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

UAV visual inspection and evaluation method and system for high-altitude steel structure corrosion

A technology of visual detection and evaluation methods, applied in neural learning methods, neural architectures, computer components, etc., can solve problems such as changeable shapes, difficult online detection and quantitative identification, complex background, etc., to reduce losses and promote safety The effect of production and improvement of detection efficiency

Active Publication Date: 2021-11-12
南京市特种设备安全监督检验研究院
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a UAV visual inspection and evaluation method and system for high-altitude steel structure corrosion, which solves the problem of large-scale high-altitude steel structure corrosion defects such as cranes, towers, and wind power blades with changeable shapes, complex backgrounds, and difficulties in online detection. Quantitative identification of technical issues

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
  • UAV visual inspection and evaluation method and system for high-altitude steel structure corrosion
  • UAV visual inspection and evaluation method and system for high-altitude steel structure corrosion
  • UAV visual inspection and evaluation method and system for high-altitude steel structure corrosion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Such as figure 1 As shown, the UAV visual inspection and evaluation method for high-altitude steel structure corrosion includes the following steps:

[0058] Step 1. The drone flight platform is equipped with a Camera Link industrial camera as a visual detection device to collect images of large high-altitude steel structures such as cranes, towers, and wind turbine blades in all directions and from multiple angles;

[0059] Step 2, transmit the collected high-altitude steel structure image to the edge computing image processing module based on FPGA or embedded GPU through the Camera Link interface;

[0060] Step 3. Using the improved YOLOV3 deep neural network classification model, the size of the anchor frame is automatically generated by the K-means clustering method, and the surface corrosion defects of three-dimensional complex steel structures such as box girders, I-beams, and trusses in the high-altitude steel structure image are analyzed. Quickly detect and cl...

Embodiment 2

[0102] Such as Figure 4 As shown, the UAV visual inspection and evaluation system for high-altitude steel structure corrosion includes a telecommunications-connected UAV flight platform 1, Camera Link industrial camera 2, edge computing equipment 3, wireless transmission equipment 4, ground terminal display equipment 5 and Alarm component6. The UAV flight platform is equipped with a Camera Link industrial camera to collect images of the steel structure to be inspected in real time, and transmits them to the edge computing device for image processing in real time through the Camera Link interface.

[0103] The edge computing device 3 includes a storage module and an image processing module. Wherein, the storage module is used to store the image of the steel structure to be detected collected by the drone, and transmit the image to the image processing module; the image processing module performs image data processing on the image to be detected, and runs the detection method ...

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 unmanned aerial vehicle visual detection and evaluation method and system for corrosion of high-altitude steel structures. The image is transmitted to the edge computing image processing module; 3. Use the deep neural network classification model to judge whether there are corrosion defects in the image, and automatically generate the size of the anchor frame through the K-means clustering method, and mark the corrosion target frame area; 4. Segment the image of the detected corrosion target frame area, extract the connected domain to invert the shape of the defect, and use the pixel point method to count the corrosion area; set the weight factor, calculate the weighted corrosion rate, and evaluate the corrosion classification of the detection equipment. This method solves the problems of large-scale high-altitude steel structure corrosion defects such as changeable form, complex background, difficult detection and quantitative identification, etc., and improves detection accuracy and efficiency.

Description

technical field [0001] The invention belongs to the technical field of non-destructive testing, and in particular relates to a method and system for unmanned aerial vehicle visual detection and evaluation of high-altitude steel structure corrosion. Background technique [0002] Corrosion of in-service large steel structures represented by port cranes, large amusement facilities, boilers, storage tanks, steel bridges, towers, wind power equipment, etc. will greatly reduce the allowable fatigue stress and the cold brittleness resistance of steel materials, and reduce the corrosion resistance of steel structures. The bearing capacity of the structure can reduce the service time of the equipment. In severe cases, the structure will break and crash, causing major vicious casualties. After the steel structure is corroded, its original color, shape, texture and other characteristics will change. According to the characteristics of corrosion defects that are different from normal ar...

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): G06T7/00G06T7/11G06K9/62G06N3/04G06N3/08
CPCG06T7/0004G06T7/11G06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30136G06N3/045G06F18/23213G06F18/24
Inventor 周前飞庆光蔚丁树庆冯月贵胡静波王会方宁士翔蒋铭王爽吴祥生倪大进丁必勇褚曙
Owner 南京市特种设备安全监督检验研究院