基于DGA和改进型灰关联度模型的牵引变压器故障诊断

Fault Diagnosis for Traction Transformer Based on DGA and Improved Grey Correlation Analysis Model

油中溶解气体分析(DGA)是诊断普通电力变压器故障的重要方法,但牵引变压器有着自身的特点,若仿效普通电力变压器的故障诊断方法,在诊断牵引变压器故障时精度较低。文中针对牵引变压器发生故障时的气体特征,提出了一种基于改进的灰关联度分析模型用于牵引变压器故障诊断的方法。该方法充分利用了牵引变压器油中气体数据的全部信息,且发挥了灰关联度适用于小样本、贫信息系统的优势,避免了局部关联和信息损失的缺陷。实例分析结果表明,该方法可以很好地判断牵引变压器故障类型,提高诊断精度。

DGA（dissolved gas analysis） is an important method for fauk diagnosis of power transformer, but if this method is used in fault diagnosis of traction transformer alike, the diagnosis accuracy will be very low because of some own characteristics of traction transformer. Therefore, considering the all gas features of a traction transformer when a fault takes place, a method based on the improved grey correlation analysis model for fault diagnosis of traction transformer is proposed in this paper. This method can utilize overall information of DGA fully, and can make use of the advantage of grey correlation analysis in dealing with less samples and lean grey information, thus partial correlation and information loss can be avoided. The analysis result of examples show that this method can determine fault types effectively with very higher diagnosis accuracy than ever.