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

Predictive maintenance method and system for transformer oil chromatography on-line monitoring device

A monitoring device and transformer oil technology, applied in measuring devices, predictions, neural learning methods, etc., can solve problems such as harsh operating environment, low operating life, and high professional requirements for personnel, so as to improve the level of operational reliability, early detection, and timely The effect of overhaul

Pending Publication Date: 2020-11-27
STATE GRID JIANGSU ELECTRIC POWER CO ELECTRIC POWER RES INST +2
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the operating life of the current oil chromatography on-line monitoring device is much lower than that of the power transformer body, and most of the oil chromatography on-line monitoring devices are installed outdoors, the operating environment is harsh, and there are many The accuracy of oil chromatographic analysis and even data distortion caused by factors such as oil chromatographic analysis have greatly reduced the reliability and credibility of oil chromatographic monitoring data.
In addition, the on-site regular calibration of the oil chromatography device has constraints such as complicated instrument operation and high professional requirements for personnel, which makes it extremely difficult to conduct a comprehensive regular calibration of the oil chromatography on-line monitoring device after on-site operation in practice. Therefore, it is urgent to Study on Predictive Maintenance of On-line Oil Chromatography Monitoring Device

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
  • Predictive maintenance method and system for transformer oil chromatography on-line monitoring device
  • Predictive maintenance method and system for transformer oil chromatography on-line monitoring device
  • Predictive maintenance method and system for transformer oil chromatography on-line monitoring device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0119] The gas components detected by the current oil chromatography online monitoring device include H 2 、CH 4 、C 2 h 4 、C 2 h 6 、C 2 h 2 , CO, CO 2 , 7 characteristic gases, but most of the existing online monitoring devices can only monitor the first 5 gases. In this embodiment, a total of 540,000 effective records of 354 oil chromatography online monitoring devices in a province were collected from 2007 to 2019 (removing obvious abnormal data such as data interruption, zero value, and infinity), and a sample library was established by using the sliding pane method. Sliding pane length = 30 days, step size = 5 days, such as Figure 6 As shown, a total of 32774 effective training samples were obtained.

[0120] The computer used in this embodiment is equipped with 8-core Xeon CPU, GTX1080TI graphics card and 32G memory, retrieves 441 pieces of relevant oil chromatography online monitoring and verification record data from the PMS database, and marks 4541 samples acc...

Embodiment 3

[0125] On the basis of Example 1, in order to obtain the best DBN structure and training parameters, this example compares the evaluation effect of the model on the oil chromatographic monitoring data under different Boltzmann machine layers and training cycles, so that according to The actual characteristics of the input samples construct the optimal DBN model.

[0126] see Figure 11 , the recognition accuracy of the DBN model tends to converge after the number of network layers reaches 4 and the training cycle reaches 250. If the number of model layers or training cycle is increased at this time, the training and testing time will be increased, which will affect the calculation efficiency. Therefore, for the actual situation of the data in this embodiment, a 4-layer DBN model is selected, and the number of training cycles is 250.

[0127] In order to verify the effectiveness of the oil chromatographic monitoring data of the method of the present invention, this embodiment ...

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 predictive maintenance method and system for a transformer oil chromatography online monitoring device. Carrying out data fitting and empirical mode analysis on the oil chromatogram by adopting B-EMD; obtaining oil chromatography effectiveness evaluation parameters; an oil chromatography data validity analysis network based on multi-dimensional DBN is adopted; according to the method, the modal characteristics of the oil chromatography data are subjected to effectiveness evaluation, and finally, comprehensive evaluation results of the effectiveness of the oil chromatography data are obtained by comprehensively weighting different dimensions through the comprehensive weight factor sorting network, so that the operation reliability evaluation of the oil chromatography online monitoring device is realized, and planned maintenance can be carried out in a targeted manner.

Description

technical field [0001] The invention belongs to the field of fault diagnosis of power equipment, and in particular relates to a predictive maintenance method for a transformer oil chromatography online monitoring device based on multi-scale deep feature learning. Background technique [0002] As the most critical equipment of the power system, the reliability of the power transformer is directly related to the operation safety of the power system. At present, dissolved gas analysis in transformer oil (dissolved gas analysis, DGA) (referred to as oil chromatographic analysis), as an effective means of monitoring and diagnosing transformer defects and latent faults, has been widely used in power transformer condition monitoring, and provincial power grids have also deployed A large number of oil chromatography online monitoring devices can analyze the composition and content of dissolved gases in power transformer oil online, and evaluate the operation status of transformers t...

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): G06Q10/04G06Q10/00G06N3/04G06N3/08G01N30/00
CPCG06Q10/04G06Q10/20G06N3/084G01N30/00G06N3/045
Inventor 贾骏陶风波胡成博黄强路永玲秦建华刘子全王真徐阳
Owner STATE GRID JIANGSU ELECTRIC POWER CO ELECTRIC POWER RES INST
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