Power transformer state prediction method based on machine learning and neural network

A power transformer and neural network technology, applied in the field of prediction, can solve problems such as high technical cost and time cost, high accident rate, and singular value of sampling data, and achieve the effect of improving safety reliability and accuracy

Pending Publication Date: 2021-03-30
HARBIN UNIV OF SCI & TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Although the transformer itself has a variety of protective measures, such as lightning arresters, gas, differential and grounding protection, the accident rate is still very high due to the complex insulation structure inside the transformer, uneven distribution of internal electric and thermal fields, and long-term uninterrupted work. high
The online monitoring technology of transformer oil chromatography is the basis of fault diagnosis and online monitoring. However, the technical cost and time cost of online monitoring technology are high, the sampling data often has problems such as singular values ​​and missing values, and the detection cycle of dissolved gas in oil is too long long, unable to achieve online monitoring

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
  • Power transformer state prediction method based on machine learning and neural network
  • Power transformer state prediction method based on machine learning and neural network
  • Power transformer state prediction method based on machine learning and neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042]The purpose of the present invention is to propose a power transformer state prediction method based on machine learning and neural network, the prediction method can effectively predict the future operating state of the transformer, and use the transformer state prediction method to timely check the predicted faults to ensure Safety and stability of transformer operation.

[0043] Based on above purpose, the present invention proposes a kind of power transformer state prediction method based on machine learning and neural network, and it comprises steps:

[0044] Step 1, train the RP neural network and deep belief network;

[0045] Input the concentration value of the characteristic gas in the historical data of transformer oil chromatography into the RP neural network and the deep confidence network for training, so that the output of the RP neural network and the deep confidence network is the future concentration value and future concentration ratio of the characteri...

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 power transformer state prediction method based on machine learning and a neural network. The method comprises the following steps: (1) training an RP neural network and a deep belief network; (2) outputting a future concentration value and a future concentration ratio of a to-be-identified transformer characteristic gas by utilizing the trained RP neural network and thedeep belief network; and (3) predicting the future operation state of the transformer based on the future gas concentration ratio. The future operation state of the transformer can be effectively predicted; the operation state of the transformer is predicted, potential threats of the transformer can be perceived in time, and the fault development trend of the transformer is mastered; and great significance is achieved for improving the equipment operation safety and reliability.

Description

technical field [0001] The invention relates to a prediction method, in particular to a state prediction method for a transformer. Background technique [0002] Although the transformer itself has a variety of protective measures, such as lightning arresters, gas, differential and grounding protection, the accident rate is still very high due to the complex insulation structure inside the transformer, uneven distribution of internal electric and thermal fields, and long-term uninterrupted work. high. The online monitoring technology of transformer oil chromatography is the basis of fault diagnosis and online monitoring. However, the technical cost and time cost of online monitoring technology are high, the sampling data often has problems such as singular values ​​and missing values, and the detection cycle of dissolved gas in oil is too long Long, unable to achieve online monitoring. Transformer faults are mostly irreversible faults. Even if the transformer is disconnecte...

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): G06Q10/04G06N3/08G06K9/62G06Q50/06
CPCG06Q10/04G06N3/084G06Q50/06G06F18/214
Inventor 田伟稼吕艳玲申昱博
Owner HARBIN UNIV OF SCI & TECH
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap