Transformer substation acoustic signal feature extraction method based on MFCC

Abstract

The invention discloses a transformer substation acoustic signal feature extraction method based on MFCC, and belongs to the field of monitoring. The method comprises the following steps: performing acoustic signal preprocessing, fast Fourier transform, Mel filter bank and logarithm DCT operation on a transformer acoustic signal in sequence, and extracting the characteristic quantity of the transformer acoustic signal; wherein the preprocessing comprises two steps of framing and windowing; converting the time domain signal into a frequency domain through fast Fourier transform, and calculatingan amplitude spectrum and spectral line energy of each frame; enabling the Mel filter bank to calculate energy for each frame of spectral line energy spectrum through the filter bank; carrying out logarithm DCT operation to obtain logarithms of the energy values, calculating an energy matrix and identifying the fault type in a fuzzy clustering or neural network mode. Distinguishing is carried outthrough timbre, extracted feature vectors have obvious difference, the operation speed is high, and the operation cost of a computer can be reduced; and the feature vectors are classified and markedby using a support vector machine algorithm, so that discrimination speed is high, accuracy is high and instruction is simple. The method can be widely applied to the field of operation monitoring andfault judgment of unattended substations.

Description

technical field [0001] The invention belongs to the field of monitoring, and in particular relates to a method for analyzing or monitoring the characteristics of the operating sound signal of primary equipment in a substation. Background technique [0002] The power transformer is a very critical equipment in the power system, and its operating status directly affects the operation of the entire power system. Under different operating conditions of the transformer, the acoustic signals of the operating status are also different. Therefore, during the regular inspections of the traditional inspectors, they often judge the operating status of the transformer by listening to the operating acoustic signal of the transformer. The sound signal of transformer operation can be used as an important judgment basis for the evaluation of transformer operation status, so the extraction of its characteristic parameters has important practical significance. [0003] Traditional feature pa...

AI Technical Summary

Problems solved by technology

However, wavelet and wavelet packet transformation need to select wavelet basis functions, which are used to analyze the entire signal after selection, so the adaptability is poor

[0005] In addition, ensemble empirical mode decomposition is an improved empirical mode decomposition method, which reduces frequency aliasing to a certain extent, and selects the decomposed intrinsic mode function and marginal spectral entropy as eigenvectors, but ensemble empirical mode decomposition has no mathematical theory Support, after decomposition, frequency components irrelevant to the original signal will be introduced, and the amount of calculation is large, taking up more resources, so the requirements for hardware computing performance are high, which restricts the accuracy and timeliness of the implementation of the acoustic signal detection method

Images