Enhancing Neural Networks-based Classification of Incipient Faults in Power Transformers via Preprocessing

被引：2

作者：

Rocha Reis, Agnaldo J. ^{[1
]}

Castanheira, Luciana G. ^{[1
]}

Barbosa, Ruben C. ^{[2
]}

机构：

[1] Univ Fed Ouro Preto, Sch Mines, Dept Control Engn & Automat, Ouro Preto, MG, Brazil

[2] Univ Fed Vicosa, Dept Agr Engn, Vicosa, MG, Brazil

来源：

2013 1ST BRICS COUNTRIES CONGRESS ON COMPUTATIONAL INTELLIGENCE AND 11TH BRAZILIAN CONGRESS ON COMPUTATIONAL INTELLIGENCE (BRICS-CCI & CBIC) | 2013年

关键词：

Patterns Recognition; Neural Networks; Preprocessing; Dissolved Gas Analysis; IN-OIL ANALYSIS; DIAGNOSIS;

D O I：

10.1109/BRICS-CCI-CBIC.2013.109

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The power transformer is one of the most important equipment in an electric power system. If this equipment is out of order for some reason, the damage for both society and electric utilities are very significant. In this work, we present a comparative study of the application of Linear Networks, Multi-Layer Perceptrons - with three and four layers - and Radial Basis Functions Networks in the classification of incipient faults via Dissolved Gas Analysis (DGA) in power transformers. Besides, preprocessing techniques for databases have been discussed as well. The proposed procedures have been applied to real databases derived from chromatographic tests of power transformers. The results obtained by all techniques are compared and fully described.

引用

页码：622 / 627

页数：6

共 50 条

[11] Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift
Miranda, Vladimiro
Garcez Castro, Adriana R.
Lima, Shigeaki
[J]. IEEE TRANSACTIONS ON POWER DELIVERY, 2012, 27 (03) : 1350 - 1357
[12] Graph Neural Networks-Based Multilabel Classification of Citation Network
Lachaud, Guillaume
Conde-Cespedes, Patricia
Trocan, Maria
[J]. INTELLIGENT INFORMATION AND DATABASE SYSTEMS, ACIIDS 2022, PT II, 2022, 13758 : 128 - 140
[13] A New Method for Fault Detection and Identification of Incipient Faults in Power Transformers
Ozgonenel, O.
Kilic, Erdal
Khan, M. Abdesh
Rahman, M. Azizur
[J]. ELECTRIC POWER COMPONENTS AND SYSTEMS, 2008, 36 (11) : 1226 - 1244
[14] Utilization of Wavelet Transform to Detect the Internal Incipient Faults of Power Transformers
Naderi, Mehdi Salay
Beiza, J.
Taghizadegan, N.
Dadjouyan, A. A.
Rabbaani, J.
[J]. INTERNATIONAL REVIEW OF ELECTRICAL ENGINEERING-IREE, 2011, 6 (04): : 1590 - 1597
[15] Virtual Instrument based Fault Classification in Power Transformers using Artificial Neural Networks
Nanda, Santosh Kumar
Gopalakrishna, S.
[J]. 2013 IEEE 1ST INTERNATIONAL CONFERENCE ON CONDITION ASSESSMENT TECHNIQUES IN ELECTRICAL SYSTEMS (CATCON), 2013, : 169 - 173
[16] The Importance of Variable Selection for Neural Networks-Based Classification in an Industrial Context
Cateni, Silvia
Colla, Valentina
[J]. ADVANCES IN NEURAL NETWORKS: COMPUTATIONAL INTELLIGENCE FOR ICT, 2016, 54 : 363 - 370
[17] Particle swarm optimization-based SVM for incipient fault classification of power transformers
Lee, Tsair-Fwu
Cho, Ming-Yuan
Shieh, Chin-Shiuh
Lee, Hong-Jen
Fang, Fu-Min
[J]. FOUNDATIONS OF INTELLIGENT SYSTEMS, PROCEEDINGS, 2006, 4203 : 84 - 90
[18] A new model of faults classification in power transformers based on data optimization method
Abdo, Ali
Liu, Hongshun
Zhang, Hongru
Guo, Jian
Li, Qingquan
[J]. ELECTRIC POWER SYSTEMS RESEARCH, 2021, 200
[19] ENSEMBLE OF NEURAL NETWORKS FOR DETECTION AND CLASSIFICATION OF FAULTS IN NUCLEAR POWER SYSTEMS
Razavi-Far, Roozbeh
Zio, Piero Baraldi Enrico
[J]. UNCERTAINTY MODELING IN KNOWLEDGE ENGINEERING AND DECISION MAKING, 2012, 7 : 1202 - 1207
[20] Preprocessing for Image Classification by Convolutional Neural Networks
Pal, Kuntal Kumar
Sudeep, K. S.
[J]. 2016 IEEE INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ELECTRONICS, INFORMATION & COMMUNICATION TECHNOLOGY (RTEICT), 2016, : 1778 - 1781

← 1 2 3 4 5 →