Fault Diagnosis of Transformer Based on KPCA and Elman Neural Network

被引：4

作者：

Lin, Jun ^{[1
]}

Sheng, Gehao ^{[1
]}

Gao, Yuhao ^{[2
]}

Yan, Yingjie ^{[1
]}

Jiang, Xiuchen ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai, Peoples R China

[2] Hubei Univ Technol, Sch Elect Engn & Automat, Wuhan, Hubei, Peoples R China

来源：

2018 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT) | 2018年

基金：

中国国家自然科学基金;

关键词：

Transformer; KPCA; Elman Neural network; Fault diagnosis;

D O I：

10.1109/ICIT.2018.8352354

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Analysis of monitoring data of transformer can provide important theoretical basis for transformer fault diagnosis. In this paper, a transformer fault diagnosis method based on kernel principal component analysis (KPCA) and improved Elman neural network is proposed. Firstly, gas concentration, several commonly used ratios and seven new parameters are introduced as reference vectors. Then the main characteristic parameters extracted by KPCA algorithm are used as the input of Elman neural network to train the neural network. Finally, the test set is experimented with the trained network. The results indicate that the method in this paper compared with SVM and BP neural network has a higher diagnosis accuracy.

引用

页码：1232 / 1235

页数：4

共 21 条

[1]

Bai Cuifen, 2013, High Voltage Engineering, V39, P330, DOI 10.3969/j.issn.1003-6520.2013.02.011

[2] Knowledge discovery in neural networks with application to transformer failure diagnosis [J].

Castro, ARG ;

Miranda, V .

IEEE TRANSACTIONS ON POWER SYSTEMS, 2005, 20 (02) :717-724

[3] Intelligent Optimal Recurrent Wavelet Elman Neural Network Control System for Permanent-Magnet Synchronous Motor Servo Drive [J].

El-Sousy, Fayez F. M. .

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2013, 9 (04) :1986-2003

[4] Seam Tracking Monitoring Based on Adaptive Kalman Filter Embedded Elman Neural Network During High-Power Fiber Laser Welding [J].

Gao, Xiangdong ;

You, Deyong ;

Katayama, Seiji .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2012, 59 (11) :4315-4325

[5] Tangent Hyperplane Kernel Principal Component Analysis for Denoising [J].

Im, Joon-Ku ;

Apley, Daniel W. ;

Runger, George C. .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2012, 23 (04) :644-656

[6] Anomaly Detection and Characterization in Spatial Time Series Data: A Cluster-Centric Approach [J].

Izakian, Hesam ;

Pedrycz, Witold .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2014, 22 (06) :1612-1624

[7]

Izakian H, 2013, PROCEEDINGS OF THE 2013 JOINT IFSA WORLD CONGRESS AND NAFIPS ANNUAL MEETING (IFSA/NAFIPS), P1513, DOI 10.1109/IFSA-NAFIPS.2013.6608627

[8]

Luo Si-jia, 2007, High Voltage Engineering, V33, P106

[9] Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift [J].

Miranda, Vladimiro ;

Garcez Castro, Adriana R. ;

Lima, Shigeaki .

IEEE TRANSACTIONS ON POWER DELIVERY, 2012, 27 (03) :1350-1357

[10] An Adaptive Approach Based on KPCA and SVM for Real-Time Fault Diagnosis of HVCBs [J].

Ni, Jianjun ;

Zhang, Chuanbiao ;

Yang, Simon X. .

IEEE TRANSACTIONS ON POWER DELIVERY, 2011, 26 (03) :1960-1971

← 1 2 3 →