A DC Arc Fault Detection Method Based on Catboost Algorithm for Different Electrode Materials

doi:10.7652/xjtuxb202203013

您当前的位置：

首页 >

文章列表页 >

A DC Arc Fault Detection Method Based on Catboost Algorithm for Different Electrode Materials

更新时间：2025-07-09

- A DC Arc Fault Detection Method Based on Catboost Algorithm for Different Electrode Materials
- Vol. 56, Issue 3, Pages: 124-134(2022)
- 作者机构：
  
  西安交通大学电力设备电气绝缘国家重点实验室,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202203013
  CLC： O441.1
- Online First：10 March 2022，
  
  Published：2022
- 稿件说明：
移动端阅览
A DC Arc Fault Detection Method Based on Catboost Algorithm for Different Electrode Materials[J]. 2022, 56(3): 124-134.
DOI：

A DC Arc Fault Detection Method Based on Catboost Algorithm for Different Electrode Materials[J]. 2022, 56(3): 124-134. DOI： 10.7652/xjtuxb202203013.

摘要

为了研究直流系统内不同电极材料对故障电弧检测造成的干扰

针对性地解决多种电极材料下故障电弧检测的误动与拒动问题

提出了改进Catboost算法的直流故障电弧检测算法。搭建直流故障电弧实验平台

以拉弧的方式获取了6种电极材料条件下的直流故障电弧数据

通过构建故障电弧检测特征评价指标

采用小波变换方法在不同电极材料条件下更有效地提取故障电弧时频特征; 分析不同电极材料对直流故障电弧检测特征、算法效率的影响

指出检测特征指标与材料熔点、电阻率呈正相关关系; 提出的算法相较于现有的阈值比较算法和Adaboost算法提高了电弧检测范围

有效解决了纯铝电极材料下难以准确检测电弧的问题。该算法在6种不同电极材料下均能实现1.5 s内对电弧的快速检测

检测准确率达到100%

满足UL1699B标准要求。

Abstract

In order to study the interference of different electrode materials on arc fault detection in DC system

and to solve the malfunction problems of arc fault detection with avarious electrode materials

a DC arc fault detection algorithm based on Catboost algorithm is proposed. A DC arc fault experiment platform is built and the DC arc fault data from 6 electrode materials are obtained by the pulling-apart method. Through constructing the evaluation index of the arc fault detection characteristic

the wavelet transform method is used to extract time-frequency characteristics of arc faults more effectively for different electrode materials. The influences of different electrode materials on DC arc fault detection characteristics and efficiency of the algorithms are analyzed

and it is pointed out that the detection characteristic index has a positive correlation with the melting point and resistivity of electrode material. Compared with the existing threshold comparison method and the Adaboost algorithm

the proposed algorithm improves the range of arc fault detection and effectively solves the problem that it is difficult to accurately detect arc faults using pure aluminum electrode material. This algorithm can realize rapid detection of arc faults within 1.5 s for the 6 different electrode materials

and the detection accuracy reaches 100%

which meets the requirements of UL1699B standard.

关键词

Keywords

references

刘小军, 熊庆, 汲胜昌, 等. 针对串联直流电弧的电容电流时频检测方法 [J]. 西安交通大学学报, 2018, 52(12): 152-158.

LIU Xiaojun, XIONG Qing, JI Shengchang, et al. Detection method for series DC arc using time-frequency domain characteristics of capacitive current [J]. Journal of Xi'an Jiaotong University, 2018, 52(12): 152-158.

JOHNSON J, PAHL B, LUEBKE C, et al. Photovoltaic DC arc fault detector testing at Sandia National Laboratories [C]∥Proceedings of the 2011 37th IEEE Photovoltaic Specialists Conference. Piscataway, NJ, USA, IEEE, 2012: 3614-3619.

王毅, 陈进, 李松浓, 等. 基于时频域分析和随机森林的故障电弧检测 [J]. 电子测量与仪器学报, 2021, 35(5): 62-68.

WANG Yi, CHEN Jin, LI Songnong, et al. Arc fault detection based on time and frequency analysis and random forest [J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(5): 62-68.

陈思磊, 李兴文, 屈建宇. 直流故障电弧研究综述 [J]. 电器与能效管理技术, 2015(15): 1-6.

CHEN Silei, LI Xingwen, QU Jianyu. Overview of research about DC arc fault [J]. Electrical Energy Management Technology, 2015(15): 1-6.

LU S, PHUNG B, ZHANG D. A comprehensive review on DC arc faults and their diagnosis methods in photovoltaic systems [J]. Renewable and Sustainable Energy Reviews, 2018, 89: 88-98.

International Electrotechnical Commission. General requirements for arc fault detection devices: IEC 62606-2013 [S]. Geneva: IEC, 2013.

Underwriters Laboratories Inc..Standard for safety for photovoltaic(PV)DC arc-fault circuit protection: UL 1699B-2018 [S]. Northbrook, IL, USA: UL, 2018.

ABDULLAH Y, SHAFFER J, HU B, et al. Hurst-exponent-based detection of high-impedance DC arc events for 48-V systems in vehicles [J]. IEEE Transactions on Power Electronics, 2021, 36(4): 3803-3813.

AHMADI M, SAMET H, GHANBARI T. A new method for detecting series arc fault in photovoltaic systems based on the blind-source separation [J]. IEEE Transactions on Industrial Electronics, 2020, 67(6): 5041-5049.

熊庆, 肖戎, 汲胜昌, 等. 基于电磁辐射特性的直流电弧检测方法 [J]. 高电压技术, 2017, 43(9): 2967-2975.

