Self-learning control systems using identification-based adaptive iterative learning controller

One of the promising algorithms for self-learning control systems is iterative learning control (ILC), which is an algorithm capable of tracking a desired trajectory within a specific period of time. Conventional ILC algorithms have the problem of relatively slow convergence rate and because of their fixed control laws they are unable to adapt to changes in performance requirements and system changes. This paper suggests a novel approach by combining system identification techniques with the proposed ILC approach to overcome such problems. Several practical simulation examples are presented to illustrate the design procedure and to confirm the effectiveness and robustness of the algorithm. The optimal gain matrices values are calculated using the steepest descent approach. Convergence condition for the approach is also derived. Declining cost and increasing power of computers and embedded systems makes the implementation of such schemes highly feasible.