An improvement of speed control performances of a two-mass system using a universal approximator

A new control scheme using a universal approximator based on a radial basis function network (RBFN) is proposed and investigated for improving the control characteristics of the high-performance motion control system. This control method presents better performance in the corresponding speed vibration response, compared with the inverse model-based disturbance observer. The proposed RBFN-universal approximator keeps the self-learning capability, whereas the inverse model-based disturbance observer with the low-pass filter should adjust the time constant of the filter according to the resonance frequency determined by varying the system parameters. The simulation results show the validity of the proposed control scheme.