XIONG Qing, XIAO Rong, JI Shengchang, et al. Detection method for DC arc based on electromagnetic radiation characteristics [J]. High Voltage Engineering, 2017, 43(9): 2967-2975.

XIONG Q, JI S, LIU X, et al. Electromagnetic radiation characteristics of series DC arc fault and its determining factors [J]. IEEE Transactions on Plasma Science, 2018, 46(11): 4028-4036.

CHEN S, LI X. PV series arc fault recognition under different working conditions with joint detection method [C]∥Proceedings of the 2016 IEEE 62nd Holm Conference on Electrical Contacts. Piscataway, NJ, USA, IEEE, 2016: 25-32.

CHEN S, LV Q, MENG Y, et al. Hardware implementation of series arc fault detection algorithm for different DC resistive systems [C]∥Proceedings of the 2019 IEEE 65th Holm Conference on Electrical Contacts. Piscataway, NJ, USA, IEEE, 2019: 245-249.

蔡焕青, 周明, 邵瑰玮, 等. 不锈钢复合材料用于输电线路杆塔接地系统及其耐腐蚀性研究 [J]. 高电压技术, 2014, 40(9): 2938-2944.

CAI Huanqing, ZHOU Ming, SHAO Guiwei, et al. Research of stainless steel composite material applied to grounding device for transmission line tower and its corrosion resistance [J]. High Voltage Engineering, 2014, 40(9): 2938-2944.

YAO X, HERRERA L, JI S, et al. Characteristic study and time-domain discrete-wavelet-transform based hybrid detection of series DC arc faults [J]. IEEE Transaction on Power Electronics, 2014, 29(6): 3103-3115.

张黎明, 张小栋, 陆竹风, 等. 用于稳态视觉诱发电位特征频率提取的同步压缩短时傅里叶变换方法 [J]. 西安交通大学学报, 2017, 51(2): 20-26.

ZHANG Liming, ZHANG Xiaodong, LU Zhufeng, et al. A synchrosqueezing short-time fourier transform method characteristic frequency extraction of steady state visual evoked potential [J]. Journal of Xi'an Jiaotong University, 2017, 51(2): 20-26.

SHI J, ZHANG Q, XU D, et al. Speed detection based on STFT for no-coupling SACS motor testing [C]∥Proceedings of the IEEE 2002 28th Annual Conference of the Industrial Electronics Society. Piscataway, NJ, USA: IEEE, 2002: 1594-1599.

CHEN S, LI X, XIONG J. Series arc fault identification for photovoltaic system based on time-domain and time-frequency-domain analysis [J]. IEEE Journal of Photovoltaics, 2017, 7(4): 1105-1114.

XU N, YANG Y, JIN Y, et al. Identification of series fault arc of low-voltage power cables in substation based on wavelet transform [C]∥2020 IEEE 5th International Conference on Integrated Circuits and Microsystems. Piscataway, NJ, USA: IEEE, 2020: 188-192.

CHEN S, LI X, MENG Y, et al. Wavelet-based protection strategy for series arc faults interfered by multicomponent noise signals in grid-connected photovoltaic systems [J]. Solar Energy, 2019, 183: 327-336.

XIA K, HE S, TAN Y, et al. Wavelet packet and support vector machine analysis of series DC arc fault detection in photovoltaic system [J]. IEEJ Transactions on Electrical and Electronic Engineering, 2019, 14(2): 192-200.

LE V, Yao X, HUNG T, et al. Series DC arc fault detection based on ensemble machine learning [J]. IEEE Transactions on Power Electronics, 2020, 35(8): 7826-7839.

翟夕阳, 王晓丹, 李睿, 等. 采用多类代价指数损失函数的代价敏感AdaBoost算法 [J]. 西安交通大学学报, 2017, 51(8): 33-39.

ZHAI Xiyang, WANG Xiaodan, LI Rui, et al. A multi-class cost sensitivity Adaboost algorithm using multi-class cost exponential loss function [J]. Journal of Xi'an Jiaotong University, 2017, 51(8): 33-39.

HANCOCK J, KHOSHGOFTAAR T. Medicare fraud detection using CatBoost [C]∥Proceedings of the 2020 IEEE 21st International Conference on Information Reuse and Integration for Data Science. Piscataway, NJ, USA: IEEE, 2020: 97-103.

YIN Z, WANG L, ZHANG B, et al. An integrated DC series arc fault detection method for different operating conditions [J]. IEEE Transactions on Industrial Electronics, 2020, 68(12): 12720-12729.

AHMADI M, SAMET H, GHANBARI T. Series arc fault detection in photovoltaic systems based on signal to noise ratio characteristics using cross-correlation function [J]. IEEE Transactions on Industrial Informatics, 2019, 16(5): 3198-3209.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Influencing Factors on Manganese Dioxide Deposited with Pulse Current Method for Supercapacitors

Research on the Electrohydrodynamic Effects of Ionic Liquid-Modified Fuels

A Structure-Semantics-Residual Collaborative Image Compression Framework：Towards Privacy Protection and High-Fidelity Reconstruction

Windage Loss and Flow Characteristics in Impeller Back Gaps of sCO2 Radial Inflow Turbines

Numerical Simulation of Heat-Moisture Barrier Performance of a Horizontal Air Curtain in Cold Storage

Related Author

马扬洲 1

徐友龙 1

肖芳 1

白海春 1

Related Institution

Electronic Materials Research Laboratory, Key Laboratory of the Ministry of Education, Xi'an Jiaotong University

International Dielectric Materials Research Center, Xi'an Jiaotong University

⁰