Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

BRISK feature-based partial discharge feature extraction and classification method

A feature extraction and partial discharge technology, applied in the field of image recognition, can solve the problem of insufficient reports of partial discharge characteristics in image recognition technology, and achieve the effects of improving recognition effect, fast operation speed and improving efficiency

Pending Publication Date: 2021-08-20
SHANGHAI JIAO TONG UNIV +1
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, there are not many reports on image recognition technology in advance of partial discharge characteristics

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
  • BRISK feature-based partial discharge feature extraction and classification method
  • BRISK feature-based partial discharge feature extraction and classification method
  • BRISK feature-based partial discharge feature extraction and classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] This embodiment implements a partial discharge feature extraction and classification method based on BRISK features.

[0051] attached figure 1 The partial discharge feature extraction and classification method step diagram based on the BRISK feature, the partial discharge signal image acquisition and processing unit, the image feature extraction unit and the random forest classifier unit in the block diagram can be realized based on a local server, or can be Cloud computing-based service implementation, or both; the specific implementation can be a project based on the Python language.

[0052] as attached figure 1 As shown, a method for extracting and classifying partial discharge features based on BRISK features in this embodiment includes the following steps:

[0053] S1. The partial discharge signal image acquisition and processing unit collects the partial discharge signal image, and preprocesses the partial discharge signal image;

[0054] S2. The partial disc...

Embodiment 2

[0063] This embodiment implements a partial discharge feature extraction and classification method based on BRISK features.

[0064] attached figure 2 It is a flow chart of an embodiment of a partial discharge feature extraction and classification method based on BRISK features, as attached figure 2 As shown, a method for extracting and classifying partial discharge features based on BRISK features in this embodiment includes the following steps:

[0065] Step 1. Collect partial discharge signal images of Z types of faults as a sample set X={X 1 ,X 2 ,...,X t ,...,X Z}, 1t represents the sample set of the t-th class signal; and N tIndicates the total number of partial discharge signal samples of the t-type fault, Indicates the j-th sample in the t-th type of fault, 1≤j t ≤N t .

[0066] Step 2, extract the BRISK features of all partial discharge signal image sample sets X, and obtain the feature set B={B of all sample sets 1 ,B 2 ,...,B i ,...,B Z}, B i Repr...

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 relates to a BRISK feature-based partial discharge feature extraction and classification method. The method comprises the following steps of collecting and sending a partial discharge signal image; carrying out BRISK feature extraction on the partial discharge signal image; obtaining visual frequency square data of the partial discharge signal image; performing normalization processing on the visual frequency histogram data of the partial discharge signal image; dividing the normalized partial discharge signal image feature data into a training set and a test set; performing training to obtain a partial discharge signal image random forest classifier model; and performing fault diagnosis on the partial discharge signal image by using the partial discharge signal image random forest classifier model. The method has the advantages that the classification effect of partial discharge fault types is improved, automatic diagnosis and accurate recognition of partial discharge faults are achieved, and partial discharge image features are effectively extracted and classified under the conditions of different image qualities, pixel sizes and view angle transformation of the images.

Description

【Technical field】 [0001] The invention relates to the technical field of image recognition, in particular to a partial discharge feature extraction and classification method based on BRISK features. 【Background technique】 [0002] The discharge that only occurs in a local area in the insulator, but does not penetrate between the conductors to which the voltage is applied, can occur near the conductor or in other places. This phenomenon is called partial discharge. Partial discharge is not only a symptom of insulation deterioration in electrical equipment, but also a key factor leading to insulation deterioration. The type of partial discharge fault is closely related to the severity of partial discharge, so it is of great significance to realize the effective detection and fault diagnosis of partial discharge in power equipment for risk assessment. Due to the large amount of discharge information, it is difficult to directly analyze it, and there will be a large amount of r...

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): G06K9/00G06K9/62
CPCG06F2218/02G06F2218/08G06F2218/12G06F18/23213G06F18/24323G06F18/214
Inventor 李泽钱勇陈孝信臧奕茗王辉舒博盛戈皞江秀臣
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products