FPGA implementation of neural network classifier for partial discharge time resolved data from magnetic probe

Thi Ngoc Tho Nguyen, Chandan Kumar Chakrabarty, Basri Abd Ghani Ahmad, Keem Siah Yap

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

2 Citations (Scopus)

Abstract

Partial discharge (PD) is a common reason that causes electrical breakdown in high voltage underground XLPE cables. This paper proposes a concept of how to build an on-line, on-site system that is able to diagnose the severity of PD activities in XLPE cable as well as differentiate different types of PD signals. The system consists of magnetic probes, low noise amplifier, 3GSPS analog to digital converter (ADC) and a field programmable gate array (FPGA) board. The energy of PD signals is used to assess the severity of PD activities and artificial neural network (ANN) is used to classify different types of PD waveforms. In addition, wavelet transform is used to clean the time-resolved input signals and statistical method is used to extract important features of PD signals to fetch into neural network. The training of ANN is done on personal computer. The prototype and results of the research is elaborated in this paper.

Original languageEnglish
Title of host publicationAPAP 2011 - Proceedings
Subtitle of host publication2011 International Conference on Advanced Power System Automation and Protection
Pages451-455
Number of pages5
DOIs
Publication statusPublished - 01 Dec 2011
Event2011 International Conference on Advanced Power System Automation and Protection, APAP 2011 - Beijing, China
Duration: 16 Oct 201120 Oct 2011

Publication series

NameAPAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection
Volume1

Other

Other2011 International Conference on Advanced Power System Automation and Protection, APAP 2011
CountryChina
CityBeijing
Period16/10/1120/10/11

Fingerprint

Partial discharges
Field programmable gate arrays (FPGA)
Classifiers
Neural networks
Underground cables
Low noise amplifiers
Digital to analog conversion
Personal computers
Wavelet transforms
Statistical methods
Cables
Electric potential

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Safety, Risk, Reliability and Quality

Cite this

Nguyen, T. N. T., Kumar Chakrabarty, C., Ahmad, B. A. G., & Yap, K. S. (2011). FPGA implementation of neural network classifier for partial discharge time resolved data from magnetic probe. In APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection (pp. 451-455). [6180444] (APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection; Vol. 1). https://doi.org/10.1109/APAP.2011.6180444
Nguyen, Thi Ngoc Tho ; Kumar Chakrabarty, Chandan ; Ahmad, Basri Abd Ghani ; Yap, Keem Siah. / FPGA implementation of neural network classifier for partial discharge time resolved data from magnetic probe. APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection. 2011. pp. 451-455 (APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection).
@inproceedings{d5cea9582ed74d92bf62495c6244e2dd,
title = "FPGA implementation of neural network classifier for partial discharge time resolved data from magnetic probe",
abstract = "Partial discharge (PD) is a common reason that causes electrical breakdown in high voltage underground XLPE cables. This paper proposes a concept of how to build an on-line, on-site system that is able to diagnose the severity of PD activities in XLPE cable as well as differentiate different types of PD signals. The system consists of magnetic probes, low noise amplifier, 3GSPS analog to digital converter (ADC) and a field programmable gate array (FPGA) board. The energy of PD signals is used to assess the severity of PD activities and artificial neural network (ANN) is used to classify different types of PD waveforms. In addition, wavelet transform is used to clean the time-resolved input signals and statistical method is used to extract important features of PD signals to fetch into neural network. The training of ANN is done on personal computer. The prototype and results of the research is elaborated in this paper.",
author = "Nguyen, {Thi Ngoc Tho} and {Kumar Chakrabarty}, Chandan and Ahmad, {Basri Abd Ghani} and Yap, {Keem Siah}",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/APAP.2011.6180444",
language = "English",
isbn = "9781424496198",
series = "APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection",
pages = "451--455",
booktitle = "APAP 2011 - Proceedings",

}

Nguyen, TNT, Kumar Chakrabarty, C, Ahmad, BAG & Yap, KS 2011, FPGA implementation of neural network classifier for partial discharge time resolved data from magnetic probe. in APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection., 6180444, APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection, vol. 1, pp. 451-455, 2011 International Conference on Advanced Power System Automation and Protection, APAP 2011, Beijing, China, 16/10/11. https://doi.org/10.1109/APAP.2011.6180444

FPGA implementation of neural network classifier for partial discharge time resolved data from magnetic probe. / Nguyen, Thi Ngoc Tho; Kumar Chakrabarty, Chandan; Ahmad, Basri Abd Ghani; Yap, Keem Siah.

APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection. 2011. p. 451-455 6180444 (APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection; Vol. 1).

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

TY - GEN

T1 - FPGA implementation of neural network classifier for partial discharge time resolved data from magnetic probe

AU - Nguyen, Thi Ngoc Tho

AU - Kumar Chakrabarty, Chandan

AU - Ahmad, Basri Abd Ghani

AU - Yap, Keem Siah

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Partial discharge (PD) is a common reason that causes electrical breakdown in high voltage underground XLPE cables. This paper proposes a concept of how to build an on-line, on-site system that is able to diagnose the severity of PD activities in XLPE cable as well as differentiate different types of PD signals. The system consists of magnetic probes, low noise amplifier, 3GSPS analog to digital converter (ADC) and a field programmable gate array (FPGA) board. The energy of PD signals is used to assess the severity of PD activities and artificial neural network (ANN) is used to classify different types of PD waveforms. In addition, wavelet transform is used to clean the time-resolved input signals and statistical method is used to extract important features of PD signals to fetch into neural network. The training of ANN is done on personal computer. The prototype and results of the research is elaborated in this paper.

AB - Partial discharge (PD) is a common reason that causes electrical breakdown in high voltage underground XLPE cables. This paper proposes a concept of how to build an on-line, on-site system that is able to diagnose the severity of PD activities in XLPE cable as well as differentiate different types of PD signals. The system consists of magnetic probes, low noise amplifier, 3GSPS analog to digital converter (ADC) and a field programmable gate array (FPGA) board. The energy of PD signals is used to assess the severity of PD activities and artificial neural network (ANN) is used to classify different types of PD waveforms. In addition, wavelet transform is used to clean the time-resolved input signals and statistical method is used to extract important features of PD signals to fetch into neural network. The training of ANN is done on personal computer. The prototype and results of the research is elaborated in this paper.

UR - http://www.scopus.com/inward/record.url?scp=84860689238&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860689238&partnerID=8YFLogxK

U2 - 10.1109/APAP.2011.6180444

DO - 10.1109/APAP.2011.6180444

M3 - Conference contribution

AN - SCOPUS:84860689238

SN - 9781424496198

T3 - APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection

SP - 451

EP - 455

BT - APAP 2011 - Proceedings

ER -

Nguyen TNT, Kumar Chakrabarty C, Ahmad BAG, Yap KS. FPGA implementation of neural network classifier for partial discharge time resolved data from magnetic probe. In APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection. 2011. p. 451-455. 6180444. (APAP 2011 - Proceedings: 2011 International Conference on Advanced Power System Automation and Protection). https://doi.org/10.1109/APAP.2011.6180444