一种基于改进贝叶斯分类器的基本信任分配构造方法

针对D-S证据理论在应用于变压器故障诊断时基本信任分配的问题,本文提出了一种基于改进贝叶斯分类器的基本信任分配函数的构造方法,该方法根据不同的属性值来确定满足条件的取值区间,克服了贝叶斯分类器同一区域内基本信任分配函数无法变化的问题。实验表明,构造的基本信任分配函数正确有效。...

Full description

Saved in:
Bibliographic Details
Published in电测与仪表 Vol. 51; no. 18; pp. 34 - 38
Main Author 苑津莎 何亚军 秦英
Format Journal Article
LanguageChinese
Published 华北电力大学,河北保定,071003 2014
Subjects
变压器
基本信任分配函数
故障诊断
贝叶斯分类器
变压器
power transformer
fault diagnosis
BPA
故障诊断
贝叶斯分类器
基本信任分配函数
Bayesian classifier
Online AccessGet full text
ISSN1001-1390

Cover

More Information
Summary:针对D-S证据理论在应用于变压器故障诊断时基本信任分配的问题,本文提出了一种基于改进贝叶斯分类器的基本信任分配函数的构造方法,该方法根据不同的属性值来确定满足条件的取值区间,克服了贝叶斯分类器同一区域内基本信任分配函数无法变化的问题。实验表明,构造的基本信任分配函数正确有效。
Bibliography:power transformer, fault diagnosis, BPA, Bayesian classifier
23-1202/TH
YUAN Jin-sha, HE Ya-jun, QIN Ying （North China Electric Power University, Baoding 071003, Hebei, China）
Due to the problem of the basic probability assignment （BPA） function produced by D-S evidence theory being adopted in the transformer fault diagnosis, an improved Bayesian classifier based method has been proposed in this paper, which will confirm the suitable interval according to the different attribute values so as to solve the problem that the basic probability assignment is invariable in the individual areas. Experimental results varify the effectiveness and accuracy.
ISSN:1001-1390