Robustness improvement for permanent synchronous motor drive using neural network

The report suggests using an active disturbance rejection control (ADRC) system to decrease torque ripple in PMSM motor drives. The system combines an extended state observer (ESO) with a neural network-based torque compensator, which reduces torque harmonic distortion caused by cogging and back EMF...

Full description

Saved in:
Bibliographic Details
Main Author: Tan, Eugene Yan Hao
Other Authors: Christopher H. T. Lee
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/167326
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:The report suggests using an active disturbance rejection control (ADRC) system to decrease torque ripple in PMSM motor drives. The system combines an extended state observer (ESO) with a neural network-based torque compensator, which reduces torque harmonic distortion caused by cogging and back EMF. The ESO detects and rejects low-frequency disturbances, while the NN compensator has two layers that output backpropagation torque compensation to further reduce torque ripple. Simulations and experiments on the Simulink Model show that this approach is effective in suppressing torque ripple.