Transformer winding looseness recognition method based on LMD and permutation entropy

Abstract

The invention discloses a transformer winding looseness recognition method based on combination of LMD and permutation entropy. The method comprises the following steps: 1, collecting related historical vibration signals; 2, carrying out LMD decomposition on the collected vibration signal to obtain each PF part; 3, calculating a correlation coefficient method and selecting a PF part of which the correlation coefficient is higher than a set threshold value; 4, extracting the permutation entropy of each PF part as a feature vector; 5, dividing the vibration signals into a training set and a test set, and optimizing feature vectors of the training set; 6, inputting the optimized training set into the support vector machine for training, and testing by using the test set to obtain a trained support vector machine model; and 7, using the obtained support vector machine model as a classifier to carry out classification recognition on the test sample set. According to the method, the loose state of the transformer winding can be recognized before steady-state operation of the transformer, fault diagnosis of the transformer is achieved, and a new method is provided for transformer vibration signal feature extraction and fault diagnosis.

Description

technical field [0001] The invention belongs to the technical field of power transformer mechanical fault diagnosis, and in particular relates to a transformer winding looseness recognition method based on LMD and permutation entropy. Background technique [0002] The transformer is one of the most critical equipment in the power system. It may have internal faults during operation, which will affect the normal operation of the transformer and even cause damage to the entire power system. Therefore, in order to detect potential transformer failures in time and avoid sudden accidents, it is of great significance to carry out research on transformer condition monitoring and fault diagnosis. [0003] Loose transformer winding fault is the main early cause of transformer insulation problems, winding burnout and other serious faults and accidents. Traditional winding fault diagnosis methods include short-circuit impedance method, frequency response analysis method, low-voltage p...

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the present invention provides a transformer winding looseness recognition method based on LMD and permutation entropy, which solves the problem of misjudgment in the diagnostic method in the prior art

Images