Transformer winding fault diagnosis method based on improved G-means vector element

Abstract

The invention discloses a transformer winding fault diagnosis method based on an improved G-means vector element. The accuracy of transformer fault diagnosis is improved. The method comprises the following steps: 1, acquiring a transformer winding vibration signal, performing G-means vector element decomposition (VED) on the actually measured transformer winding vibration signal, and introducing a deviation coefficient gamma to obtain K deviation vector functions IMgamma; 2, constructing signal feature vectors (energy entropy and root-mean-square value); 3, optimizing and selecting an initial vector element center of a G-means algorithm through an artificial sardine swarm algorithm; 4, running a G-means algorithm optimized by the artificial sardine swarm algorithm, and determining a vector element center by using the training sample; 5, fault diagnosis: calculating the minimum Euclidean distance between the test sample and different vector element centers, and realizing fault identification according to the minimum Euclidean distance principle. According to the invention, the condition that the G-means algorithm is caught in local optimum is avoided through the improved sardine swarm algorithm, and the vector element classification accuracy and the fault diagnosis accuracy are improved.

Description

technical field [0001] The invention relates to the technical field of transformer winding fault diagnosis, in particular to an improved G-means vector element transformer winding fault diagnosis method. Background technique [0002] Transformer failure will endanger the safe and stable operation of the power system, and winding mechanical failure accounts for a large proportion of transformer failures, so it is necessary to effectively sense and diagnose the state of transformer windings. To quickly and accurately identify the status information of transformer windings and implement fault diagnosis, the premise is to carry out effective feature extraction on the status signals of transformer windings. [0003] During the use of the transformer, the load current flowing through the winding is subjected to electromotive force under the leakage magnetic field, causing the winding to generate mechanical vibration, and the vibration is transmitted to the surface of the transform...

AI Technical Summary

Problems solved by technology

G-means vector element decomposition can decompose the nonlinear and non-stationary signal into the sum of multiple simple stationary signals, each signal has a center frequency, bu

Images