基于集对分析的变压器故障案例检索方法

Transformer Fault Case Retrieval Method Based on Set Pair Analysis

工程应用中,案例推理是设备故障分析的重要手段之一。针对将传统案例检索技术应用于变压器故障分析时,会发生因其待诊数据向量残缺,而导致检索结果不理想的问题,文中提出了一种基于集对分析的变压器故障案例检索方法,通过集对分析中的联系数定义案例间的相似性,配合“案例级”的指标权重设计,一方面计及了针对不同故障模式时同一指标权重的变化;另一方面解决了数据缺失、指标权重变化情况下案例相似度可比的问题。实例分析的结果表明:文中方法在变压器故障诊断中的有效性更具优势。

In engineering applications,case-based reasoning is one of the important means of equipment failure analysis.When the traditional case retrieval technology is applied to the transformer failure analysis,the problem that the retrieval result is not ideal due to the lack of data will occur.This paper presents a transformer fault case retrieval method based on set pair analysis.This paper use contact number in the set pair analysis as the similarity between cases,with the case-level weight of the index,to solve this problem.On the one hand,it takes into account the changes of indicator weight under different failure modes;on the other hand,it solves the problem that the case similarity is comparable under the insufficient data,and non-uniform weights.Example analysis result shows that the proposed method is more effective in the diagnosis of transformer fault diagnosis.