Power equipment environment noise identification method based on time domain and frequency domain self-similarity

Abstract

The invention discloses a power equipment environment noise identification method based on time domain and frequency domain self-similarity. The method comprises the following steps: firstly, acquiring an operation sound signal of power equipment to be monitored; segmenting the collected audio into minute-level recording samples, setting a proper frame length, framing each sample, and extracting time domain and frequency domain features of each frame; and performing similarity analysis on the features by utilizing a clustering-based similarity analysis method, and considering that the sampleswhich can only be clustered into one class cluster have time domain and frequency domain self-similarity characteristics, otherwise, the samples do not have similarity. When the recording sample has time domain and frequency domain self-similarity, the recording sample is reserved; otherwise, the recording sample is rejected. According to the method, the recording samples without time domain and frequency domain self-similarity noise interference can be effectively recognized and eliminated, effective samples are screened out, and support is provided for subsequent recognition of the operationstate of the power equipment based on sound signals.

Description

technical field [0001] The invention belongs to the field of online monitoring of power equipment status based on sound signals, and in particular relates to a method for identifying environmental noise of power equipment based on time domain and frequency domain self-similarity. Background technique [0002] At present, the maintenance and inspection of power equipment is transitioning from the traditional manual periodic inspection to the condition-based inspection based on condition-based online monitoring. After decades of development, various state-of-the-art online monitoring technologies for temperature, oil and gas, and vibration at home and abroad have become very mature in theory. Among the state online monitoring technologies currently applied in engineering, except for infrared temperature measurement and video monitoring, most of them are contact state monitoring. Contact online monitoring on high-voltage electrical equipment not only needs to solve the problem...

AI Technical Summary

Problems solved by technology

The audible background noise in the operating environment of power equipment has strong uncertainty. Filtering processing based on wavelet analysis is mainly used to eliminate weak noise or deterministic noise where the frequency bands of signal and noise are separated from each other. It is difficult to filter out strong background noise. In addition, there are Difficult to control parameters and easy to weaken effective data

The second is the sound source separation technology, which is used to recover the radiation source signal from the observation signal. There are a lot of researches on separating the body vibration sound from the equipment operation sound containing environmental noise, but the actual environmental noise and the vibration state of the body may change dynamically. However, this method is still difficult to weaken the effective data

[0005] Different from the environment where the substation equipment is located, the power distribution equipment is generally placed in the ring main unit or the power distribution room or even near the electric pole on the side of the road. It operates in an open and harsh environment, and the traditional method based on filtering or sound separation is difficult. Adapt to complex and changeable environmental noise

Due to the inability to accurately identify the interference of environmental noise, the application of sound-based online monitoring technology for power distribution equipment is greatly limited.

Images