|
In this thesis a high-performance speed control approach us- ing artificial neural networks (ANN's) for the field- oriented induction motor is proposed. The speed of an induction motor can be controlled to follow an arbitrarily selected speed tra- jectory Especially, an accurate track of the speed can still be obtained when uncertainties of the motor and its load exist. The uncertainties include the unknown load on the motor and the vari- ation of the motor rotor resistance due to the temperature rise. To evaluate the performance of the proposed control system, the system has been simulated by using detailed models of the induc- tion motor vector control, the current hysteresis controlled VSI (Voltage Source Inverter) and the ANN's. The scenarios simulated on a typical induction motor are composed of unknown nonlinear load, different trajectories of speed and patterns of rotor tance variation. Simulated results of the proposed system are pared with those of the traditional PI (Proportional Plus Integr- al) controller. Preliminary results show that our proposed con- trol system can achieve superior performances on the speed tra- jectory tracking and the adaptability to the parameter variation of rotor resistance.
|