Online diagnosis method for transformer winding deformation position

Abstract

The invention discloses an online diagnosis method for a transformer winding deformation position. The method comprises the steps of (1) collecting a transformer with a known winding state, and dividing into a plurality of position sub-samples; (2) performing feature extraction on each position sub-sample by using an information entropy, adding a label of deforming or not, and inputting into a support vector machine for training a diagnostic model; (3) dividing the transformer to be diagnosed into several position sub-samples by the method in step (1), adopting the feature extraction method ofstep (2), and inputting to the trained diagnostic model in step (2); (4) outputting the diagnostic result of the support vector machine about whether the sub-samples of each position of the transformer to be diagnosed are deformed. The method can comprehensively analyze the variation of each monitoring index of the transformer in the complexity, the time-frequency domain and the like, automatically learn a diagnosis logic from the fault feature through a machine learning algorithm, achieve the intelligent diagnosis of the winding deformation, reduce the labor cost and improve the diagnosis effectiveness.

Description

technical field [0001] The invention relates to the field of fault diagnosis, in particular to an online diagnosis method for transformer winding deformation positions. Background technique [0002] Transformer is one of the main equipment of the power system, which plays a pivotal role in grid interconnection and power exchange. When the transformer is subjected to short-circuit impact or transportation collision and other factors, the transformer winding may undergo axial or radial dimension changes under the action of electrodynamic or mechanical force, usually characterized by local distortion, bulge or displacement of the winding, which is called winding out of shape. [0003] Severe winding deformation will lead to insulation breakdown, resulting in power system accidents and huge economic and social losses. The difficulty of the transformer winding deformation problem is that the winding deformation has the characteristics of concealment and gradual change, and the ...

AI Technical Summary

Problems solved by technology

The above method can judge whether the current power transformer winding is deformed or not, but it cannot accurately determine the position of the winding deformation

Images