A Novel Method to Estimate the Rotor Resistance of the Induction Motor Using Support Vector Machines

Modern indirect vector control based drives of the squirrel cage induction motor (SCIM) have a main weakness in the true value of the rotor time constant is always unknown, which is used by the control block to know the exact position of the rotor flux and locate the synchronous d-q axes correctly. The main parameter affecting the rotor time constant variation is the rotor resistance whose value may change because of temperature rise, flux saturation, and skin effect. A novel rotor resistance estimator of the SCIM was designed using support vector machines (SVM) as a non-linear regressor. The all drive including a SCIM model with time-varying rotor resistance was simulated. Flux errors according to the current and voltages models were obtained. SVM was trained with those flux error records and variable rotor resistance. The drive with the rotor resistance estimator in closed loop showed a well performance when was undergone to other operation conditions different to that from the training signals were obtained and nevertheless to achieve an excellent estimation of the rotor resistance, even during start up of the machine