基于证据理论的优化集成分类器融合算法及应用

doi:10.3969/j.issn.0438-1157.2012.09.032

化工学报 ›› 2012, Vol. 63 ›› Issue (9): 2877-2881.DOI: 10.3969/j.issn.0438-1157.2012.09.032

基于证据理论的优化集成分类器融合算法及应用

杜海莲¹, 吕锋¹, 辛涛¹, 杜妮²

1. 河北师范大学职业技术学院, 河北石家庄 050024;
2. 河北师范大学物理科学与信息工程学院, 河北石家庄 050024

收稿日期:2012-06-16 修回日期:2012-06-23 出版日期:2012-09-05 发布日期:2012-09-05
通讯作者: 吕锋
作者简介:杜海莲(1978-),女,硕士,讲师。
基金资助:
国家自然科学基金项目(60974063,61175059);河北师范大学科学研究基金项目(L2011Q10);河北省科技厅资助项目(11215650)。

Algorithm and application of optimal multi-classifier combination based on evidence theory

DU Hailian¹, LÜ Feng¹, XIN Tao¹, DU Ni²

1. College of Academic and Technology, Hebei Normal University, Shijiazhuang 050024, Hebei, China;
2. College of Physics Science and Information Engineering, Hebei Normal University, Shijiazhuang 050024, Hebei, China

Received:2012-06-16 Revised:2012-06-23 Online:2012-09-05 Published:2012-09-05
Supported by:
supported by the National Natural Science Foundation of China(60974063,61175059),the Foundation of Hebei Normal University(L2011Q10)and the Foundation of the Department of Science and Technology of Hebei Province(11215650).

摘要/Abstract

摘要： 多分类器融合方法在融合过程中需要对各分类器的输出进行加权,常见的加权方法是通过各分类器的分类正确率计算分类器的加权,但是这种方法得出的权值常常是不精确的。针对这个问题,给出了一种确定各个多分类器权值的方法。首先,通过训练集样本得出分类器系统的输出向量。然后,依据多分类器系统的输出向量与训练集样本的类别向量之间的距离最小提出一种权值的优化学习算法。最后,将得出的权值用于多分类器系统对故障类别的判定。实验结果表明,提出的方法提高了分类的正确率,能更好地判别出故障的类别。

关键词: 故障诊断, 多分类器融合, 证据理论

Abstract: In the multi-classifier system,how to determine the weights of individual classifier in order to get more accurate results becomes a question that need to be solved.An optimal weight learning method is presented in this paper.First,the training samples are respectively input into the multi-classifier system based on Dempster-Shafer theory in order to obtain the output vector.Then the error is calculated by means of figuring up the distance between the output vector and class vector of corresponding training sample,and the objective function is defined as mean-square error of all the training samples.The optimal weight vector is obtained by means of minimizing the objective function.Finally,new samples are classified according to the optimal weight vector.The effectiveness of this method is illustrated by the UCI standard data set and electric actuator fault diagnostic experiment.

Key words: fault diagnosis, multi-classifier combination, Dempster-Shafer theory

中图分类号:

TP391

杜海莲, 吕锋, 辛涛, 杜妮. 基于证据理论的优化集成分类器融合算法及应用[J]. 化工学报, 2012, 63(9): 2877-2881.

DU Hailian, LÜ Feng, XIN Tao, DU Ni. Algorithm and application of optimal multi-classifier combination based on evidence theory[J]. CIESC Journal, 2012, 63(9): 2877-2881.

