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

Construction method and application of GIL mechanical fault diagnosis model, computer readable medium and fault diagnosis system

A technology of mechanical failure and diagnosis model, which is applied in the testing and calculation of computer components and mechanical components, etc., which can solve problems such as equipment disintegration, manpower, material and financial resources, and delay in maintenance process, achieving high accuracy and improving feature learning Good effect, noise reduction effect

Pending Publication Date: 2022-04-15
国网河南省电力公司超高压公司 +2
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the long length of the GIL, the location of the fault cannot be accurately located in a timely manner during troubleshooting and daily maintenance monitoring. The equipment needs to be dismantled during maintenance, which consumes a lot of manpower, material resources, and financial resources. At the same time, it will delay the maintenance process and cause unnecessary 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
  • Construction method and application of GIL mechanical fault diagnosis model, computer readable medium and fault diagnosis system
  • Construction method and application of GIL mechanical fault diagnosis model, computer readable medium and fault diagnosis system
  • Construction method and application of GIL mechanical fault diagnosis model, computer readable medium and fault diagnosis system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] Embodiment 1: a kind of construction method of GIL mechanical fault diagnosis model, comprises the following steps:

[0023] A vibration sensor is installed on the GIL shell. When the first type of mechanical failure of the GIL occurs in real or simulated GIL, the GIL vibration-induced variable electrical signal output by the vibration sensor is obtained in the early stage of the first type of mechanical failure of the GIL. Generally, the more samples trained by the deep residual shrinkage network, the better its effectiveness. Therefore, there are multiple groups of GIL vibration-induced variable electric signals, which come from multiple GILs that have the first type of mechanical failure of GIL. In the early stage of the first type of mechanical failure in GIL, it refers to the stage in which the abnormality can be detected by using the chaos theory algorithm to process the noise-reduced signal.

[0024] One training sample is obtained for each set of GIL vibration-i...

Embodiment 2

[0051] Embodiment 2: the application of the GIL mechanical fault diagnosis model obtained in embodiment 1 comprises the following steps:

[0052] Receive the electrical signal output by the vibration sensor installed on the GIL;

[0053] The electrical signal is processed for noise reduction; the signal noise reduction method is: use variational mode decomposition GIL vibration-induced variable electric signal, remove the IMF component of the noise segment and reconstruct the signal, and use the wavelet packet threshold algorithm for noise reduction processing and reconstruction after the signal.

[0054] The chaos theory algorithm is used to perform early fault diagnosis on the signal after noise reduction, and if no abnormality is detected, the first diagnosis conclusion is output. The first diagnostic conclusion is: during the GIL detection period corresponding to the currently processed electrical signal, the GIL has no GIL metal shell faults and GIL insulator rupture fau...

Embodiment 3

[0064] Embodiment 3: A computer-readable medium storing a GIL mechanical fault diagnosis program, the GIL mechanical fault diagnosis program includes an input module, a signal noise reduction module, an early fault detection module, a fault diagnosis module and an output module, and the input The module is used to receive the GIL vibration acceleration signal. The signal noise reduction module uses the variational mode to decompose the GIL vibration acceleration signal, and reconstructs the signal after removing the IMF component of the noise segment, and uses the wavelet packet threshold algorithm to denoise the reconstruction After the signal; the early fault detection module uses the Duffin oscillator algorithm to carry out early fault diagnosis on the signal after noise reduction, if no abnormality is detected, the first diagnosis conclusion is generated, and if abnormality is detected, the fault diagnosis module is run; The fault diagnosis module receives the noise-reduced...

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 construction method and application of a GIL mechanical fault diagnosis model, a computer readable medium and a fault diagnosis system, and the method comprises the steps: obtaining GIL vibration-induced variable electric signals at the early stage of a GIL first mechanical fault, the GIL vibration-induced variable electric signals are divided into a plurality of groups, and the GIL vibration-induced variable electric signals are respectively from a plurality of GIL with the GIL first mechanical fault; carrying out noise reduction processing on the GIL vibration-induced variable electric signals, and constructing training set samples by using the processed signals; constructing a deep residual shrinkage network initial model, and training the deep residual shrinkage network initial model by using the training set sample to obtain a GIL mechanical fault diagnosis model for diagnosing a first type of GIL mechanical fault; wherein the GIL first type mechanical fault is a GIL metal shell pseudo soldering fault or a GIL insulator fracture fault. And GIL mechanical fault diagnosis can be realized by using the method.

Description

technical field [0001] The present invention relates to the technical field of UHV GIL fault diagnosis, in particular to a construction method of a GIL mechanical fault diagnosis model and its application, a computer-readable medium storing a GIL mechanical fault diagnosis program, and a GIL mechanical fault diagnosis system. Background technique [0002] The common mechanical failures of UHV GIL (gas insulated transmission lines) include metal shell welding failures and insulator rupture failures. Due to the long length of the GIL, the location of the fault cannot be accurately located in a timely manner during troubleshooting and daily maintenance monitoring. The equipment needs to be dismantled during maintenance, which consumes a lot of manpower, material resources, and financial resources. At the same time, it will delay the maintenance process and cause unnecessary Economic losses. [0003] Patent document CN108168682A discloses a GIL fault online monitoring system ba...

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): G06K9/00G06N3/04G01M13/00
Inventor 汤会增张孝远张利巩持恒肖子航王恩钢曹永欣王育淼张金浩杨立新候交通李津黄健金程朝磊周文宣杨竣博
Owner 国网河南省电力公司超高压公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com