Insulator abnormal automatic detection method based on ensemble classifier online learning

An integrated classifier, automatic detection technology, applied in the field of machine learning and image processing, transmission line insulator anomaly detection

Active Publication Date: 2018-11-06
XI'AN POLYTECHNIC UNIVERSITY
View PDF4 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still few studies on online classification and detection of insulat

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
  • Insulator abnormal automatic detection method based on ensemble classifier online learning
  • Insulator abnormal automatic detection method based on ensemble classifier online learning
  • Insulator abnormal automatic detection method based on ensemble classifier online learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0075] The present invention is based on the insulator anomaly automatic detection method of integrated classifier online learning, such as figure 1 As shown, the specific steps are as follows:

[0076] Step 1. Collect the insulator image and obtain the sample D of the insulator to be tested. Specifically, use a drone or a pole tower equipped with a high-definition pan-tilt camera to collect the insulator image. The best shooting focal length is determined by continuously adjusting the shooting angle of the camera, so as to ensure the collection The obtained images are easier to extract the effective characteristic parameters of different types of insulators.

[0077] Step 2, establish a training sample set, specifically, use the insulator sample set with the determined fault type as the offline training sample set to train the classifier, e...

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 insulator abnormal automatic detection method based on ensemble classifier online learning. The method comprises the following concrete steps of carrying a high-definition PTZ camera by using a unmanned aerial vehicle/pole tower as a carrier; shooting a power transmission line visible light insulator image; performing preprocessing, image division, image multi-feature extraction and the like on the obtained image to obtain various typical features of abnormal isolator images and to perform normalization processing; next, selecting decision trees to be used as a weakclassifier; using the normalization features as the classification attribute to train the weak classifier; performing repeated training to obtain a plurality of decision trees and the classification weight; finally, generating a strong classifier with high classification accuracy through weighted voting; meanwhile, timely updating the strong classifier by combining the online learning technology;and separating each type of abnormal insulator images for subsequent processing. The method has the advantages that the principle is simple and visual; the implementation is easy; the image processingtechnology and the machine learning algorithm are combined for intelligently recognizing the insulator abnormality; and a novel idea and method is provided for the insulator abnormal operation monitoring.

Description

technical field [0001] The invention belongs to the technical fields of transmission line insulator anomaly detection, machine learning and image processing, and in particular relates to an insulator anomaly automatic detection method based on integrated classifier online learning. Background technique [0002] Insulators are widely used in power grids and are of various types. They are one of the key components of high-voltage overhead transmission lines and occupy a very important position. On the one hand, it is responsible for the mechanical support of the wire; on the other hand, it plays the role of insulation to prevent the current from forming a channel to the ground. However, due to the long-term exposure of insulators to the wild environment, various electrical and mechanical failures are likely to occur, which may lead to interruption of the power supply system, and even paralysis of the power grid in severe cases. Therefore, insulators are directly related to the...

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): G06T7/00G06T7/12G06T7/136G06T7/155
CPCG06T7/0004G06T7/12G06T7/136G06T7/155G06T2207/20081
Inventor 黄新波刘成张烨杨璐雅章小玲
Owner XI'AN POLYTECHNIC UNIVERSITY
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