Dong-Juan Li

Reinforcement Learning Design-Based Adaptive Tracking Control With Less Learning Parameters for Nonlinear Discrete-Time MIMO Systems

Based on the neural network (NN) approximator, an online reinforcement learning algorithm is proposed for a class of affine multiple input and multiple output (MIMO) nonlinear discrete-time systems with unknown functions and disturbances. In the design procedure, two networks are provided where one is an action network to generate an optimal control signal and the other is a critic network to approximate the cost function. An optimal control signal and adaptation laws can be generated based on two NNs. In the previous approaches, the weights of critic and action networks are updated based on the gradient descent rule and the estimations of optimal weight vectors are directly adjusted in the design. Consequently, compared with the existing results, the main contributions of this paper are: (1) only two parameters are needed to be adjusted, and thus the number of the adaptation laws is smaller than the previous results and (2) the updating parameters do not depend on the number of the subsystems for MIMO systems and the tuning rules are replaced by adjusting the norms on optimal weight vectors in both action and critic networks. It is proven that the tracking errors, the adaptation laws, and the control inputs are uniformly bounded using Lyapunov analysis method. The simulation examples are employed to illustrate the effectiveness of the proposed algorithm.

Fuzzy Adaptive Control With State Observer for a Class of Nonlinear Discrete-Time Systems With Input Constraint

In this paper, an adaptive fuzzy controller is constructed for a class of nonlinear discrete-time systems with unknown functions and bounded disturbances. The main characteristics of the systems are that they take into account the effect of discrete-time dead zone and the system states are not required to be measurable. The stability problem of this class of systems is for the first time to be addressed in this paper. Due to the unavailability of the states and the presence of the discrete-time dead zone, the controller design becomes more difficult. To stabilize the uncertain nonlinear discrete-time systems, the fuzzy logic systems are used to approximate the unknown functions, a fuzzy state observer is designed to estimate the immeasurable states, and the effect caused by discrete-time dead zone can be solved via establishing an adaptation auxiliary signal. Based on the Lyapunov approach, it is proved that all the signals of the closed-loop system are the semiglobal uniformly ultimately bounded, and the tracking error is made within a small neighborhood around zero. The feasibility of the developed control scheme is verified via two simulation examples.

Neural Controller Design-Based Adaptive Control for Nonlinear MIMO Systems With Unknown Hysteresis Inputs

This paper studies an adaptive neural control for nonlinear multiple-input multiple-output systems in interconnected form. The studied systems are composed of

Adaptive Controller Design-Based ABLF for a Class of Nonlinear Time-Varying State Constraint Systems

{N}

Adaptive output feedback control for a class of nonlinear systems with full-state constraints

subsystems in pure feedback structure and the interconnection terms are contained in every equation of each subsystem. Moreover, the studied systems consider the effects of Prandtl-Ishlinskii (PI) hysteresis model. It is for the first time to study the control problem for such a class of systems. In addition, the proposed scheme removes an important assumption imposed on the previous works that the bounds of the parameters in PI hysteresis are known. The radial basis functions neural networks are employed to approximate unknown functions. The adaptation laws and the controllers are designed by employing the backstepping technique. The closed-loop system can be proven to be stable by using Lyapunov theorem. A simulation example is studied to validate the effectiveness of the scheme.

Adaptive Neural Tracking Control for Nonlinear Time-Delay Systems With Full State Constraints

In this paper, we address an adaptive control problem for a class of nonlinear strict-feedback systems with uncertain parameter. The full states of the systems are constrained in the bounded sets and the boundaries of sets are compelled in the asymmetric time-varying regions, i.e., the full state time-varying constraints are considered here. This is for the first time to control such a class of systems. To prevent that the constraints are overstepped, the time-varying asymmetric barrier Lyapunov functions (TABLFs) are employed in each step of the backsstepping design and we also establish a novel control TABLF scheme to ensure the asymptotic output tracking performance. The performances of the adaptive TABLF-based control are verified by a simulation example.

Adaptive NN Control Using Integral Barrier Lyapunov Functionals for Uncertain Nonlinear Block-Triangular Constraint Systems

This paper studies an adaptive output-feedback control for a class of nonlinear single-input and single-output (SISO) systems with the full-state constraints. A state observer is designed to estimate those unmeasured states. At present, all the results in the output-feedback area ignore the effects of the full-state constraints. The presence of these constraints results in a complicated procedure and the major difficulties in the design. The barrier Lyapunov function (BLF) and a novel design procedure are given to overcome these difficulties. The adaptation law and the controllers are obtained based on the backstepping design procedure. In addition, only one adjustable parameter needs to be updated, and thus, the online computation burden is alleviated. The stability of the closed-loop system is proven by using the Lyapunov theorem. A simulation example is given to verify the effectiveness of the approach.

Adaptive control for a class of chemical reactor systems in discrete-time form

In this paper, an adaptive neural tracking control strategy is presented to stabilize a class of uncertain nonlinear strict-feedback systems with the full state constraints and time-delays. Because the full state constraints and time-delays appear simultaneously in the systems, they lead to the difficulties in the controller design. The opportune barrier Lyapunov functions (BLFs) are designed to ensure that the states constraints are not violated. The novel backstepping procedures with BLFs are utilized to eliminate the effect of the nonlinear system which caused by the time-delays. Finally, it is proved that all the signals in the closed-loop system are semiglobal uniformly ultimately bounded and the tracking errors converge to a small interval based on proposed Lyapunov and backstepping design method. The effectiveness of the proposed scheme is demonstrated by a simulation in this paper.

Robust adaptive NN control for a class of uncertain discrete-time nonlinear MIMO systems

A neural network (NN) adaptive control design problem is addressed for a class of uncertain multi-input-multi-output (MIMO) nonlinear systems in block-triangular form. The considered systems contain uncertainty dynamics and their states are enforced to subject to bounded constraints as well as the couplings among various inputs and outputs are inserted in each subsystem. To stabilize this class of systems, a novel adaptive control strategy is constructively framed by using the backstepping design technique and NNs. The novel integral barrier Lyapunov functionals (BLFs) are employed to overcome the violation of the full state constraints. The proposed strategy can not only guarantee the boundedness of the closed-loop system and the outputs are driven to follow the reference signals, but also can ensure all the states to remain in the predefined compact sets. Moreover, the transformed constraints on the errors are used in the previous BLF, and accordingly it is required to determine clearly the bounds of the virtual controllers. Thus, it can relax the conservative limitations in the traditional BLF-based controls for the full state constraints. This conservatism can be solved in this paper and it is for the first time to control this class of MIMO systems with the full state constraints. The performance of the proposed control strategy can be verified through a simulation example.

Adaptive neural network control for unified chaotic systems with dead-zone input

In this paper, an adaptive predictive control algorithm is applied to control a class of SISO continuous stirred tank reactor (CSTR) system in discrete time. The main contribution of the paper is that the considered systems belong to pure-feedback form where the unknown dead-zone is considered in the in-fan, and dead-zone is nonsymmetric, and it is first to control this class of systems. Radial basis function neural networks are used to approximate the unknown functions, and the mean value theorem is exploited in the design. Based on the Lyapunov analysis method, it is proven that all the signals of the resulting closed-loop system are guaranteed to be semi-global uniformly ultimately bounded, and the tracking error can be reduced to a small compact set. A simulation example for CSTR systems is studied to verify the effectiveness of the proposed approach.