Unlock instant, AI-driven research and patent intelligence for your innovation.

A large transformer fault detection method based on sound features

A technology for transformer faults and detection methods, which is applied to instruments, measuring electricity, measuring devices, etc., can solve problems such as reducing the economic cost of power supply companies, difficulty in detecting related latent faults, and inability to realize online transformer detection, and achieve cost Low, easy-to-achieve, easy-to-distinguish effects

Active Publication Date: 2021-10-01
UNIV OF SCI & TECH OF CHINA
View PDF18 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the existing method is only a protection method after a fault occurs, which will reduce the quality of power consumption and increase the economic cost of the power supply company
Moreover, this protection method is difficult to detect related latent faults, and cannot realize effective online detection of transformers.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A large transformer fault detection method based on sound features
  • A large transformer fault detection method based on sound features
  • A large transformer fault detection method based on sound features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The technical solutions in the embodiments of the present invention will be clearly and completely described below in combination with the specific content of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention. The content not described in detail in the embodiments of the present invention belongs to the prior art known to those skilled in the art.

[0017] Such as figure 1 As shown, the embodiment of the present invention provides a large-scale transformer fault detection method based on sound features. After pre-training to obtain a sound dictionary containing large-scale transformer normal operation and various faults, it is detected according to the following steps:

[0018] ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a large-scale transformer fault detection method based on sound features. After pre-training to obtain a sound dictionary containing the normal operation of large-scale transformers and various faults, the detection is performed according to the following steps: Step 1, through the large-scale transformer to be detected. The sound pickup device collects the sound from a large transformer; step 2, extract the corresponding amplitude and real part after transforming the collected sound, project the amplitude and real part to the sound dictionary respectively, and obtain the sparse representation of normal operation and various faults Coefficients, use the obtained normal operation and various fault sparse representation coefficients to reconstruct the corresponding sound, and calculate the error of the reconstructed corresponding sound relative to the collected sound; step 3, according to the size of the error, determine the type of fault of the large transformer. This method can maintain a good detection ability for normal operation and various faults, not only has a low cost, but also can realize all-weather real-time online detection of large transformer faults, which is convenient for the power industry to realize.

Description

technical field [0001] The invention relates to the field of large-scale transformer fault detection, in particular to a large-scale transformer fault detection method based on sound features. Background technique [0002] Nowadays, the demand for electricity continues to increase, and the quality of electricity has also received widespread attention. The stable supply of electricity is also closely related to the national economy. The stable supply of power requires good protection of transformers, timely confirmation and elimination of faults. [0003] At present, the protection method of the transformer is mainly carried out relay protection through electrical parameters such as voltage and current when fault occurs. [0004] However, the existing method is only a protection method after a failure occurs, which will reduce the quality of power consumption and increase the economic cost of the power supply company. Moreover, this protection method is difficult to detect ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G01R31/00G01H17/00G06K9/62
CPCG01R31/00G01H17/00G06F18/28
Inventor 叶中付
Owner UNIV OF SCI & TECH OF CHINA