Neural Network Adaptive L2 Robust Control for Induction Motors

A neural network adaptive L₂ robust control method is proposed for induction motors. The proposed controllers are combined with a rotor flux observer. The disturbances caused by the uncertainties of stator and rotor resistances and load torque are compensated using radial basis function neural networks (RBFNNs). Based on backstepping, RBFNN, and HJI (Hamilton-Jaccobi-Issacs) inequality, the neural network adaptive L₂ robust controllers are designed and the control system is proved to have L₂-gain less than or equal to a specified positive constant gamma without solving the HJI inequality directly. The simulation results indicate that the proposed method is robust to the considered uncertainties of the induction motor parameters and has high dynamic performance.