Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Artificial intelligence-based distribution transformer anomaly analysis and early warning method

An artificial intelligence and abnormal technology, applied in the direction of prediction, instrument, character and pattern recognition, etc., to achieve the effect of reducing complaints, improving power supply reliability, and reliable data assurance

Pending Publication Date: 2021-03-12
STATE GRID HENAN ELECTRIC POWER COMPANY ZHENGZHOU POWER SUPPLY +2
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is: to overcome the deficiencies of the existing technology, use multi-dimensional data analysis and mining technology, construct an evaluation algorithm based on TOPSIS, construct an evaluation model, realize effective monitoring of "heavy overload" of distribution transformers, and pre-evaluate distribution The possibility of "heavy overload" in the power grid can improve the reliability of power supply, improve the operation efficiency and lean management level of the power grid, and the analysis and early warning method of distribution transformer abnormality based on artificial intelligence

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
  • Artificial intelligence-based distribution transformer anomaly analysis and early warning method
  • Artificial intelligence-based distribution transformer anomaly analysis and early warning method
  • Artificial intelligence-based distribution transformer anomaly analysis and early warning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0028] Example: see figure 1 , figure 2 , image 3 , Figure 4 , Figure 5 , Figure 6 , Figure 7 and Figure 8 .

[0029] The specific steps of the distribution transformer abnormality analysis and early warning method based on artificial intelligence are as follows: 1. Collect the distribution transformer overload record data through corresponding sensors and perform preprocessing; 2. Based on the correlation analysis method of mutual information coefficient Select the key factors affecting the abnormality of the public variable from the data information; 3. Through multi-dimensional analysis methods, analyze the change of overload under different factors, and obtain the weight of each factor affecting the overload of the public variable; 4. Use the K-Means algorithm to analyze the overload Common change clustering analysis, get overload common change clustering results, select the best overload common change characteristics and types; 5. Based on the TOPSIS evaluat...

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 an artificial intelligence-based distribution transformer anomaly analysis and early warning method, which comprises the following steps: performing sensitivity analysis on associated factors such as air temperature, capacity and operation age limit, constructing a TOPSIS-based evaluation algorithm by using a multi-dimensional data analysis and mining technology, constructing an evaluation model, evaluating and scoring each distribution transformer by using the TOPSIS evaluation algorithm, estimating the distribution transformer overload occurrence probability, issuingan advanced early warning notification to a professional department, providing differentiated operation and maintenance suggestions for abnormal distribution transformers according to the severity reflected by scoring, providing big data support for lean operation and maintenance of the distribution transformers, thus realizing post-event governance to pre-event pre-control, improving the advancedmonitoring, early warning and operation and maintenance level of the distribution transformers, and reducing the distribution transformer overload rate.

Description

Technical field: [0001] The invention relates to the field of power supply and transformation maintenance, in particular to an artificial intelligence-based analysis and early warning method for distribution transformer abnormality. Background technique: [0002] With the continuous development of social economy and the rapid improvement of people's lives, the demand for electricity in the whole society continues to increase, especially during the summer and winter peak load periods, distribution transformers (low voltage, three-phase imbalance) lead to heavy overload of transformers Frequently, the resulting complaints from residents are also high. How to solve the abnormal operation of distribution transformers, avoid equipment accidents, improve power supply quality, power supply reliability and high-quality service levels is particularly important. [0003] In the prior art, the distribution transformers are regularly inspected to find out the problems and repair them. 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): G06Q10/04G06Q10/06G06Q10/00G06Q50/06G06K9/62
CPCG06Q10/04G06Q10/0639G06Q10/20G06Q50/06G06F18/23213Y04S10/50
Inventor 马妍吴晖鲍薇段贝莉赵利思李京朱帆郭岩岩李林蔚王爽
Owner STATE GRID HENAN ELECTRIC POWER COMPANY ZHENGZHOU POWER SUPPLY
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
Eureka Blog
Learn More
PatSnap group products