Unlock instant, AI-driven research and patent intelligence for your innovation.

Insulator Defect Detection and Recognition Method Based on Ultraviolet Imaging

A technology of ultraviolet imaging and recognition methods, applied in neural learning methods, character and pattern recognition, image analysis, etc., can solve the problems of sensor installation and monitoring system maintenance workload, and achieve the effect of reducing pressure

Active Publication Date: 2021-10-01
STATE GRID JIANGSU ELECTRIC POWER CO LTD NANTONG POWER SUPPLY BRANCH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Leakage Current refers to the current flowing through the surface of the insulator, which is collected by relevant devices and transmitted to the background control center for further processing and analysis. Generally, the number of pulses and the maximum value of the leakage current are used to characterize the operation of the insulator state, this method is generally recognized by practitioners in the power industry at present, it is easy to realize online monitoring, and the effect is good, but this method is a contact detection method, and the installation of sensors and the maintenance of the monitoring system require a lot of work

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 Defect Detection and Recognition Method Based on Ultraviolet Imaging
  • Insulator Defect Detection and Recognition Method Based on Ultraviolet Imaging
  • Insulator Defect Detection and Recognition Method Based on Ultraviolet Imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] A method for detecting and identifying insulator defects based on ultraviolet imaging, comprising the following steps:

[0032] (1) Perform grayscale processing on the collected original RGB color ultraviolet image, and the processing formula is to obtain the grayscale image Y:

[0033] (2) Perform Gaussian filtering on the grayscale image obtained in step (1) to suppress noise, and use a 3×3 Gaussian template to convolve the grayscale image Y with the Gaussian template to obtain the image Y after suppressing noise g ;

[0034] (3) For the image Y obtained in step (2) g Perform binarization processing to obtain a binary image, and the binarization formula is:

[0035]

[0036] (4) Computing the connected domain of the binary image that step (3) obtains;

[0037] (1) The first scan:

[0038] Access current pixel B(x,y), if B(x,y)==1:

[0039] a. If the label values ​​in the field of B(x,y) are all 0, give B(x,y) a new label value label:

[0040] label+=1, B(x,y)...

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 defect detection and recognition method based on an ultraviolet imaging method. The collected original RGB color ultraviolet image is grayscaled to obtain a grayscale image Y; the grayscale image is Gaussian filtered to suppress noise and grayscale Degree image Y is convolved with a Gaussian template to obtain an image after suppressing noise; binarize the obtained image to obtain a binary image; calculate the connected domain of the binary image; three defect insulators form a group, and each group of insulators Continuously collect 100 frames of ultraviolet pictures for each defect; process the sample pictures and calculate the connected domain of the image, and the three values ​​constitute the feature description of the defect type; use the SVM classifier to train three defect recognition models; detect insulators. The invention utilizes the image processing method and the machine learning method to not only locate the position of the defect of the insulator, but also determine the type of the defect, thereby reducing the pressure of manual inspection.

Description

technical field [0001] The invention relates to an insulator defect detection and identification method. Background technique [0002] With the continuous expansion of power transmission scale, the first concern is how to ensure the safe and effective operation of power transmission lines. Insulators are devices installed between different components that can withstand voltage and mechanical effects, and play an important role in power transmission lines. Fixed suspension through insulators can increase the transmission distance. The insulation function can reduce the capacitive reactance between wires and reduce the loss of current. Therefore, insulators are widely used in overhead lines and are often seen in daily life. Since the insulator is exposed to the air for a long time, it is easily affected by lightning, icing, pollution, etc., which will cause problems such as self-exposure, damage, and dirt of the insulator. In order to ensure the safe and reliable operation o...

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 Patents(China)
IPC IPC(8): G06T7/00G06K9/62G06N3/04G06N3/08G06T5/00G06T7/187
CPCG06T7/0006G06T7/187G06N3/08G06T2207/10024G06T2207/20024G06N3/045G06F18/2411G06T5/70
Inventor 朱富云李学均茅雷徐晓轶吴勉宏徐冰陈金华戴相龙毛艳芳蒋勇王晓鹏何成虎
Owner STATE GRID JIANGSU ELECTRIC POWER CO LTD NANTONG POWER SUPPLY BRANCH