Model Predictive Current Control Using Single Layer Neural Network for PMSM Drives

Hasan Ali Gamal Al-Kaf; Samer Saleh Hakami; Laith M. Halabi; Kyo Beum Lee

doi:10.1109/ECCE50734.2022.9947720

Model Predictive Current Control Using Single Layer Neural Network for PMSM Drives

Hasan Ali Gamal Al-Kaf, Samer Saleh Hakami, Laith M. Halabi, Kyo Beum Lee

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Model predictive control (MPC) is regarded as a significant modern control for the current control of permanent magnet synchronous motor (PMSM). However, the computation burden of MPC imposes its advantage to be implemented in sophisticated converter topologies and multistep prediction horizons. Multilayer neural network with MPC (MLNN-MPC) is increasingly used in different converters to overcome the drawback of high computational time. However, it has a higher computational time compared to a single-layer neural network (SLNN). In addition, many parameters need to be optimized such as initial weights, number of iterations, and neurons. In this paper, a SLNN with MPC is proposed to predict the current of PMSM. The proposed SLNN-MPC is trained using the Levenberg Marquardt algorithm. Meanwhile, it shows better performance than MLNN-MPC with lower computational time by optimizing only one parameter. Furthermore, the simulation results are shown to verify the effectiveness of the proposed method.

Original language	English
Title of host publication	2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728193878
DOIs	https://doi.org/10.1109/ECCE50734.2022.9947720
State	Published - 2022
Externally published	Yes
Event	2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022 - Detroit, United States Duration: 9 Oct 2022 → 13 Oct 2022

Publication series

Name	2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022

Conference

Conference	2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022
Country/Territory	United States
City	Detroit
Period	9/10/22 → 13/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

PMSM
model predictive current control
single layer neural network
two-level inverter

ASJC Scopus subject areas

Electrical and Electronic Engineering
Mechanical Engineering
Safety, Risk, Reliability and Quality
Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
Control and Optimization

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ECCE50734.2022.9947720

Cite this

Al-Kaf, H. A. G., Hakami, S. S., Halabi, L. M., & Lee, K. B. (2022). Model Predictive Current Control Using Single Layer Neural Network for PMSM Drives. In 2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022 (2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ECCE50734.2022.9947720

@inproceedings{ce2e20e13f374ede9ccf174e3b0980f6,

title = "Model Predictive Current Control Using Single Layer Neural Network for PMSM Drives",

abstract = "Model predictive control (MPC) is regarded as a significant modern control for the current control of permanent magnet synchronous motor (PMSM). However, the computation burden of MPC imposes its advantage to be implemented in sophisticated converter topologies and multistep prediction horizons. Multilayer neural network with MPC (MLNN-MPC) is increasingly used in different converters to overcome the drawback of high computational time. However, it has a higher computational time compared to a single-layer neural network (SLNN). In addition, many parameters need to be optimized such as initial weights, number of iterations, and neurons. In this paper, a SLNN with MPC is proposed to predict the current of PMSM. The proposed SLNN-MPC is trained using the Levenberg Marquardt algorithm. Meanwhile, it shows better performance than MLNN-MPC with lower computational time by optimizing only one parameter. Furthermore, the simulation results are shown to verify the effectiveness of the proposed method.",

keywords = "PMSM, model predictive current control, single layer neural network, two-level inverter",

author = "Al-Kaf, \{Hasan Ali Gamal\} and Hakami, \{Samer Saleh\} and Halabi, \{Laith M.\} and Lee, \{Kyo Beum\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022 ; Conference date: 09-10-2022 Through 13-10-2022",

year = "2022",

doi = "10.1109/ECCE50734.2022.9947720",

language = "English",

series = "2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022",

address = "United States",

}

Al-Kaf, HAG , Hakami, SS, Halabi, LM & Lee, KB 2022, Model Predictive Current Control Using Single Layer Neural Network for PMSM Drives. in 2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022. 2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022, Institute of Electrical and Electronics Engineers Inc., 2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022, Detroit, United States, 9/10/22. https://doi.org/10.1109/ECCE50734.2022.9947720

Model Predictive Current Control Using Single Layer Neural Network for PMSM Drives. / Al-Kaf, Hasan Ali Gamal ; Hakami, Samer Saleh; Halabi, Laith M. et al.
2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Model Predictive Current Control Using Single Layer Neural Network for PMSM Drives

AU - Al-Kaf, Hasan Ali Gamal

AU - Hakami, Samer Saleh

AU - Halabi, Laith M.

AU - Lee, Kyo Beum

PY - 2022

Y1 - 2022

N2 - Model predictive control (MPC) is regarded as a significant modern control for the current control of permanent magnet synchronous motor (PMSM). However, the computation burden of MPC imposes its advantage to be implemented in sophisticated converter topologies and multistep prediction horizons. Multilayer neural network with MPC (MLNN-MPC) is increasingly used in different converters to overcome the drawback of high computational time. However, it has a higher computational time compared to a single-layer neural network (SLNN). In addition, many parameters need to be optimized such as initial weights, number of iterations, and neurons. In this paper, a SLNN with MPC is proposed to predict the current of PMSM. The proposed SLNN-MPC is trained using the Levenberg Marquardt algorithm. Meanwhile, it shows better performance than MLNN-MPC with lower computational time by optimizing only one parameter. Furthermore, the simulation results are shown to verify the effectiveness of the proposed method.

AB - Model predictive control (MPC) is regarded as a significant modern control for the current control of permanent magnet synchronous motor (PMSM). However, the computation burden of MPC imposes its advantage to be implemented in sophisticated converter topologies and multistep prediction horizons. Multilayer neural network with MPC (MLNN-MPC) is increasingly used in different converters to overcome the drawback of high computational time. However, it has a higher computational time compared to a single-layer neural network (SLNN). In addition, many parameters need to be optimized such as initial weights, number of iterations, and neurons. In this paper, a SLNN with MPC is proposed to predict the current of PMSM. The proposed SLNN-MPC is trained using the Levenberg Marquardt algorithm. Meanwhile, it shows better performance than MLNN-MPC with lower computational time by optimizing only one parameter. Furthermore, the simulation results are shown to verify the effectiveness of the proposed method.

KW - PMSM

KW - model predictive current control

KW - single layer neural network

KW - two-level inverter

UR - https://www.scopus.com/pages/publications/85144022690

U2 - 10.1109/ECCE50734.2022.9947720

DO - 10.1109/ECCE50734.2022.9947720

M3 - Conference contribution

AN - SCOPUS:85144022690

T3 - 2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022

BT - 2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 IEEE Energy Conversion Congress and Exposition, ECCE 2022

Y2 - 9 October 2022 through 13 October 2022

ER -

Model Predictive Current Control Using Single Layer Neural Network for PMSM Drives

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Cite this