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

SF6 device secondary fault diagnosis method based on mass data parallel computation

A massive data, secondary fault technology, applied in the field of power system, can solve the problem of inability to accurately judge the type and severity of equipment faults, and achieve the effect of improving diagnosis efficiency, saving time, and quickly diagnosing

Inactive Publication Date: 2018-05-01
HOHAI UNIV CHANGZHOU
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the pulse current method, ultrasonic method and UHF method cannot accurately judge the fault type and severity of the equipment

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
  • SF6 device secondary fault diagnosis method based on mass data parallel computation
  • SF6 device secondary fault diagnosis method based on mass data parallel computation
  • SF6 device secondary fault diagnosis method based on mass data parallel computation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] like figure 1 As shown, the block diagram of the secondary fault method of SF6 equipment based on massive data parallel operation.

[0051] Step 1. Normalize the training data, the test data and the data to be diagnosed.

[0052] Step 2: Build a first-level model in parallel, and build a decision tree model by using the CART algorithm for parallel tree building according to training data and test data.

[0053] (1.1) The tree-building process is performed using parallel operations.

[0054] (1.1.1) Open the parallel pool according to the number of attribute sets of the training data;

[0055] (1.1.2) The Gini value of each lab computing attribute of the parallel pool; the attribute with the smallest Gini value is selected as the current division attribute; Gini is defined as follows: For the sample set D, there are K classes, which belong to the sample subset of the Kth class is Ck, then its Gini is:

[0056]

[0057] where: |C k | is the size of CK, and |D| is ...

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 SF6 device secondary fault diagnosis method based on mass data parallel computation. According to the corresponding relationship between the SF6 decomposed gas component content and the fault type in an electrical device, firstly, a secondary fault diagnosis model of an SF6 electrical device is parallelly constructed, and the modeling efficiency is improved. Then parallel diagnosis of the SF6 electrical device is achieved, the diagnosis rapidity and accuracy in a big data environment are improved. The parallel diagnosis process of the SF6 device secondary fault diagnosis method is that each lab diagnoses different pieces of data at the same time, specifically, a decision tree model is employed to carry out primary diagnosis on the pieces of data and determine whether the device has a fault, and therefore the mass data processing speed is increased. For fault data, the fault type is accurately determined through a neural network model. By employing the SF6 device secondary fault diagnosis method, the diagnosis result can be obtained only through simple data processing, the demand on the professional skill of an operator is greatly reduced, when a lot of SF6 electrical devices are diagnosed, the diagnosis efficiency is greatly improved.

Description

technical field [0001] The invention relates to the technical field of electric power systems, in particular to a secondary fault diagnosis method for SF6 equipment based on massive data parallel operation. Background technique [0002] With the development of my country's electric power industry, the application of SF6 electrical equipment in the transmission network is more and more extensive, and its operation reliability directly affects the safe and stable operation of the power grid. Due to possible defects in the design, manufacture, operation and maintenance of the equipment, partial discharge or even arc discharge occurs inside the equipment, and some SF6 molecules decompose, and the decomposition products generally have high chemical activity and corrosiveness, causing the insulation performance of the equipment to decline. Grid security. Therefore, timely detection of the internal defects of SF6 electrical equipment is of great significance to ensure the safe ope...

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): G06K9/62G06N3/08
CPCG06N3/08G06F18/214
Inventor 苗红霞萧旋旋齐本胜贾澜顾倚榜熊天宇
Owner HOHAI UNIV CHANGZHOU
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