Distribution network fault visual screening method based on alony forest algorithm

A technology of forest algorithm and screening method, which is applied in the field of visual screening of distribution network faults, can solve problems such as single and comprehensive reflection of fault characteristics, and achieve the effect of improving maintenance work efficiency and accuracy

Pending Publication Date: 2021-12-07
唐纳科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are many methods for screening and sorting distribution faults. Most of them use the power flow solutions before and after the accident to evaluate the severity of the fault. The method is re...

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
  • Distribution network fault visual screening method based on alony forest algorithm
  • Distribution network fault visual screening method based on alony forest algorithm
  • Distribution network fault visual screening method based on alony forest algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Refer figure 1 , figure 2 with image 3 For the first embodiment of the present invention, a distribution method based on a lonely forest algorithm is provided, including:

[0031] S1: The expected weight of the voltage stabilized fault grade in the distribution network system is based on the expected weight of the voltage stable fault level. It will be described herein that the fault level includes:

[0032] First class fault, secondary fault and three faults;

[0033] Level 1 fault includes serious failure;

[0034] Secondary faults include, general faults;

[0035] Three-level fault includes slight failure.

[0036] Specifically, the calculation expectations include:

[0037] Initialization fault level;

[0038] Add a branch, bus, circuit breaker, and node indicator parameters;

[0039] Adjust the learning rate 0.1, the number of calculations is n, and n is the number of times the global parameters;

[0040] Open the learning machine for calculation, output the desired we...

Embodiment 2

[0068] In order to better verify the technical effects employed in the method of the present invention, the conventional power fault analysis method is selected to compare the method of the method of the present invention in this embodiment, and the method of the present invention is verified by the method of the method of the present invention. Has a true effect.

[0069] The traditional power failure analysis method cannot directly display the power grid failure abnormality node, and it is impossible to filter the power grid failure. It is only for power grid failures. In the later stage, maintenance personnel are still needed to perform manual screening, to verify the method of the present invention relative to The conventional method has a high work efficiency, and in this embodiment, the conventional method and the method of the method of the present invention are used to screen the grid failure of the simulation platform, respectively.

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 distribution network fault visual screening method based on an alony forest algorithm, wherein the method comprises the steps: calculating an expected weight of an index according to a voltage stability fault level in a distribution network system; constructing a fault screening model based on an alony forest algorithm and the expected weight; and standardizing the fault screening model, matching a distribution network fault type in combination with a similarity strategy, and adaptively generating an SVG graph. According to the method, the SVG graph can be adaptively generated, the distribution network fault visualization is subjected to anomaly screening in combination with the alony forest algorithm, so that the maintenance work efficiency and accuracy of distribution network workers are improved.

Description

Technical field [0001] The present invention relates to the technical field of distributing visualization screening, and more particularly to a distribution method of distribution failure based on a lonely forest algorithm. Background technique [0002] In the operation and planning of the distribution network, the voltage stability of the system in various accidents is a basic task. In recent years, due to the fact that voltage stability has caused a lot of power outage, the voltage stable and safety assessment is increasingly The operator and researchers have also put forward higher requirements for the method and results of voltage stability analysis. One of the important contents of voltage stability is fault screening and sorting; in complex distribution network, the number of faults Huang, and for a certain mode of operation, only a few faults have a great impact on the stability of the system, which is a serious failure. It is necessary to in-depth research. How to quickly...

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
IPC IPC(8): G06F16/9035G06F16/28G06F30/20G06K9/62G06Q50/06
CPCG06F16/9035G06F16/287G06Q50/06G06F30/20G06F18/24323G06F18/214
Inventor 张宇超安慧城杨光林
Owner 唐纳科技有限公司
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