基于大数据挖掘的电力变压器健康状态差异预警规则策略

考虑到模糊边界问题以及变压器个体之间的差异性特征,提出了一种基于大数据挖掘的电力变压器健康状态差异预警规则策略。应用模糊C-均值法辨识变压器的最优特性,通过概率图验证该方法能最大限度地反映变压器的个性化特征,且所选特征下的全套溶解数据符合Weibull模型。然后对溶解气体分布特征与缺陷/故障率进行关联分析,计算出相应的报警阈值。将气体浓度和气体增加率与已建立的警告相关联,可以识别变压器的运行状态。在此基础上,提出了基于不同阈值的预警规则,并将其应用于现场运行的变压器。试验结果表明,提出的方法准确率高达98.21%,证明了提出方法具有良好的状态监测性能。

Early warning rule strategy of power transformer health status difference based on big data mining

Considering the fuzzy boundary problem and the differences between individual transformers, a Personalized early warning strategy of power transformer based on fuzzy c-means was proposed. The fuzzy c-means method was used to identify the optimal characteristics of the transformer. The probability diagram was used to verify that the method can reflect the personalized characteristics of the transformer to the maximum extent, and the full set of dissolution data under the selected characteristics conform to the Weibull model. Then, the relationship between the distribution characteristics of dissolved gas and the defect/failure rate was analyzed, and the corresponding alarm threshold was calculated. The operation status of transformer could be identified by associating gas concentration and gas increase rate with established warning. On this basis, early warning rules based on different thresholds were proposed and applied to the field operation of transformers. The experimental results show that the accuracy rate of the proposed method is as high as 98.21%, which proves that the proposed method has good condition monitoring performance.