[1]张 伟,陈建峡,李 超,等.输电线路故障分析多分类模型研究及应用[J].湖北工业大学学报,2019,34(2):5-9+21.
 ZHANG Wei,CHEN Jianxia,LI Chao,et al.Research and Application of Multi Classification Model for Fault Analysis of Transmission Lines[J].,2019,34(2):5-9+21.
点击复制

输电线路故障分析多分类模型研究及应用()
分享到:

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
34卷
期数:
2019年第2期
页码:
5-9+21
栏目:
湖北工业大学学报
出版日期:
2019-04-30

文章信息/Info

Title:
Research and Application of Multi Classification Model for Fault Analysis of Transmission Lines
文章编号:
1003-4684(2019)02-0005-05
作者:
张  伟1 陈建峡1 李  超1 黄煜俊1 徐欣雨2
1 湖北工业大学计算机学院, 湖北 武汉 430068;
2 日本东京大学工程学院, 日本 东京
Author(s):
ZHANG Wei1 CHEN Jianxia1 LI Chao1 HUANG Yujun1 XU Xinyu2
1 School of Computer Science,Hubei Univ. of Tech.,Wuhan430068, China;
2 School of Engineering, University of Tokyo, Tokyo, Japan
关键词:
核密度逻辑回归 核密度估计 二叉树 输电线路 故障分析
Keywords:
DLR kernel density estimation two fork tree transmission line fault analysis
分类号:
TP301.6
文献标志码:
A
摘要:
为了有效而准确地分析智能电网中输电线路故障和寻找诱发故障的主要因素,研发了基于二叉树的核密度逻辑回归多分类模型,以解决输电线路不对称故障分析的问题。该模型根据NadarayaWatson密度估计将训练数据映射到了特定的特征空间,根据二叉树结构特点将多个DLR模型组合成一个具有多分类能力的二叉树,并加以优化。实验结果表明,基于MCDLR的分类结果在准确率上和分类时间上明显优于已有的传统的多分类算法。
Abstract:
This paper proposes a novel MCDLRBT model (Multi-Classification of Density logistic regression based on binary tree, for short, MCDLRBT) in order to solve the problem of asymmetric fault analysis of transmission lines. The MCDLRBT model firstly maps the training data to a specific feature space based on the Nadaraya-Watson density estimation. Then, according to the structure characteristics of the two forked tree, MCDLRBT combines the multiple DLR (Density Estimation Logistic Regression, DLR) model into a two fork tree with multiple classification abilities and optimizes it in the end. The experimental results show that the classification results based on MCDLRBT are superior to the existing traditional multiple classification algorithms in the respects of accuracy and classification time.

参考文献/References:

[1] Zhan Cailiang. Application of AI technology in fault diagnosis of power system[J]. Guangdong Electric Power,2011,24(9):87-92.
[2] Zhang H, Berg A C, Maire M, et al. Svm-knn: Discriminative nearest neighbor classification for visual category recognition[J]. Proc.ieee Conf.computer Vision & Pattern Recognition, 2006, 2:2126-2136.
[3] 虞和济,陈长征,张省. 基于神经网络的只能诊断[J]. 振动工程学,2000,13(2):202-209.
[4] Mao Lin, Lu Quanhua, Cheng Tao. The research and application of ensemble logistic regression classification algorithm based on high dimensional data[J]. Bulletin of Science and Technology, 2013,29(12):64-66.
[5] Mao Yi, Chen Wenlin, Guo Baolong, Chen Yixin. A novel logistic regression model based on density estimation[J].Acta Automatica Sinica,2014,40(1):62- 72.
[6] 党华丽.Matlab/Simulink仿真在信号与系统分析中的应用[J].信息技术,2010(3):123-127.
[7] 马笑潇,黄席樾,柴毅.基于 SVM 的二叉树多类分类算法及其在故障诊断中的应用[J].控制与决策,2003,18(3):272-276.
[8] 韩邦合,李永明.计算逻辑学中的误差累积理论[J]计算工程与应用,2009,45(23):9-10.
[9] Silverman B W, Green P J. Density estimation for statistics and data analysis[M].London: Chapman and Hall, 1986.
[10] kuronya A, Lozovanu V. Infinitesimal newton-okounkov bodies and jet separation[J].Duke Mathematical journal 2017,166(7):1349-1376.
[11] 李昆仑,黄厚宽,田盛丰,一种基于有向无环图的多类SVM 分类器[J].模式识别与人工智能,2003,16(2):164-168.
[12] 袁胜发,褚福磊.SVM多类分类算法及其在故障诊断中的应用[J].振动工程学报,2004,17(5):419-421.
[13] 吕晓丽,李雷,曹未丰.基于二叉树的SVM多类分类算法[J].信息技术2008(4):1-3.
[14] 王成江,马新明,官云,等.基于 SVM 的改进二叉树输电线路故障分类器[J].电力系统保护与控制,2010,38(5):39-44.
[15] Eltibi M F, Ashour W M. Initializing kmeans clusteringalgorithmusing.statistical.information[J]. International Journal of Computer Applications 2013,29(7):51-55.

备注/Memo

备注/Memo:
[收稿日期] 2018-06-22
[基金项目] 湖北省科技厅自然科学基金青年面上项目(2017CFB326)
[第一作者] 张    伟(1992-), 男, 湖北黄冈人,湖北工业大学硕士研究生,研究方向为机器学习,云计算与大数据
[通信作者] 陈建峡(1971-), 女, 湖北丹江口人,工学硕士,湖北工业大学副教授,研究方向为机器学习,云计算与大数据
更新日期/Last Update: 2019-11-29