating rules of the cost function, the costate function, and the tracking control law are provided in the framework of generalized value iteration. Moreover, the monotonicity and the admissibility analysis of the generalized iteration algorithm are given. The model network, the critic network, and the action network are introduced to facilitate the implementation of the algorithm. Finally, the evolving policies in the iterative process are adopted to adjust the concentrations of dissolved oxygen and nitrate nitrogen in the experimental simulation, which verifies that the proposed generalized GDHP-based optimal tracking control method is applicable online.

关键词： adaptive dynamic programming Generalized value iteration Neural networks Optimal tracking control Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Integral sliding mode-based event-triggered optimal fault tolerant tracking control of continuous-time nonlinear systems ☆

引用

EUROPEAN JOURNAL OF CONTROL 2024年 79卷

作者： Zhang, Yongwei Zhang, Shunchao South China Agr Univ Coll Math & Informat Guangzhou 510642 Peoples R China Guangdong Univ Finance Sch Internet Finance & Informat Engn Guangzhou 510521 Peoples R China

In this paper, the integral sliding mode -based event -triggered optimal fault tolerant tracking control of continuous -time nonlinear systems is investigated via adaptive dynamic programming. The developed control scheme consists of two parts, i.e., integral sliding mode control and event -triggered optimal tracking control. For the first part, an integral sliding mode controller is designed to eliminate the affect of actuator fault and the dynamics of nominal nonlinear systems is obtained. For the second part, a novel quadratic cost function with respect to the tracking error and its dynamics is developed such that the feedforward control law or the discount factor is not required, which reduces the complexity of the control method and guarantees the tracking performance. Moreover, a critic -only structure is established to obtain the solution of tracking Hamilton-Jacobi-Bellman equation. It should be noted that the optimal tracking control law is updated only at triggering moments in order to preserve computing and communication resources. Finally, the effectiveness of the present approach is demonstrated through simulation examples of a robotic arm system and a Van der Pol circuit system.

关键词： adaptive dynamic programming Integral sliding-mode control Fault tolerant control Tracking control

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Optimal Safety Control for Nonlinear Safety-Critical Systems with Disturbance 34

Event-Triggered Optimal Safety Control for Nonlinear Safety-...

引用

34th Chinese Control and Decision Conference (CCDC)

作者： Zhu, Heyang Wang, Jinguang Zhang, Jishi Zhang, Dehua Xiao, Qiyang Qin, Chunbin Henan Univ Sch Artificial Intelligence Zhengzhou 450000 Peoples R China Henan Univ Sch Software Kaifeng 475000 Peoples R China

ISBN: (纸本)9781665478960

In this paper, the event-triggered optimal safety control method is proposed to solve the zero-sum game problem of nonlinear safety-critical systems with disturbance. First, we transform the safety-critical system with safety constraints into an equivalent system without safety constraints by using the barrier function. Then, for relieving the computation pressure and saving communication cost, the event-triggered mechanism is introduced, and a safe event-triggered condition is presented, meanwhile, the Zeno behavior is excluded. In addition, only a critic neural network (NN) is used to implement the proposed method. During the learning process, the past data and current data are used to relax the persistence of excitation (PE) condition. According to the Lyapunov theory, it can be proved that the states and the weight estimation error of critic NN are uniformly ultimately bounded (UUB). Finally, a simulation example shows the effectiveness of the proposed method.

关键词： adaptive dynamic programming Barrier function Event-triggered control Neural network Safety

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：