Abstract
PI controllers have been widely used in industrial systems application, because they have a simple structure and offer a satisfactory performance for a wide range operation. However, for varieties of plant parameters and the nonlinear operating condition, fixed gain PI controllers cannot provide the desired control performance. In this paper, advanced PI controller was utilized to control the speed of the induction motor in Direct Torque Control (DTC) for electric propulsion application. The proposed method is developed from conventional PI controller combined with feed-forward neural networks (FFNN). The FFNN is used to tune the gain of PI controller. The effectiveness of the complete proposed control scheme is clarified with a variation of speed reference and load torque applied to the motor. Load torque of induction motor depends on the speed rotation and pitch of propeller. Simulation results show the FFNN tuning technique provides better speed control performance.
Original language | English |
---|---|
Pages (from-to) | 6135-6145 |
Number of pages | 11 |
Journal | International Journal of Innovative Computing, Information and Control |
Volume | 7 |
Issue number | 11 |
Publication status | Published - Nov 2011 |
Keywords
- Direct torque control
- Electric propulsion
- Neural network
- PI controller