Transformer winding state on-line monitoring method based on clustering analysis

Abstract

The invention discloses a transformer winding state on-line monitoring method based on clustering analysis. The transformer winding state on-line monitoring method comprises the steps that a vibrationsignal of a box wall of a transformer is collected, and the collected vibration signal is standardized; the standardized vibration signal is intercepted, and thus m sets of vibration signals are obtained; clustering analysis is conducted on the m sets of vibration signals of the transformer, and thus a transformer vibration characteristic curve is obtained; the root-mean-square values of the curve change rates Y<ci> of all types of vibration signals in class clusters C<t><(k)> relative to the transformer vibration characteristic curve Z<t> is calculated, and the average value Y<cm> of the root-mean-square values is calculated; the mean square value Y'<cm> of the curve change rates Y'<c> of to-be-detected transformer vibration curves y'<c> relative to the transformer vibration characteristic curve Z<t> is calculated; the Y'<cm> and the Y<cm> are compared, and if the Y'<cm> is less than or equal to the Y<cm>, it is judged that the operation state of a transformer winding is normal; andif the Y'<cm> is greater than the Y<cm>, the transformer winding is loosened or deformed. According to the transformer winding state on-line monitoring method, the loosening and deformation conditionsof the transformer winding can be monitored on line in effective and high-sensitivity modes.

Description

technical field [0001] The invention relates to a transformer signal monitoring method, in particular to an online transformer winding state monitoring method based on cluster analysis. Background technique [0002] Transformer is one of the most important equipment in the power system, and the stability of its operation has a great influence on the safety of the power system. With the increasing capacity of my country's power grid, the short-circuit capacity is also increasing, and the huge electromagnetic force generated by the surge current formed by the short-circuit at the outlet of the transformer poses a serious threat to the mechanical strength of the winding. After a transformer suffers a sudden short circuit, its winding may be loose or slightly deformed first, and the deformation of the transformer winding has a cumulative effect. Correspondingly, if the looseness or deformation cannot be detected and repaired in time, the short-circuit resistance capability of t...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to improve a method for on-line monitoring of transformer winding state based on cluster analysis, so as to solve the problem of using the vibration signal analysis on the surface of the transformer box as the fault diagnosis of transformer winding in the prior art due to the influence of the transformer mechanical structure. Due to the influence of various factors such as the dispersion of the process and the operating environment of the substation, it is impossible to efficiently and accurately obtain a relatively accurate monitoring of the winding state from the massive vibration signals obtained from the transformer vibration online monitoring system.

Images