Search

This paper proposes a non-model based approach to iterative learning control (ILC) via extremum seeking. Single-input–single-output discrete-time nonlinear systems are considered, where the objective is to recursively construct an input such that the corresponding system output tracks a prescribed reference trajectory as closely as possible on finite horizon. The problem is formulated in terms of extremum seeking control, which is amenable to a range of local and global optimisation methods. Contrary to the existing ILC literature, the formulation allows the initial condition of each iteration to be incorporated as an optimisation variable to improve tracking. Sufficient conditions for convergence to the reference trajectory are provided. The main feature of this approach is that it does not rely on knowledge about the system’s model to perform iterative learning control, in contrast to most results in the literature. [ABSTRACT FROM AUTHOR]

Abstract: The iterative learning control (ILC) is constructed for the discrete-time large scale systems. Each subsystem is affine nonlinear and its observation equation is with noise. Subsystems are nonlinearly connected via the large state vector of the whole system. The possibility of data missing, and communication delay is taken into account. It is proved that ILC given in the paper with probability one converges to the optimal one minimizing the tracking error. The simulation results are consistent with theoretical analysis. [Copyright &y& Elsevier]

In this paper, to eliminate the tracking error by using adaptive dynamic programming (ADP) algorithms, a novel formulation of the value function is presented for the optimal tracking problem (TP) of nonlinear discrete-time systems. Unlike existing ADP methods, this formulation introduces the control input into the tracking error, and ignores the quadratic form of the control input directly, which makes the boundedness and convergence of the value function independent of the discount factor. Based on the proposed value function, the optimal control policy can be deduced without considering the reference control input. Value iteration (VI) and policy iteration (PI) methods are applied to prove the optimality of the obtained control policy, and derived the monotonicity property and convergence of the iterative value function. Simulation examples realized with neural networks and the actor–critic structure are provided to verify the effectiveness of the proposed ADP algorithm. [ABSTRACT FROM AUTHOR]