摘要
为了提高汽轮机组故障诊断的效率,设计并实现了基于粗糙集和多类支持向量机的融合算法。把粗糙集作为数据的前处理器,对条件属性进行知识约简和去除冗余属性以达到降低数据维数的目的。然后构造多类支持向量机分类器并用约简后的新样本数据训练。测试结果表明,基于粗糙集和支持向量机融合算法的故障诊断方法诊断速度快,推广能力强。
In order to raise the efficiency of fault diagnosis of steam turbine units,a data fusion algorithm based on rough sets theory and support vector machine is developed and implemented.In this algorithm,the rough sets is used as data pre-processor,knowledge reduction of condition attribute and removal of redundant data attribute have reached the target of lowering the data dimension.Multi-class support vector machine classifier is constructed and trained with reduced sample data.Test results show that the fault diagnoses method based on rough sets theory and support vector machine has high speed and strong generalization ability.
出处
《武汉理工大学学报》
CAS
CSCD
北大核心
2010年第6期115-118,148,共5页
Journal of Wuhan University of Technology
基金
国家自然科学基金重大国际合作项目(50620130441)
武汉市科技攻关项目(200810321153)
武汉市青年科技晨光计划项目(200750731289)
关键词
粗糙集
支持向量机
数据融合
汽轮机组
故障诊断
rough sets
support vector machine
data fusion
steam turbine units
fault diagnosis
