Event-triggered reinforcement learningH∞control design for constrained-input nonlinear systems subject to actuator failures

Event-based adaptive fixed-time optimal control for saturated fault-tolerant nonlinear multiagent systems via reinforcement learning algorithm

This article investigates the problem of adaptive fixed-time optimal consensus tracking control for nonlinear multiagent systems (MASs) affected by actuator faults and input saturation. To achieve optimal control, reinforcement learning (RL) algorithm which is implemented based on neural network (NN) is employed. Under the actor-critic structure, an innovative simple positive definite function is constructed to obtain the upper bound of the estimation error of the actor-critic NN updating law, which is crucial for analyzing fixed-time stabilization. Furthermore, auxiliary functions and estimation laws are designed to eliminate the coupling effects resulting from actuator faults and input saturation. Meanwhile, a novel event-triggered mechanism (ETM) that incorporates the consensus tracking errors into the threshold is proposed, thereby effectively conserving communication resources. Based on this, a fixed-time event-triggered control scheme grounded in RL is proposed through the integration of the backstepping technique and fixed-time theory. It is demonstrated that the consensus tracking errors converge to a specified range in a fixed time and all signals within the closed-loop systems are bounded. Finally, simulation results are provided to verify the effectiveness of the proposed control strategy.

ADP-based online compensation hierarchical sliding-mode control for partially unknown switched nonlinear systems with actuator failures

This article investigates an adaptive dynamic programming-based online compensation hierarchical sliding-mode control problem for a class of partially unknown switched nonlinear systems with actuator failures and uncertain perturbations under an identifier-critic neural networks architecture. Firstly, by introducing a cost function related to hierarchical sliding-mode surfaces for the nominal system, the original control problem is equivalently converted into an optimal control problem. To obtain this optimal control policy, the Hamilton-Jacobi-Bellman equation is solved through an adaptive dynamic programming method. Compared with conventional adaptive dynamic programming methods, the identifier-critic network architecture not only overcomes the limitation on the unknown internal dynamic but also eliminates the approximation error arising from the actor network. The weights in the critic network are tuned via the gradient descent approach and the experience replay technology, such that the persistence of excitation condition can be relaxed. Then, a compensation term containing hierarchical sliding-mode surfaces is used to offset uncertain actuator failures without the fault detection and isolation unit. Based on the Lyapunov stability theory, all states of the closed-loop nonlinear system are stable in the sense of uniformly ultimately boundedness. Finally, numerical and practical examples are given to demonstrate the effectiveness of our presented online compensation control strategy.

Event-triggered fault-tolerant control for input-constrained nonlinear systems with mismatched disturbances via adaptive dynamic programming

In this paper, the issue of event-triggered optimal fault-tolerant control is investigated for input-constrained nonlinear systems with mismatched disturbances. To eliminate the effect of abrupt faults and ensure the optimal performance of general nonlinear dynamics, an adaptive dynamic programming (ADP) algorithm is employed to develop a sliding mode fault-tolerant control strategy. When the system trajectories converge to the sliding-mode surface, the equivalent sliding mode dynamics is transformed into a reformulated auxiliary system with a modified cost function. Then, a single critic neural network (NN) is adopted to solve the modified Hamilton-Jacobi-Bellman (HJB) equation. In order to overcome the difficulty that arises from the persistence of excitation (PE) condition, the experience replay technique is utilized to update the critic weights. In this study, a novel control method is proposed, which can effectively eliminate the effects of abrupt faults while achieving optimal control with the minimum cost under a single network architecture. Furthermore, the closed-loop nonlinear system is proved to be uniformly ultimate boundedness based on Lyapunov stability theory. Finally, three examples are presented to verify the validity of the control strategy.

Distributed optimized dynamic event-triggered control for unknown heterogeneous nonlinear MASs with input-constrained

The distributed optimized dynamic event-triggered controller is investigated for completely unknown heterogeneous nonlinear multi-agent systems (MASs) on a directed graph subject to input-constrained. First, the distributed observer is designed to estimate the information of the leader for each follower, and a network of the augmented system is constructed by employing the dynamics of the followers and the observers. An identifier with a compensator is designed to approximate the unknown augmented system (agent) with an arbitrarily small identifier error. Then, consider that the input-constrained optimal controller, along with Hamilton-Jacobi-Bellman (HJB) equation, is under pressure to execute in certain systems associated with bottlenecks such as communication and computing burdens. A critic-actor-based optimized dynamic event-triggered controller, which tunes the parameters of critic-actor neural networks (NNs) by the dynamic triggering mechanism, is leveraged to determine the rule of aperiodic sampling and maintain the desired synchronization service. In addition, the existence of a positive minimum inter-event time (MIET) between consecutive events is also proved. Finally, the applications in non-identical nonlinear MAS and 2-DOF robots illustrate the availability of the proposed theoretical results.