Supercharge Your Innovation With Domain-Expert AI Agents!

Defect detection method for porcelain post insulators based on normal single-class ensemble model

An integrated model, normal single-class technology, applied in processing detection response signals, using sound waves/ultrasonic waves/infrasonic waves to analyze solids, etc., can solve missed judgments, misjudgments, size, shape and location difficulties, power grid operation risks and Economic loss and other issues, to achieve the effect of easy collection

Active Publication Date: 2017-01-04
STATE GRID CORP OF CHINA +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in actual work, the size, shape and location of cracks, slag inclusions, interlayers, and pores on porcelain post insulators are difficult to determine in advance, and external forces and environmental factors are even more unpredictable, so it is almost impossible to exhaustively list out all the sound waves of the fault. Relying on the above methods may cause missed or misjudgment during defect detection, resulting in grid operation risks and economic losses

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
  • Defect detection method for porcelain post insulators based on normal single-class ensemble model
  • Defect detection method for porcelain post insulators based on normal single-class ensemble model
  • Defect detection method for porcelain post insulators based on normal single-class ensemble model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] Such as figure 1 As shown, the present invention provides a vibroacoustic defect detection method and identification method for porcelain post insulators based on a normal single-class integrated model, which specifically includes the following steps:

[0019] The first step is to collect data and construct a data set of normal state of porcelain post insulators.

[0020] Porcelain post insulator normal state data set, contains the following fields

[0021] The model of the Field 1 porcelain post insulator corresponds to the specific manufacturer and model of a specific porcelain post insulator.

[0022] Field 2 Excitation Rod Hitting Position, where the excitation rod of the percussion device is placed.

[0023] Field 3 receiving rod listening position, where the receiving rod of the percussion device is placed.

[0024] Field 4 is a set of acoustic wave sampling data in normal state, which corresponds to the acoustic wave data of the porcelain post insulator in nor...

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

A defect detection method for porcelain post insulators based on the normal single-class integrated model, including constructing a data set of normal state of porcelain post insulators, each record in the data set corresponds to the model of a specific porcelain post insulator, the tapping position of the excitation rod, the listening position of the receiving rod, A set of sound wave sampling data in normal state, sound wave attribute description vector table, and state judgment single-class integrated model; find the corresponding data in the normal state data set according to its model, and follow the specified excitation rod tapping position and receiving rod listening position in the data set Knock the porcelain post insulator to obtain the acoustic wave data, convert the sound wave into vector attribute data according to the division of m time periods and n frequency bands, and then use the normal single-class integration model to judge and obtain the fault condition of the porcelain post insulator. The invention collects the acoustic wave data of the porcelain post insulator in normal state more easily and cheaply, does not need to artificially destroy the insulator to find defect data, has more practical application value, and is more stable and efficient.

Description

technical field [0001] The invention relates to the field of power grid equipment maintenance, in particular to the detection and quality evaluation of porcelain post insulator defects in the power grid. Background technique [0002] Porcelain post insulator is an important part of power grid operation, which plays the role of supporting wire and insulating. Since the insulator is an electric porcelain product sintered at high temperature, if the formula is improper during the production process and the raw materials are not mixed uniformly during the process, it is easy to form internal defects of the porcelain part. In addition, it may also withstand the mechanical load and harsh environment during operation for a long time. , These problems are likely to cause failure and fracture of porcelain post insulators, endangering the safe operation of the power grid. Therefore, it is very important to strengthen the inspection and quality evaluation of the porcelain post insulat...

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): G01N29/04G01N29/48
Inventor 侯安家赵殿全林乐亭
Owner STATE GRID CORP OF CHINA
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More