Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Decision tree identification method based on sulfur hexafluoride partial discharge

A sulfur hexafluoride gas, partial discharge technology, applied in character and pattern recognition, measurement of electricity, measurement of electrical variables and other directions, can solve the problems of equipment electric field distortion, metal burrs, loose parts or poor contact, etc., to improve the recognition rate , the effect of improving processing efficiency

Inactive Publication Date: 2018-03-20
STATE GRID CHONGQING ELECTRIC POWER CO ELECTRIC POWER RES INST +2
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, SF 6 Gas insulated equipment (referred to as SF 6 Electrical equipment, such as gas-insulated combined electrical appliances (GIS, gas-insulated circuit breakers GCB, gas-insulated transformers GIT, and gas-insulated lines or pipelines GIL, etc.), will inevitably appear in the process of manufacturing, transportation, installation, maintenance and operation. A variety of insulation defects, such as metal burrs on the conductor, loose parts or poor contact, air gaps formed by the stripping of the conductor and the supporting insulator, remnants after overhaul, and metal particles in the cavity, etc., will cause SF 6 Different degrees of insulation defects are formed inside the equipment, which leads to distortion of the electric field inside the equipment, and then produces partial discharge (PD)

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
  • Decision tree identification method based on sulfur hexafluoride partial discharge
  • Decision tree identification method based on sulfur hexafluoride partial discharge
  • Decision tree identification method based on sulfur hexafluoride partial discharge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0063] Example: such as Figure 1 to Figure 3 Shown; A kind of decision tree identification method based on partial discharge of sulfur hexafluoride gas, it comprises: described decision tree forms process as follows:

[0064] S1: Determine whether the training sample is empty, if not, go to step S2; otherwise, go to step S6;

[0065] S2: Judging that the sample in the node has only one category, if not, go to step S3; otherwise, go to step S6;

[0066] The judgment process of the step S2 also includes:

[0067] S21: Calculate the information gain rate under each attribute in the sample;

[0068] S22: Find the attribute A with the largest information gain rate.

[0069] S3: Determine whether the attribute A of the information gain rate in the sample is a continuous quantity, if not, go to step S4; otherwise, go to step S6;

[0070] S4: Find the segmentation threshold of attribute A;

[0071] S5: grow a new node according to attribute A, and return to step S1;

[0072] S6...

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 decision tree identification method based on sulfur hexafluoride (SF6) partial discharge. The method includes a decision tree formation process as follows: S1, determining whether the training samples are empty, going to S2 if the training samples are empty, otherwise, going to S6; S2, determining whether there is only one category of samples in a node, going to S3 if there is more than one category of samples in the node, otherwise, going to S6; S3, determining whether the attribute A of the information gain ratio in the samples is continuous, going to S4 if the attribute A of the information gain ratio in the samples is not continuous, otherwise, going to S6; S4, finding the segmentation threshold of the attribute A; S5, growing a new node according to the attribute A, and returning to S1; S6, taking the new node as a leaf node, and naming the new node as a corresponding category; and S7, forming a decision tree. The beneficial effect achieved is that safe and reliable operation of SF6 devices is ensured, the ability to differentiate various defects is improved, and the efficiency of insulation fault processing is improved. The pattern of partial discharge acquired is identified by using the decision tree, and the identification rate of partial discharge is further improved.

Description

technical field [0001] The invention relates to the technical field of sulfur hexafluoride decomposition, in particular to a decision tree identification method based on partial discharge of sulfur hexafluoride gas. Background technique [0002] Sulfur hexafluoride (SF 6 ) gas is widely used in gas-insulated equipment due to its excellent insulation and arc extinguishing properties. However, SF 6 Gas insulated equipment (referred to as SF 6 Electrical equipment, such as gas-insulated combined electrical appliances (GIS, gas-insulated circuit breakers GCB, gas-insulated transformers GIT, and gas-insulated lines or pipelines GIL, etc.), will inevitably appear in the process of manufacturing, transportation, installation, maintenance and operation. A variety of insulation defects, such as metal burrs on the conductor, loose parts or poor contact, air gaps formed by the stripping of the conductor and the supporting insulator, remnants after overhaul, and metal particles in th...

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
IPC IPC(8): G01R31/12G06K9/62
CPCG01R31/1254G06F18/2155
Inventor 邱妮何国军姚强苗玉龙唐炬曾福平杨华夏籍勇亮胡晓锐宫林张施令
Owner STATE GRID CHONGQING ELECTRIC POWER CO ELECTRIC POWER RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products