Acoustic fingerprint early warning device for large power transformer

Abstract

The invention discloses an acoustic fingerprint early warning device for a large power transformer, and the device is characterized in that an acoustic signal detection module is used for detecting the operation state of the transformer, monitoring the variable of a fault physics model, and comparing the variable with the calculated value of the model to obtain the sound data of the power transformer; the sound signal analysis module is used for analyzing statistical law characteristics of target source signals, separating source signals from collected sound data, summarizing and gradually searching an optimal separation matrix in the separation process, and enabling the separated signals to be mutually independent so as to extract target sound signals in a noise environment; the method is used for adding a limited number of white noise sequences into signals, inhibiting modal aliasing of EMD and eliminating white noise by averaging decomposition results of limited numbers, a fingerprint model dynamically extracts monitoring data in the monitoring process to form transformer noise fingerprints in a certain period of time, the noise fingerprints are visually displayed through a three-dimensional model and a pseudo-color map, and the transformer noise fingerprints are displayed in a real-time mode through the three-dimensional model and the pseudo-color map. And the equipment state can be intuitively analyzed conveniently.

Description

technical field [0001] The invention relates to the field of transformer monitoring, in particular to an acoustic fingerprint early warning device for large power transformers. Background technique [0002] At present, among the numerous monitoring methods of transformers, non-electricity monitoring methods represented by noise, temperature, and vibration are widely used because they do not have direct electrical or magnetic contact with the equipment under test and have little impact on the safe operation of the power system. . Since the sound is caused by the vibration of the particle, the main source of the noise of the transformer is the vibration of the oil tank, winding, iron core and fan of the cooling device, so the insulation condition inside the transformer can be judged by detecting the vibration of the transformer box. [0003] Usually the transformer operates in an alternating electromagnetic environment, the periodic changes of the electric field and the magne...

AI Technical Summary

Problems solved by technology

[0003] Usually the transformer operates in an alternating electromagnetic environment, the periodic changes of the electric field and the magnetic field will cause the transformer core and winding to vibrate periodically, these internal vibrations are transmitted to the transformer oil tank through multiple paths, and finally the vibration through the oil tank is manifested as noise , because the data obtained by the vibration detection method usually cannot clearly represent the fault information of the electrical equipment, and the vibration parameters are difficult to detect, and the signal strength obtained is weak and messy, it is difficult to judge the fault type and information of the equipment in time

Images