Power transformer fault prediction and diagnosis method and system based on audio characteristics

Abstract

The invention provides a power transformer fault prediction and diagnosis method based on audio characteristics. The method specifically comprises the steps that S1, detecting effective signals of power transformer audio data under the noise background based on chaotic oscillators; S2, calculating a logarithm energy spectrum on the nonlinear Mel scale to serve as a characteristic quantity of the audio signal of a power transformer; S3, calculating a principal component of the audio signal characteristic quantity of the power transformer by adopting a principal component analysis method; S4, optimizing the optimal hyper-parameter training power transformer fault prediction model of the vector machine algorithm by adopting a quantum particle swarm optimization algorithm; and S5, if the powertransformer is in a fault state, adopting a 1 / 3 octave algorithm to extract the fault characteristic frequency range amplitude, comparing the fault characteristic frequency range amplitude with an expert experience rule base, and predicting / obtaining the fault type of the power transformer. According to the method, the identification precision of power transformer operation state fault predictioncan be improved, and the calculation amount is reduced; fault judgment can be carried out based on other measurement data or infrared images.

Description

technical field [0001] The invention belongs to the technical field of power transformer fault diagnosis, and in particular relates to a power transformer fault prediction and diagnosis method and system based on audio features. Background technique [0002] In the power system, power transformers play an important role in voltage conversion, power distribution, voltage regulation, isolation, etc., which are related to the safe, stable, reliable and economical operation of the power system. The power transformer has a complex structure, mainly composed of iron core, winding, oil tank, oil pillow, insulating bushing, tap, etc., and it is generally installed outdoors, and the working environment is harsh. As the running time increases, failures will inevitably occur. The failure involves Windings, main insulation, leads, tap changers, bushings, etc. According to DL / T573-95 "Guidelines for Maintenance of Power Transformers" and the operating environment of power transformers, ...

AI Technical Summary

Problems solved by technology

[0007] (1) Most of the extraction of sound features of power transformers use frequency domain analysis methods, or use wavelet transform, Hilbert-Huang transform, etc. to extract some components of the reaction fault, instead of using cepstrum for reference to the sound recognition principle of human ear , Mel cepstrum angle for further analysis;

[0008] (2) The structure of the power transformer is complex, the operating environment is harsh, and the background noise cannot be ignored. Especially when the energy of the background noise is large, the sound component that reflects the fault characteristics of the power transformer may be submerged. However, the existing transformer fault prediction based on sound signals Most of the diagnostic methods only use a simple filtering algorithm to filter out the noise;

[0009] (3) Due to the limitations of existing sound signal feature extraction methods, artificial intelligence methods such as neural networks and Support VectorMachine (SVM) are not yet common in power transformer fault prediction based on sound signals

Images