Neural network-based model reference adaptive system for torque ripple reduction in sensorless poly phase induction motor drive

S. Usha, C. Subramani*, Sanjeevikumar Padmanaban

*Kontaktforfatter

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

This paper proposes the modified, extended Kalman filter, neural network-based model reference adaptive system and the modified observer technique to estimate the speed of a five-phase induction motor for sensorless drive. The proposed method is generated to achieve reduced speed deviation and reduced torque ripple efficiently. In inclusion, the result of speed performance and torque ripple under parameter variations were analysed and compared with the conventional direct synthesis method. The speed estimation of a five-phase motor in the four methods is analysed using MATLAB Simulink platform, and the optimum method is recognized using time domain analysis. It is observed that speed error is minimized by 60% and torque ripple is reduced by 75% in the proposed method. The hardware setup is carried out for the optimized method identified.
OriginalsprogEngelsk
Artikelnummer920
TidsskriftEnergies
Vol/bind12
Udgave nummer5
Antal sider25
ISSN1996-1073
DOI
StatusUdgivet - jan. 2019

Fingerprint

Induction Motor
Adaptive systems
Ripple
Reference Model
Adaptive Systems
Induction motors
Torque
Neural Networks
Neural networks
Time domain analysis
Time Domain Analysis
Extended Kalman filters
MATLAB
Matlab/Simulink
Kalman Filter
Observer
Hardware
Deviation
Inclusion
Synthesis

Citer dette

@article{ff6e51910e634c38b44557fc79368f9c,
title = "Neural network-based model reference adaptive system for torque ripple reduction in sensorless poly phase induction motor drive",
abstract = "This paper proposes the modified, extended Kalman filter, neural network-based model reference adaptive system and the modified observer technique to estimate the speed of a five-phase induction motor for sensorless drive. The proposed method is generated to achieve reduced speed deviation and reduced torque ripple efficiently. In inclusion, the result of speed performance and torque ripple under parameter variations were analysed and compared with the conventional direct synthesis method. The speed estimation of a five-phase motor in the four methods is analysed using MATLAB Simulink platform, and the optimum method is recognized using time domain analysis. It is observed that speed error is minimized by 60{\%} and torque ripple is reduced by 75{\%} in the proposed method. The hardware setup is carried out for the optimized method identified.",
keywords = "Induction motor, Kalman filter, Luenberger observer, Model reference adaptive system, Speed estimation",
author = "S. Usha and C. Subramani and Sanjeevikumar Padmanaban",
year = "2019",
month = "1",
doi = "10.3390/en12050920",
language = "English",
volume = "12",
journal = "Energies",
issn = "1996-1073",
publisher = "M D P I AG",
number = "5",

}

Neural network-based model reference adaptive system for torque ripple reduction in sensorless poly phase induction motor drive. / Usha, S.; Subramani, C.; Padmanaban, Sanjeevikumar.

I: Energies, Bind 12, Nr. 5, 920, 01.2019.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Neural network-based model reference adaptive system for torque ripple reduction in sensorless poly phase induction motor drive

AU - Usha, S.

AU - Subramani, C.

AU - Padmanaban, Sanjeevikumar

PY - 2019/1

Y1 - 2019/1

N2 - This paper proposes the modified, extended Kalman filter, neural network-based model reference adaptive system and the modified observer technique to estimate the speed of a five-phase induction motor for sensorless drive. The proposed method is generated to achieve reduced speed deviation and reduced torque ripple efficiently. In inclusion, the result of speed performance and torque ripple under parameter variations were analysed and compared with the conventional direct synthesis method. The speed estimation of a five-phase motor in the four methods is analysed using MATLAB Simulink platform, and the optimum method is recognized using time domain analysis. It is observed that speed error is minimized by 60% and torque ripple is reduced by 75% in the proposed method. The hardware setup is carried out for the optimized method identified.

AB - This paper proposes the modified, extended Kalman filter, neural network-based model reference adaptive system and the modified observer technique to estimate the speed of a five-phase induction motor for sensorless drive. The proposed method is generated to achieve reduced speed deviation and reduced torque ripple efficiently. In inclusion, the result of speed performance and torque ripple under parameter variations were analysed and compared with the conventional direct synthesis method. The speed estimation of a five-phase motor in the four methods is analysed using MATLAB Simulink platform, and the optimum method is recognized using time domain analysis. It is observed that speed error is minimized by 60% and torque ripple is reduced by 75% in the proposed method. The hardware setup is carried out for the optimized method identified.

KW - Induction motor

KW - Kalman filter

KW - Luenberger observer

KW - Model reference adaptive system

KW - Speed estimation

UR - http://www.scopus.com/inward/record.url?scp=85063060412&partnerID=8YFLogxK

U2 - 10.3390/en12050920

DO - 10.3390/en12050920

M3 - Journal article

AN - SCOPUS:85063060412

VL - 12

JO - Energies

JF - Energies

SN - 1996-1073

IS - 5

M1 - 920

ER -