Induction motors are widely used in several industrial sectors. However, the selection of induction motors is often inaccurate because, in most cases, the load behavior in the shaft is completely unknown. The proposal of this paper is to use artificial neural networks as a tool for dimensioning induction motors rather than conventional methods, which use classical identification techniques and mechanical load modeling. The potential of this approach is the simple hardware implementation since the methodology does not require torque sensor nor powerful computational processors. Simulation results are also presented to validate the proposed approach.
Induction motors; load modeling; neural networks; parameter estimation; system identification