Torque ripple and harmonics in permanent magnet synchronous motor (PMSM) cause negative impacts on its speed control and overall efficiency. In this article, an Elman neural network (ENN)-controlled feedback linearization-based direct torque control strategy has been proposed to mitigate torque ripples and undesirable harmonics of PMSM. In this approach, the stator flux, stator flux position, and developed torque are used to generate a switching pulse to the impedance source inverter employing ENN controller. By changing the switching pattern of the impedance source inverter through modifying the pulse width modulation using the proposed control strategy. It is possible to control the armature current of the PMSM at various orders and corresponding time harmonics under different operating conditions. The outstanding aspect of the proposed control strategy is that it boosts the inverter operation and reduces the requirement of the DC-DC converter in boosting. For evaluating the performance of the developed control strategy, an extensive simulation study has been conducted in the MATLAB/Simulink environment, and experimental analysis is carried out using the Xilinx-FPGA kit.
|Journal||International Transactions on Electrical Energy Systems|
|Number of pages||23|
|Publication status||Published - Jan 2021|
Bibliographical noteFunding Information:
This research received funding from the Science and Engineering Research Board, Department of Science & Technology, Government of India (ECR/2017/000259).
© 2020 John Wiley & Sons Ltd
- artificial neural network
- direct torque control
- feedback linearization
- impedance source inverter
- permanent magnet synchronous motor