Title :
Neural Approach for Automatic Identification of Induction Motor Load Torque in Real-Time Industrial Applications
Author :
Goedtel, A. ; da Silva, I.N. ; Serni, P. J A
Author_Institution :
Electr. Eng. Dept., Sao Paulo Univ.
Abstract :
Induction motors are widely used in several industrial sectors. However, the dimensioning 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. Since the proposed approach uses current, voltage and speed values as the only input parameters, one of its potentialities is related to the facility of hardware implementation for industrial environments and field applications. Simulation results are also presented to validate the proposed approach.
Keywords :
electric machine analysis computing; induction motors; neural nets; parameter estimation; torque; artificial neural network; induction motor; load torque automatic identification; real-time industrial sector; Artificial neural networks; Induction motors; Industrial control; Load modeling; Mathematical analysis; Proposals; Reactive power; Shafts; Torque control; Voltage; Induction motors; load modeling; neural networks; parameter estimation; system identification;
Conference_Titel :
Power Electronics, Drives and Energy Systems, 2006. PEDES '06. International Conference on
Conference_Location :
New Delhi
Print_ISBN :
0-7803-9772-X
Electronic_ISBN :
0-7803-9772-X
DOI :
10.1109/PEDES.2006.344292