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

Partial discharge mode identification method based on SIFT data feature extraction algorithm and BP neural network model

A BP neural network and partial discharge technology, applied in the field of electric power, can solve problems such as inability to quantify analysis and objective evaluation, dependence on fault diagnosis methods, and inability to optimize data characteristics of partial discharge signals.

Active Publication Date: 2022-03-25
ZAOZHUANG POWER SUPPLY COMPANY OF STATE GRID SHANDONG ELECTRIC POWER +2
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above method is limited by the black-box property of the deep learning algorithm itself, which makes it impossible to conduct quantitative analysis and objective evaluation of its feature extraction effect. Therefore, the fault diagnosis method often relies too much on the development of computer science, and cannot be based on the characteristics of partial discharge signal data. Targeted optimization

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
  • Partial discharge mode identification method based on SIFT data feature extraction algorithm and BP neural network model
  • Partial discharge mode identification method based on SIFT data feature extraction algorithm and BP neural network model
  • Partial discharge mode identification method based on SIFT data feature extraction algorithm and BP neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be described in further detail below with reference to the accompanying drawings and specific examples.

[0048] The principle of the present invention is to provide a partial discharge time domain monitoring signal to Y (t), and the partial discharge acquisition signal under the laboratory environment performs S-transform to obtain the characteristic attribute in the time domain and the frequency domain to obtain corresponding time. Spectrogram. First, the S-transform is performed on the timing signal Y (t) to obtain S (τ, f), indicating as follows:

[0049]

[0050]

[0051] In the formula, W (τ-t, f) is a Gauss window, τ is the parameter of the Gaussian window in the time domain, T is the time variable, f is the frequency variable. That is, the Gaussian window function of the S-transform can be changed as the frequency, with this overcomes the defects caused by the traditional time-frequency transform such as a short Fourier transform.

[0...

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 belongs to the technical field of electric power, and discloses a partial discharge mode recognition method based on an SIFT data feature extraction algorithm and a BP neural network model. According to the method, image features of a partial discharge signal time-frequency spectrogram can be extracted, a corresponding feature dictionary is constructed through clustering, and the feature dictionary is visualized and then serves as input of a classifier to achieve partial discharge mode recognition.

Description

Technical field [0001] The present invention relates to the field of electricity technology, and more particularly to a partial discharge mode identification method based on SIFT data feature extraction algorithm and BP neural network model. Background technique [0002] The advantages and disadvantages of electrical equipment insulation performance are directly related to the safety and stable operation of the entire grid, and local discharge can be initially divided into four categories according to the different discharge mechanism and discharge position as an important evaluation index and expression of the electrical equipment. They are tip discharge, suspension discharge, and discharge along the surface discharge and bubbles. Different partial discharge types have also differ from the hazards of electrical equipment insulation performance, so pattern recognition in the local discharge fault diagnosis phase can make more accurate assessment of the current device insulation, ...

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 Applications(China)
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 刘玉娇仲浩李国亮张雨桐谢军谢庆康文文林煜清王坤代二刚杨凤文李森燕重阳韩锋
Owner ZAOZHUANG POWER SUPPLY COMPANY OF STATE GRID SHANDONG ELECTRIC POWER