The paper deals with the application of the extended Kalman filters in the control structure of a two-mass drive system. In the first step only linear extended Kalman filter was used for the estimation of mechanical state variables of the drive including load torque value. The estimation algorithm showed good robustness to mechanical parameters variations. For the system with some parameters changing in the wide range, simultaneous estimation of the state variables and chosen system parameters is required. For this reason the non-linear extended Kalman filter, which estimates simultaneously state variables and mechanical parameters of the two-mass drive system, was developed. Parameters of covariance matrices of used Kalman filters were set using the genetic algorithm. Both proposed estimators were investigated in simulation and experimental tests, in the open-loop operation and in the state-feedback control system of the two-mass system.
The paper presents a method for designing a neural speed controller with use of Reinforcement Learning method. The controlled object is an electric drive with a synchronous motor with permanent magnets, having a complex mechanical structure and changeable parameters. Several research cases of the control system with a neural controller are presented, focusing on the change of object parameters. Also, the influence of the system critic behaviour is researched, where the critic is a function of control error and energy cost. It ensures long term performance stability without the need of switching off the adaptation algorithm. Numerous simulation tests were carried out and confirmed on a real stand.