Wavelet entropy analysis and machine learning classification model of DC serial arc fault in electric vehicle power system

被引：14

作者：

Xia, Kun ^{[1
]}

Liu, Bangzheng ^{[1
]}

Fu, Xiale ^{[1
]}

Guo, Haotian ^{[1
]}

He, Sheng ^{[1
]}

Yu, Wei ^{[2
]}

Xu, Jingjun ^{[2
]}

Dong, Hui ^{[2
]}

机构：

[1] Univ Shanghai Sci & Technol, Elect Engn Dept, 516 JunGong Rd, Shanghai 200093, Peoples R China

[2] Hella Shanghai Elect Co Ltd, R&D Ctr, Shanghai 201201, Peoples R China

来源：

IET POWER ELECTRONICS | 2019年 / 12卷 / 15期

基金：

中国国家自然科学基金;

关键词：

learning (artificial intelligence); fault diagnosis; pattern classification; regression analysis; support vector machines; wavelet transforms; power engineering computing; arcs (electric); entropy; electric vehicles; electric vehicle power system; direct current arc; wavelet entropy algorithm; support vector machine; DC serial arc fault; EV power system; machine learning classification model; logistic regression; IDENTIFICATION; LOCALIZATION;

D O I：

10.1049/iet-pel.2019.0375

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Electric vehicle (EV) power system is flammable and explosive when the direct current (DC) arc occurs at elevated temperature. Thus, DC serial arc real-time monitoring is an insurance to keep away from disaster. In this study, the detection algorithm of DC serial arc is proposed. The wavelet entropy algorithm, the classification model based on support vector machine and logistic regression are analysed separately. The above algorithms are combined to identify the DC serial arc faults effectively under different types of loads in EV power system. The results show that the combined algorithm has a good performance of DC serial arc detection with high accuracy and robustness compared with a simple approach. Meanwhile, the false detection rate of the detection algorithm is close to zero, which could ensure the safety and stable operation of the system.

引用

页码：3998 / 4004

页数：7

共 29 条

[1] Critical aspects on wavelet transforms based fault identification procedures in HV transmission line
Adly, Ahmed R.
El Sehiemy, Ragab A.
Abdelaziz, Almoataz Youssef
Ayad, Nabil M. A.
[J]. IET GENERATION TRANSMISSION & DISTRIBUTION, 2016, 10 (02) : 508 - 517
[2] Arc Fault Detection Method Based on CZT Low-Frequency Harmonic Current Analysis
Artale, Giovanni
Cataliotti, Antonio
Cosentino, Valentina
Di Cara, Dario
Nuccio, Salvatore
Tine, Giovanni
[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2017, 66 (05) : 888 - 896
[3] Contribution to the Study of Electric Arcs in Lithium-Ion Batteries
Augeard, Amaury
Singo, Tchapo
Desprez, Philippe
Abbaoui, M'hammed
[J]. IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY, 2016, 6 (07): : 1068 - 1078
[4] Cattin V, 2013, World Electric Vehicle Journal, V6, P762
[5] Series DC Arc Fault Detection Algorithm for DC Microgrids Using Relative Magnitude Comparison
Chae, Suyong
Park, Jinju
Oh, Seaseung
[J]. IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS, 2016, 4 (04) : 1270 - 1278
[6] Series Arc Fault Identification for Photovoltaic System Based on Time-Domain and Time-Frequency-Domain Analysis
Chen, Silei
Li, Xingwen
Xiong, Jiayu
[J]. IEEE JOURNAL OF PHOTOVOLTAICS, 2017, 7 (04): : 1105 - 1114
[7] Emrani A, 2017, IEEE W CONTR MODEL
[8] The Detection of Series Arc Fault in Photovoltaic Systems Based on the Arc Current Entropy
Georgijevic, Nikola L.
Jankovic, Marko V.
Srdic, Srdjan
Radakovic, Zoran
[J]. IEEE TRANSACTIONS ON POWER ELECTRONICS, 2016, 31 (08) : 5917 - 5930
[9] The Detection of Parallel Arc Fault in Photovoltaic Systems Based on a Mixed Criterion
He, Chuxuan
Mu, Longhua
Wang, Yijian
[J]. IEEE JOURNAL OF PHOTOVOLTAICS, 2017, 7 (06): : 1717 - 1724
[10] A Machine Learning and Wavelet-Based Fault Location Method for Hybrid Transmission Lines
Livani, Hanif
Evrenosoglu, C. Yaman
[J]. IEEE TRANSACTIONS ON SMART GRID, 2014, 5 (01) : 51 - 59

← 1 2 3 →