A method of equipment voice recognition based on substation inspection robot

Abstract

The invention discloses an equipment sound identification method based on a transformer substation patrol inspection robot. A patrol inspection robot pickup is used to collect transformer and high-resistance equipment sound in a patrol inspection process, acoustical signal processing and identification technology is used to analyze and identify the equipment sound, and a transformer substation equipment sound identification method based on sound harmonic features and vector quantization is proposed. The equipment sound identification method in the invention extracts 27 harmonic waves from a sound spectral range of 0Hz to 1300Hz as features, establishes a library of a large number of samples, on this basis, codebooks of the transformer and the high-resistance equipment are obtained through LBG algorithm training, finally the two codebooks are used to accurately identify the operating status of the transformer and the high-resistance equipment, the rate of identification can reach 99%, thereby facilitating realization of automated judgment of the operating status of the equipment, and facilitating the progress of unattended operation of the transformer substation.

Description

technical field [0001] The invention relates to an equipment voice recognition method based on a substation inspection robot. Background technique [0002] For a long time, the substation equipment in my country's power industry has mostly adopted manual inspection operations. Under severe weather conditions such as high voltage, ultra-high voltage, and thunderstorms, manual inspections have great safety risks, and the detected data cannot be accurately and timely connected to the management information system, which brings certain hidden dangers to the safe operation of the power grid. [0003] The use of robot technology for substation inspection not only has the flexibility and intelligence of manual inspection, but also overcomes and makes up for the defects and deficiencies in the manual inspection process, which is the development direction of intelligent and unattended substation inspection technology. . Substation equipment inspection robot system uses autonomous o...

AI Technical Summary

Problems solved by technology

The LPCC feature is based on the cepstrum parameters obtained by linear predictive analysis. Although the linear predictive LPC method can be used for sound signal analysis, the LPC method is a parameterized model method. When modeling, it is necessary to know the number of frequency components contained in the signal. , for the operation sound of substation equipment, there are large fluctuations in the included frequency components, and it is difficult to determine the number of frequency components included in the signal

[0007] To sum up, commonly used speech recognition features are not suitable for device sound recognition

Images