A winding deformation intelligent identification technology based on a transfer function characteristic principal component and a neural network

Abstract

The invention discloses a winding deformation intelligent identification technology based on a transfer function characteristic principal component and a neural network, belonging to the field of winding deformation fault detection. First, the zeros and poles of the current winding transfer function or frequency response are obtained, and the characteristic matrix is constructed from their frequencies and amplitudes, as well as their variations with respect to the reference winding. Secondly, the principal component of the eigenvector matrix is extracted by principal component analysis, and the principal component eigenvector is normalized. Finally, the BP neural network is constructed and trained, and the BP neural network is used to identify the current mechanical state of transformer windings. According to the idea of dimension reduction, the invention effectively extracts the principal component characteristic quantity of the winding state, and reduces the calculation amount and time. Compared with manual identification, the invention can well characterize the nonlinear relationship between the type, position and degree of winding deformation and the winding structure, overcomethe subjectivity and randomness of manual identification, and realize the intelligent identification of winding deformation.

Description

technical field [0001] The invention belongs to the technical field of high voltage and relates to a winding deformation identification method based on the characteristic principal component of transfer function and neural network. Background technique [0002] Winding deformation is one of the typical faults of power transformers, which is mainly caused by the huge electromotive force generated by short-circuit current, and the cumulative effect makes the deformation gradually intensified. If it is not discovered and repaired in time, the deformation of the winding can cause partial discharge and insulation degradation at any time, and even cause catastrophic accidents. [0003] In practice, the frequency response analysis method (FRA, referred to as the frequency response method) is generally used to detect the deformation of transformer windings. It has good stability and high repeatability, but there are still shortcomings in application: the evaluation of the frequency ...

AI Technical Summary

Problems solved by technology

If it is not found and repaired in time, the deformation of the winding can cause partial discharge and insulation degradation at any time, and even cause catastrophic accidents

[0003] In practice, the frequency response analysis method (FRA, referred to as the frequency response method) is generally used to detect the deformation of transformer windings. It has good stability and high repeatability, but there are still shortcomings in application: the evaluation of the frequency response trajectory in different states of the winding depends on Due to the professional quality and subjective experience of the inspectors; different winding states may show similar trajectories and statistical feature changes, which may cause misjudgment; the transfer function obtained indirectly will lose some zeros and poles that appear as subtle inflection points on the frequency response curve , which inevitably affects the evaluation of the winding state

[0005] At present, some studies on intelligent diagnosis of winding deformation remain in the simulation stage, and some obtain limited deformation samples. Therefore, the research on winding state and intelligent judgment is still relatively fragmented, and there is a lack of simultaneous comparison of the type, location and degree of deformation. Complete inductive experimental research and intelligent diagnosis

Images