基于可拓理论的故障模式识别研究  

Study on Fault Pattern Recognition Based on Extension Theory

作　　者：朱存[1] 倪远平[1] 李凌[1] 

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650051

出　　处：《化工自动化及仪表》2010年第11期45-48,共4页Control and Instruments in Chemical Industry

基　　金：国家自然科学基金资助项目(30860055)

摘　　要：针对变压器潜伏性故障,提出一种以物元模型和关联函数为基础的可拓故障诊断法。物元模型的建立是基于变压器的三比值法和改进特征气体法,分析故障机理,选取较优的有代表性的故障特征气体或比值,作为物元模型的特征量。然后,通过可拓关联函数计算待诊变压器故障参数与标准故障模式的关联度,从而进行故障判断。用具体实例进行了诊断验证,结果表明该方法具有故障分类识别的有效性和可行性。A novel extension fault diagnosis method based on the matter-element model and correlation function was presented for latent fault of transformer.Based on three-ratio method and improved characteristics of gas method,the matter-element models were established.According to analyzing fault mechanism,better representative fault characteristics of gas were selected for characteristic quantities of matter-element models.By extension correlation function to compute the correlation degree between the parameters of stoppage transformer and the standard fault mode to determine fault.The examples prove that the method is effective and feasible for fault classification and recognition.

关 键 词：物元模型 关联函数 变压器 故障识别 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置] TM411[自动化与计算机技术—控制科学与工程]