【作者】 杨丽君； 郑绳楦；

【Author】 Yang Lijun~1 Zheng Shengxuan~2 (College of Electric Engineering,Yanshan University Qinhuangdao 066004,China) (College of Information Science and Engineering,Yanshan University Qinhuangdao 066004,China)

【机构】 燕山大学电气工程学院； 燕山大学信息工程学院；

【摘要】 鉴于电力变压器故障信息的复杂性和不完备性,建立了基于粗糙集(RS)和支持向量机(SVM)相结合的故障诊断模型。先利用RS对变压器的故障样本进行知识约简,以获得故障征兆最小条件属性与故障类型的相关关系;后利用多类SVM对小样本数据的泛化能力,建立多类故障分类器用于故障诊断。实例验证了该方法是有效的。更多还原

【Abstract】 Due to the incompleteness and complexity of fault diagnosis for power transformer,a method based on RS and multi-class SVM is proposed to identify the fault of the power transformer. It combines the reduction ability of RS with the classification ability of the SVM. The original fault examples is reduced by using the rough set theory to get a simple rule collection. Then the multi-elass SVM is used to classify the real faults. The efficiency is proved too.更多还原