Abnormal identification of dissolved gas in oil monitoring device based on multivariate statistical process monitoring

The on-line monitoring of dissolved gas in transformer oil can effectively reflect the abnormal state of transformer. However, abnormal operation of the monitoring equipment will greatly interfere with abnormal transformer identification. It is difficult to identify the abnormal operation of dissolved gas monitoring device. This paper introduces a method of processing of data-driven and presents an anomaly identification method for dissolved gas monitoring device in oil based on multivariate statistical process monitoring (MSPM). Firstly, MSPM abnormal identify model which based on PCA is established. This model can illustrate the data characteristics of the system under normal conditions. Then, identify abnormal data based on T
²
statistic and SPE statistic. T
²
can reflect most of the information of the principal component subspace, and is more suitable for the case of strong white noise. residual subspace SPE can handle the invisible information of the principal component subspace. It is found that the T
²
statistic and the SPE statistic are sensitive to the variation of characteristic gas. Finally, the abnormal work data library of monitoring device is established to identify the abnormal devices. This paper collects historical on-line monitoring data of a regional power grid to build a library, and predict device abnormal situation criterion based on this library. It listed the connection between common features of data and abnormal reason. The cross interference of monitoring equipment and overheat fault of transformer are correctly identifying to justify the method. This device can distinguish the abnormal state and detect transformer insulation cracking.