Induction motor modelling using fuzzy logic

Fuzzy logic has been widely used in many engineering applications since this can overcome the limitations of conventional method of data analysis, modelling and system identification, and control system. The capability of dealing with highly non-linear system modelling that is so complex that requir...

Full description

Saved in:

Bibliographic Details
Main Author:	Hashim, Mohd Nasri
Format:	Thesis
Language:	English English English
Published:	2013
Subjects:	TK2000-2891 Dynamoelectric machinery and auxiliaries Including generators, motors, transformers
Online Access:	http://eprints.uthm.edu.my/6695/1/24p%20MOHD%20NASRI%20HASHIM.pdf http://eprints.uthm.edu.my/6695/2/MOHD%20NASRI%20HASHIM%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/6695/3/MOHD%20NASRI%20HASHIM%20WATERMARK.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uthm-ep.6695
record_format	uketd_dc
spelling	my-uthm-ep.66952022-03-14T02:07:28Z Induction motor modelling using fuzzy logic 2013-01 Hashim, Mohd Nasri TK2000-2891 Dynamoelectric machinery and auxiliaries. Including generators, motors, transformers Fuzzy logic has been widely used in many engineering applications since this can overcome the limitations of conventional method of data analysis, modelling and system identification, and control system. The capability of dealing with highly non-linear system modelling that is so complex that require absolute analytical design make these mathematical model architecture more popular in the engineering field. This project is addressed on the modelling of induction motor Auto-Regressive with exogenous input (ARX) model structure using fuzzy logic. In this case fuzzy logic is combined with neural network of said Neuro Fuzzy (ANFIS) is applied and has functioned as estimator of the ARX model parameters. The ARX model of induction motor is estimated from its input output data. Input variable is voltage and output variable is speed. The experimental results show that the best model responses have similarly trend with the motor actual responses, final prediction error is 0.00873, loss function is 0.00807, and fit to working data is 67.22%. It means the model produce from system identification able adopt the motor dynamic and can use for replacing real motor for analysis and control design. 2013-01 Thesis http://eprints.uthm.edu.my/6695/ http://eprints.uthm.edu.my/6695/1/24p%20MOHD%20NASRI%20HASHIM.pdf text en public http://eprints.uthm.edu.my/6695/2/MOHD%20NASRI%20HASHIM%20COPYRIGHT%20DECLARATION.pdf text en staffonly http://eprints.uthm.edu.my/6695/3/MOHD%20NASRI%20HASHIM%20WATERMARK.pdf text en validuser mphil masters Universiti Tun Hussein Malaysia Fakulti Kejuruteraan Elektrik dan Elektronik
institution	Universiti Tun Hussein Onn Malaysia
collection	UTHM Institutional Repository
language	English English English
topic	TK2000-2891 Dynamoelectric machinery and auxiliaries Including generators, motors, transformers
spellingShingle	TK2000-2891 Dynamoelectric machinery and auxiliaries Including generators, motors, transformers Hashim, Mohd Nasri Induction motor modelling using fuzzy logic
description	Fuzzy logic has been widely used in many engineering applications since this can overcome the limitations of conventional method of data analysis, modelling and system identification, and control system. The capability of dealing with highly non-linear system modelling that is so complex that require absolute analytical design make these mathematical model architecture more popular in the engineering field. This project is addressed on the modelling of induction motor Auto-Regressive with exogenous input (ARX) model structure using fuzzy logic. In this case fuzzy logic is combined with neural network of said Neuro Fuzzy (ANFIS) is applied and has functioned as estimator of the ARX model parameters. The ARX model of induction motor is estimated from its input output data. Input variable is voltage and output variable is speed. The experimental results show that the best model responses have similarly trend with the motor actual responses, final prediction error is 0.00873, loss function is 0.00807, and fit to working data is 67.22%. It means the model produce from system identification able adopt the motor dynamic and can use for replacing real motor for analysis and control design.
format	Thesis
qualification_name	Master of Philosophy (M.Phil.)
qualification_level	Master's degree
author	Hashim, Mohd Nasri
author_facet	Hashim, Mohd Nasri
author_sort	Hashim, Mohd Nasri
title	Induction motor modelling using fuzzy logic
title_short	Induction motor modelling using fuzzy logic
title_full	Induction motor modelling using fuzzy logic
title_fullStr	Induction motor modelling using fuzzy logic
title_full_unstemmed	Induction motor modelling using fuzzy logic
title_sort	induction motor modelling using fuzzy logic
granting_institution	Universiti Tun Hussein Malaysia
granting_department	Fakulti Kejuruteraan Elektrik dan Elektronik
publishDate	2013
url	http://eprints.uthm.edu.my/6695/1/24p%20MOHD%20NASRI%20HASHIM.pdf http://eprints.uthm.edu.my/6695/2/MOHD%20NASRI%20HASHIM%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/6695/3/MOHD%20NASRI%20HASHIM%20WATERMARK.pdf
_version_	1747831083108401152

Induction motor modelling using fuzzy logic

Similar Items