The robust harmonic filter design using artificial neural network and taguchi method

Ying Pin Chang, Wen Kung Tseng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A systematic approach to achieving optimal discrete-value harmonic filters using artificial neural network and Taguchi method was developed for a multi-bus system under abundant harmonic current sources. In this simulation, the Taguchi method was used first to perform an efficient experimental design and analyze the robustness of the harmonic filters. Then an artificial neural network (ANN) was used to minimize the variation and make the harmonic filters less sensitive to variations. The L36 orthogonal array was used as the learning data for the ANN to construct an artificial neural network model that could predict the parameters at discrete levels. In the design of harmonic filters, the outer array used to present the noise factors effect of loading uncertainty and changing of system impedances. The searching for optimal solution is applied to the harmonic problems in a steel plant, where both AC and DC arc furnaces are used and a static var compensator (SVC) is installed. The results showed the harmonic filters performance was significantly improved compared with the original design.

Original languageEnglish
Title of host publication2006 IEEE International Conference on Mechatronics, ICM
Pages300-304
Number of pages5
DOIs
Publication statusPublished - 2006 Dec 1
Event2006 IEEE International Conference on Mechatronics, ICM - Budapest, Hungary
Duration: 2006 Jul 32006 Jul 5

Publication series

Name2006 IEEE International Conference on Mechatronics, ICM

Other

Other2006 IEEE International Conference on Mechatronics, ICM
CountryHungary
CityBudapest
Period06-07-0306-07-05

Fingerprint

Taguchi methods
Neural networks
Iron and steel plants
Design of experiments
Furnaces

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Mechanical Engineering

Cite this

Chang, Y. P., & Tseng, W. K. (2006). The robust harmonic filter design using artificial neural network and taguchi method. In 2006 IEEE International Conference on Mechatronics, ICM (pp. 300-304). [4018378] (2006 IEEE International Conference on Mechatronics, ICM). https://doi.org/10.1109/ICMECH.2006.252543
Chang, Ying Pin ; Tseng, Wen Kung. / The robust harmonic filter design using artificial neural network and taguchi method. 2006 IEEE International Conference on Mechatronics, ICM. 2006. pp. 300-304 (2006 IEEE International Conference on Mechatronics, ICM).
@inproceedings{e70f1237a4554a0cb40aa0b1f015f7ff,
title = "The robust harmonic filter design using artificial neural network and taguchi method",
abstract = "A systematic approach to achieving optimal discrete-value harmonic filters using artificial neural network and Taguchi method was developed for a multi-bus system under abundant harmonic current sources. In this simulation, the Taguchi method was used first to perform an efficient experimental design and analyze the robustness of the harmonic filters. Then an artificial neural network (ANN) was used to minimize the variation and make the harmonic filters less sensitive to variations. The L36 orthogonal array was used as the learning data for the ANN to construct an artificial neural network model that could predict the parameters at discrete levels. In the design of harmonic filters, the outer array used to present the noise factors effect of loading uncertainty and changing of system impedances. The searching for optimal solution is applied to the harmonic problems in a steel plant, where both AC and DC arc furnaces are used and a static var compensator (SVC) is installed. The results showed the harmonic filters performance was significantly improved compared with the original design.",
author = "Chang, {Ying Pin} and Tseng, {Wen Kung}",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/ICMECH.2006.252543",
language = "English",
isbn = "0780397134",
series = "2006 IEEE International Conference on Mechatronics, ICM",
pages = "300--304",
booktitle = "2006 IEEE International Conference on Mechatronics, ICM",

}

Chang, YP & Tseng, WK 2006, The robust harmonic filter design using artificial neural network and taguchi method. in 2006 IEEE International Conference on Mechatronics, ICM., 4018378, 2006 IEEE International Conference on Mechatronics, ICM, pp. 300-304, 2006 IEEE International Conference on Mechatronics, ICM, Budapest, Hungary, 06-07-03. https://doi.org/10.1109/ICMECH.2006.252543

The robust harmonic filter design using artificial neural network and taguchi method. / Chang, Ying Pin; Tseng, Wen Kung.

2006 IEEE International Conference on Mechatronics, ICM. 2006. p. 300-304 4018378 (2006 IEEE International Conference on Mechatronics, ICM).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - The robust harmonic filter design using artificial neural network and taguchi method

AU - Chang, Ying Pin

AU - Tseng, Wen Kung

PY - 2006/12/1

Y1 - 2006/12/1

N2 - A systematic approach to achieving optimal discrete-value harmonic filters using artificial neural network and Taguchi method was developed for a multi-bus system under abundant harmonic current sources. In this simulation, the Taguchi method was used first to perform an efficient experimental design and analyze the robustness of the harmonic filters. Then an artificial neural network (ANN) was used to minimize the variation and make the harmonic filters less sensitive to variations. The L36 orthogonal array was used as the learning data for the ANN to construct an artificial neural network model that could predict the parameters at discrete levels. In the design of harmonic filters, the outer array used to present the noise factors effect of loading uncertainty and changing of system impedances. The searching for optimal solution is applied to the harmonic problems in a steel plant, where both AC and DC arc furnaces are used and a static var compensator (SVC) is installed. The results showed the harmonic filters performance was significantly improved compared with the original design.

AB - A systematic approach to achieving optimal discrete-value harmonic filters using artificial neural network and Taguchi method was developed for a multi-bus system under abundant harmonic current sources. In this simulation, the Taguchi method was used first to perform an efficient experimental design and analyze the robustness of the harmonic filters. Then an artificial neural network (ANN) was used to minimize the variation and make the harmonic filters less sensitive to variations. The L36 orthogonal array was used as the learning data for the ANN to construct an artificial neural network model that could predict the parameters at discrete levels. In the design of harmonic filters, the outer array used to present the noise factors effect of loading uncertainty and changing of system impedances. The searching for optimal solution is applied to the harmonic problems in a steel plant, where both AC and DC arc furnaces are used and a static var compensator (SVC) is installed. The results showed the harmonic filters performance was significantly improved compared with the original design.

UR - http://www.scopus.com/inward/record.url?scp=34250800456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250800456&partnerID=8YFLogxK

U2 - 10.1109/ICMECH.2006.252543

DO - 10.1109/ICMECH.2006.252543

M3 - Conference contribution

AN - SCOPUS:34250800456

SN - 0780397134

SN - 9780780397132

T3 - 2006 IEEE International Conference on Mechatronics, ICM

SP - 300

EP - 304

BT - 2006 IEEE International Conference on Mechatronics, ICM

ER -

Chang YP, Tseng WK. The robust harmonic filter design using artificial neural network and taguchi method. In 2006 IEEE International Conference on Mechatronics, ICM. 2006. p. 300-304. 4018378. (2006 IEEE International Conference on Mechatronics, ICM). https://doi.org/10.1109/ICMECH.2006.252543