Neural network flux optimization using a model of losses in induction motor drives Original Research Article

This paper focuses on loss minimization in induction motor (IM) drives. In many applications Induction Motor drives work below the nominal torque most of the time. In these circumstances the IM efficiency can be improved lowering the flux. For a given torque, this decreases iron looses and increases copper losses. With appropriate algorithms an optimum point for the flux can be achieved in order to minimize IM total power losses. Using an IM model, a neural network (NN) based approach is used to improve efficiency in a vector control of the induction motor drive. A complex loss model of the motor, including magnetic and thermal deviations of its parameters, is used to estimate losses. Based on this model, the neural network is trained to estimate the optimum rotor flux. Inputs to the NN are torque, speed and rotor resistance of the IM and the output is the rotor flux. Analysis, modeling and simulation results are presented to demonstrate the validity of the proposed method.