A reinforced learning control using iterative error compensation for uncertain dynamical systems

This paper investigates a learning control using iterative error compensation for uncertain systems to enhance the precision of high speed, computer controlled machining process. It is especially useful in mass-produced parts produced by high speed machines tool system. This method uses iterative learning technique which adopts machine commands and cutting error experienced in previous maneuvers as references for compensative actions in current maneuver. Non-repetitive disturbances and nonlinear dynamics of the cutting processes and servo systems of the machine which greatly affect the convergence of the learning control systems were studied in this research. State feedback and output feedback methods were used for our controller design. Stability and performance of learning control systems designed via our method were verified by simulations on a single degree of freedom servo positioning system.