Linear quadratic state feedback and robust neural network estimator for field-oriented-controlled induction motors

A field-oriented control scheme for an induction motor with a linear quadra tic optimal regulator and a robust neural network estimator is proposed. Th e state feedback is designed by using the synchronous frame motor model. Th e number of the states is increased in order to take into account the prese nce of two integrators on the Bur and torque errors. The resulting model is suitably simplified and the corresponding approximations are discussed. Th e procedure proposed is shown to be suitable also for the design of the sta te feedback via pole placement technique, A comparison with standard propor tional integral regulators is provided. The rotor flux is estimated by usin g a robust neural network observer. The network training set is suitably de signed in order to preserve the drive effectiveness also in the presence of large parameter uncertainties. The robust neural observer is compared with an extended Kalman filter and a standard neural network observer. Using a 250-kW induction motor as a case study, the simulation results show the eff ectiveness of the proposed solution, both during transient and steady-state operating conditions.