Check patentability & draft patents in minutes with Patsnap Eureka AI!

GM (1,1) model transformer fault predicting method

A transformer failure and prediction method technology, applied in the direction of instruments, calculations, electrical digital data processing, etc., can solve problems such as faults or accidents, long repair time, etc., achieve strong applicability, high accuracy of calculation results, improve prediction accuracy and apply range effect

Inactive Publication Date: 2017-09-26
NANJING UNIV OF SCI & TECH
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Transformers are one of the most important electrical equipment in the power system. Once a fault or accident occurs, it will take a long time to repair and cause serious losses and impacts.
In recent years, although the operation reliability of transformers has been improved due to the improvement of materials, design methods and manufacturing technologies, due to some unpredictable external reasons or problems in usage methods and operation and maintenance, various types of transformers still occur. failure or accident

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
  • GM (1,1) model transformer fault predicting method
  • GM (1,1) model transformer fault predicting method
  • GM (1,1) model transformer fault predicting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0086] The embodiment of the present invention selects a group of typical monitoring data of a substation as shown in Table 1. The online monitoring historical data is used as the modeling data of the gray prediction model to predict the content of dissolved gas in the transformer oil.

[0087] Table 1 Dissolved gas content in oil

[0088]

[0089] In the first step, set the initial values ​​of α, β, and p to 0.1, and select a step size of 0.1;

[0090] In the second step, an exponential smoothing operation is performed on the dissolved gas data in the transformer oil in Table 1, and the data after the smoothing operation is accumulated once to generate, according to an exponential smoothing operation x (0) (k) = αx (00) (k)+(1-α)x (0) (k-1) and one-time cumulative generation formula get sequence X (1) (k);

[0091] The third step is to establish an improved gray GM(1,1) model for the dissolved gas content in transformer oil, and the specific expression is:

[0092]...

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 GM (1,1) model transformer fault predicting method. The method includes the following steps that 1, firstly, dissolved gas in transformer oil forms an original systematic characteristic data sequence X (00) according to time; 2, the original systematic characteristic data sequence X (00) is subjected to single exponential smoothing operation to obtain a sequence X (0), and the sequence X (0) is subjected to single accumulated generating operation to obtain a sequence X (1); 3, according to the sequence X (1) obtained in the step 2, a grey differential equation is established, the grey action quantity of grey prediction is calculated, the grey prediction is conducted on the dissolved gas in the transformer oil, and a first-order prediction model, shown in the description, of the dissolved gas in the transformer oil is obtained; 4, the first-order prediction model shown in the description is subjected to single inverse accumulated generating, an original sequence predicting value of a corresponding variable is restored, an error test is conducted on the model, and an optimal model for transformer fault prediction is obtained. The GM (1,1) model transformer fault predicting method is simple and easy to implement, detection results are reliable, and the method has great application value.

Description

technical field [0001] The invention belongs to the technical field of transformer fault detection, in particular to a GM (1,1) model transformer fault prediction method. Background technique [0002] With the rapid development of my country's electric power industry, the power system is developing in the direction of ultra-high voltage, large power grid, large capacity, and automation. From power generation, power supply to power consumption, an inseparable whole has been formed. Failure in any link may cause a chain reaction. lead to the collapse of the entire system. Therefore, it is very necessary to maintain and use the existing electrical equipment and improve the operational reliability of the equipment. [0003] Transformer is one of the most important electrical equipment in the power system. Once a fault or accident occurs, it will take a long time to repair and cause serious losses and impacts. In recent years, although the operation reliability of transformers h...

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): G06F19/00
CPCG16Z99/00
Inventor 张永尹希珂陈壮陈叶健臧瑶
Owner NANJING UNIV OF SCI & TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More