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
id sg-ntu-dr.10356-167326
record_format dspace
spelling sg-ntu-dr.10356-1673262023-07-07T15:46:33Z Robustness improvement for permanent synchronous motor drive using neural network Tan, Eugene Yan Hao Christopher H. T. Lee School of Electrical and Electronic Engineering chtlee@ntu.edu.sg Engineering::Electrical and electronic engineering::Control and instrumentation::Control engineering 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. Bachelor of Engineering (Electrical and Electronic Engineering) 2023-05-25T07:16:16Z 2023-05-25T07:16:16Z 2023 Final Year Project (FYP) Tan, E. Y. H. (2023). Robustness improvement for permanent synchronous motor drive using neural network. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/167326 https://hdl.handle.net/10356/167326 en A1057-221 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering::Control and instrumentation::Control engineering
spellingShingle Engineering::Electrical and electronic engineering::Control and instrumentation::Control engineering
Tan, Eugene Yan Hao
Robustness improvement for permanent synchronous motor drive using neural network
description 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.
author2 Christopher H. T. Lee
author_facet Christopher H. T. Lee
Tan, Eugene Yan Hao
format Final Year Project
author Tan, Eugene Yan Hao
author_sort Tan, Eugene Yan Hao
title Robustness improvement for permanent synchronous motor drive using neural network
title_short Robustness improvement for permanent synchronous motor drive using neural network
title_full Robustness improvement for permanent synchronous motor drive using neural network
title_fullStr Robustness improvement for permanent synchronous motor drive using neural network
title_full_unstemmed Robustness improvement for permanent synchronous motor drive using neural network
title_sort robustness improvement for permanent synchronous motor drive using neural network
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/167326
_version_ 1772827364439359488