Integral Backstepping Control for a PMSM Drive Using Adaptive RNN Uncertainty Observer

Due to uncertainties exist in the applications of the permanent magnet synchronous motor (PMSM) servo drive which seriously influence the control performance. The integral back stepping controller and adaptive recurrent neural network uncertainty observer (RNNUO) is proposed to control the rotor of the PMSM to track periodic references in this paper. Firstly, the field-oriented mechanism is applied to formulate the dynamic equation of the PMSM servo drive. To further increase the robustness of the PMSM drive, an adaptive RNN uncertainty observer is proposed to estimate the required lumped uncertainty. Finally, the effectiveness of the proposed control scheme is verified by experimental results.