Transformer expansion tank intelligent monitoring method and system based on image recognition

A transformer oil and image recognition technology, applied in the field of blockchain consensus, can solve problems such as abnormal vibration, reduced equipment reliability, and reduced insulation performance of cooling oil, so as to achieve repeated recycling, improve accuracy, and increase gaps Effect

Inactive Publication Date: 2021-12-07
HOHAI UNIV CHANGZHOU
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The volume change of the cooling oil in the oil tank will cause the change of the liquid level of the oil conservator, and the internal pressure will be released by the gas exchange with the external air through the oil conservator respirator. Air, if the humidity of the dry silica gel in the respirator is saturated, the air bag inside the oil conservator will bring in moisture from the outside due to the exchange of air and penetrate into the transformer cooling oil, resulting in a decrease in the insulation performance of the cooling oil, and prone to transformer insulation short-circuit accidents, and the respirator due to Dry silica gel absorbs water and expands to cause breathing blockage and rupture of explosion-proof membranes, as well as excessive temperature of hot spots of windings leading to equipment reliability reduction and internal device mechanical failures causing vibration abnormalities. These phenomena can all be reflected in the comprehensive performance status of power transformers.

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
  • Transformer expansion tank intelligent monitoring method and system based on image recognition
  • Transformer expansion tank intelligent monitoring method and system based on image recognition
  • Transformer expansion tank intelligent monitoring method and system based on image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Such as Figure 1-10 As shown, in the first aspect, the present invention provides a method for intelligent monitoring of transformer oil conservator based on image recognition, including:

[0059] The visual monitoring subsystem collects the image of the desiccant in the ventilator online;

[0060] The processor removes bright and dark noises from the collected desiccant image; the method for removing bright and dark noises from the desiccant image includes:

[0061] The desiccant image corrosion treatment, the calculation formula is:

[0062] AΘB={x|(B) x ∈A}

[0063] The desiccant image retains pixels whose calculation result values ​​are all "1";

[0064] The expansion process is performed on the corroded desiccant image, and the calculation formula is:

[0065]

[0066] Keep the pixels whose calculation results are all "0"; in the formula, A is the desiccant image; B is the convolution kernel image.

[0067] The function f(x,y) represents the desiccant ima...

Embodiment 2

[0088] A transformer oil conservator intelligent monitoring system based on image recognition. The transformer oil conservator intelligent monitoring system can be used to implement the method steps described in Embodiment 1. The transformer oil conservator intelligent monitoring system uses a 220VAC to 5VDC power supply module. The transformer oil conservator The intelligent monitoring system includes a controller, a visual monitoring subsystem, a dehumidification subsystem, a color LCD screen for displaying desiccant images, and a memory card for storing detection data and calculation data; the visual monitoring subsystem includes a visible light camera, so The visible light camera is electrically connected with the input end of the controller.

[0089] The visible light camera uses a CMOS image sensor module to collect desiccant images. The internal structure of the CMOS image sensor module is as follows: Figure 11 As shown; the internal structure of the CMOS image sensor ...

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 transformer expansion tank intelligent monitoring method and system based on image recognition in the field of blockchain consensus. A visual monitoring subsystem is used for collecting a drying agent image in a breathing machine on line; a processor is used for removing the bright and dark noisy points from the acquired drying agent image, performing color segmentation on the acquired drying agent image, calculating a color ratio in the drying agent image, and judging whether the humidity in the drying agent is greater than a set threshold value or not according to the color proportion; when the humidity of the drying agent is greater than a threshold value, the controller controls the dehumidification subsystem to dehumidify the drying agent; when the humidity of the drying agent is smaller than a threshold value, the controller closes the dehumidification subsystem. According to the machine vision technology and the image processing technology, image collection and image processing are conducted on the respirator, the proportion of the silica gel pink blue area in the respirator is calculated and converted into the humidity value, and then whether the drying function fails or not and whether blockage occurs or not are judged.

Description

technical field [0001] The invention belongs to the technical field of block chain consensus, and specifically relates to an efficient Internet of Things block chain PBFT consensus architecture. Background technique [0002] With the rapid growth of electricity demand, the power system is also constantly expanding, and the number of power transformers is increasing at a rate of hundreds of thousands every year. In the power supply system, the power transformer is the key equipment connecting the power supply system and end customers. Its step-up and step-down functions facilitate the rational transmission, distribution and use of electric energy. Common power transformers include dry-type transformers and oil-immersed transformers. In order to prevent accidents such as insulation breakdown caused by internal moisture in oil-immersed power transformers, oil-immersed power transformers often use sealed oil tanks, and the iron core and windings are immersed in full In the oil ...

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): G06T7/00G06T7/11G06T7/90G06T5/00G06T5/30G06K9/62H01F27/14
CPCG06T7/0004G06T7/11G06T7/90G06T5/002G06T5/30H01F27/14G06T2207/10024G06T2207/30232G06F18/23213
Inventor 张金波陈雅雯马新科叶金涛李彭鑫黄青青姜毅
Owner HOHAI UNIV CHANGZHOU
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