An Online Detection Method of Transformer Operating Status Based on Voiceprint Recognition

Abstract

The invention provides an online transformer operating state detection method based on voiceprint recognition, which belongs to the technical field of transformer fault detection. The method includes: S101, performing frame-by-frame processing on the voiceprint signal collected during normal operation of the transformer, and obtaining the feature vector of each frame of the voiceprint signal; S102, fusing each feature value in the feature vector to obtain a comprehensive Evaluation index and the weight of each feature value; S103, if the comprehensive evaluation index obeys the normal distribution, use the 3σ criterion in statistics to obtain the alarm line for the comprehensive evaluation index; S104, for the transformer with unknown operating status, according to the obtained The weight of the eigenvalues ​​is used to calculate the corresponding comprehensive evaluation index. If the calculated comprehensive evaluation index exceeds the alarm line for many times in a row, it is determined that the transformer with an unknown operating state is abnormal. By adopting the invention, the detection rate of abnormally operating transformers can be improved, the false detection rate is reduced, and a large number of fault samples are not needed.

Description

technical field [0001] The invention relates to the technical field of transformer fault detection, in particular to an online detection method for transformer operating status based on voiceprint recognition. Background technique [0002] In recent years, with the rapid development of UHV backbone grids, the "straight and straight" grid structure has brought enormous pressure to the safe and stable operation of the grid. Some UHV equipment has high technical complexity and is still in a period of unstable quality. Once a failure occurs, it will have a very large impact on production and life. Traditional detection methods mainly include: oil chromatography detection method, ultrasonic detection method, vibration detection method, etc.; among them, [0003] The oil chromatography detection method judges the type and severity of the fault by detecting the content of gas components in the oil. Since it takes a certain time from the occurrence of the fault to the change of the...

AI Technical Summary

Problems solved by technology

[0008] The existing feature extraction methods mainly include extracting time-frequency domain features of signals such as characteristic frequency, kurtosis, and mean value, using wavelet decomposition or wavelet packet decomposition to extract energy features, and extracting Mel-Frequency Cepstral Coefficients (Mel-Frequency Cepstral Coefficients, MFCCs) eigenvectors, etc. These methods can effectively extract the effective information of the transformer vibration-acoustic signal, but the number and selection of eigenvalues ​​are a difficult point

If too many eigenvalues ​​are extracted, the sensitivity of the system will be reduced, resulting in a low fault detection rate; The alarm rate is too high

On the other hand, in feature recognition, the methods used in existing research and patents mainly include vector quantization (VQ), hidden Markov model (HMM), support vector machine (SVM), expert analysis system, correlation analysis, etc. , the biggest problem with these methods is that a large number of fault samples must be taken as a premise to construct a reasonable classification model, but the fault samples of transformers are often few. In the case of unbalanced data sets, how to carry out effective fault identification, is the core issue that needs to be resolved urgently

Images