参考文献 10

[1]	Zhou Donghua(周东华),Hu Yanyan(胡艳艳).Fault diagnosis techniques for dynamic systems [J],Automatic Sinica(自动化学报),2009,35(6):748-758
[2]	Han Deqiang(韩德强),Yang Yi(杨艺),Han Chongzhao(韩崇昭).A novel diversity measure of multiple classifier system based on distance of evidence//The Third Chinese Information Fusion Conference.Xi’an,2011:95-102
[3]	Mi Aizhong(米爱中),Hao Hongwei(郝红卫),Zheng Xuefeng(郑雪峰),Tu Xuyan(涂序彦).A method of multiple classifier fusion with self-adjusting weights[J].Electronic Sinica(电子学报),2009,37(11):2604-2609
[4]	Chen Bing(陈冰).The research of multiple classifiers ensemble algorithm.Shandong:Shandong Normal University,2009
[5]	Sun Liang(孙亮),Han Chongzhao(韩崇昭),Shen Jianjing(沈建京),Dai Ning(戴宁).Generalized rough set method for ensemble feature selection and multiple classifier fusion[J].Automatic Sinica(自动化学报),2008,34(3):298-304
[6]	Keller J M,Gray M R,Givens J A.A fuzzy K-nearest neighbor algorithm[J].IEEE Transaction on Systems,Man and Cybernetics,1985,15(4):580-585
[7]	Shafer G.A Mathematical Theory of Evidence[M].Princeton:Princeton University Press,1976:200-210
[8]	Smets P.The combination of evidence in the transferable belief model[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,1990,12:447-458
[9]	UCI machine learning repository..http://archive.ics.uci.edu/ml
[10]	Du Hailian(杜海莲).Actuator’s fault diagnosis in control system based on data fusion.Baoding:North China Electronic Power University,2005

[1]	徐野, 黄文君, 米俊芃, 申川川, 金建祥. 多源信息融合的离心式压缩机喘振诊断方法[J]. 化工学报, 2023, 74(7): 2979-2987.
[2]	明迁, 高逸, 胡剑, 李盛杰, 王金江. 热交换器泄漏故障虚拟感知方法研究[J]. 化工学报, 2023, 74(4): 1836-1846.
[3]	高学金, 程琨, 韩华云, 高慧慧, 齐咏生. 基于中心损失的条件生成式对抗网络的冷水机组故障诊断[J]. 化工学报, 2022, 73(9): 3950-3962.
[4]	杨静, 林振康, 汤君, 樊铖, 孙克宁. 电池系统的故障特征以及多故障的诊断与识别[J]. 化工学报, 2022, 73(8): 3394-3405.
[5]	孙哲, 金华强, 李康, 顾江萍, 黄跃进, 沈希. 基于知识数据化表达的制冷空调系统故障诊断方法[J]. 化工学报, 2022, 73(7): 3131-3144.
[6]	张成, 潘立志, 李元. 基于加权统计特征KICA的故障检测与诊断方法[J]. 化工学报, 2022, 73(2): 827-837.
[7]	张弛, 李浩, 胡海涛, 朱翀, 张玉莹, 南国鹏, 舒悦. 基于自动特征工程的飞行器轴承故障诊断[J]. 化工学报, 2021, 72(S1): 430-436.
[8]	邓佳伟, 邓晓刚, 曹玉苹, 张晓玲. 基于加权统计局部核主元分析的非线性化工过程微小故障诊断方法[J]. 化工学报, 2019, 70(7): 2594-2605.
[9]	杨新, 麻哲瑞, 申赫男, 陈鸿伟. 基于多尺度特征能量-核极限学习机的双循环流化床气流堵塞故障智能诊断[J]. 化工学报, 2019, 70(7): 2616-2625.
[10]	翟坤, 杜文霞, 吕锋, 辛涛, 句希源. 一种改进的动态核主元分析故障检测方法[J]. 化工学报, 2019, 70(2): 716-722.
[11]	鲁春燕, 李炜. 基于深度置信网络的炼化空压机故障诊断方法[J]. 化工学报, 2019, 70(2): 757-763.
[12]	彭开香, 张传放, 马亮, 董洁, 焦瑞华, 唐鹏. 面向系统层级的复杂工业过程全息故障诊断[J]. 化工学报, 2019, 70(2): 590-598.
[13]	顾炳斌, 熊伟丽. 基于多块信息提取的PCA故障诊断方法[J]. 化工学报, 2019, 70(2): 736-749.
[14]	李沛洁, 杨博, 李宏光. 基于关联规则的条件状态模糊Petri网及其在故障诊断中的应用[J]. 化工学报, 2018, 69(8): 3517-3527.
[15]	王占伟, 王林, 梁坤峰, 袁俊飞, 王智伟. 基于融合的贝叶斯网络的冷水机组故障诊断[J]. 化工学报, 2018, 69(7): 3167-3173.

基于证据理论的优化集成分类器融合算法及应用

Algorithm and application of optimal multi-classifier combination based on evidence theory

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 10

相关文章 15

编辑推荐

Metrics

本文评价