Robustness improvement for permanent synchronous motor drive using neural network

• Main Author: Tan, Eugene Yan Hao
• Other Authors: Christopher H. T. Lee
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Electrical and electronic engineering::Control and instrumentation::Control engineering
• Online Access: https://hdl.handle.net/10356/167326
• Institution: Nanyang Technological University

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.