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

Steel box beam inspection method using collecting robot and deep learning algorithm

A deep learning and robotic technology, applied in the field of steel box girder crack monitoring, can solve the problems of inability to respond to steel box girder cracks in time, low identification accuracy, and long detection period, and achieves a reduction in acquisition time, high identification accuracy, and time saving. Effect

Inactive Publication Date: 2018-06-19
TONGJI UNIV
View PDF10 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This kind of manual inspection has a long detection cycle and cannot respond to cracks in steel box girders in time
Moreover, the criteria for judging cracks are more subjective, and the recognition accuracy is lower.

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
  • Steel box beam inspection method using collecting robot and deep learning algorithm
  • Steel box beam inspection method using collecting robot and deep learning algorithm
  • Steel box beam inspection method using collecting robot and deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] Such as Figure 4 As shown, the present invention firstly designs the inspection route of the robot according to the drawing of the standard section of the steel box girder. The route should take into account the viewing angle and definition requirements of image acquisition when the robot is walking.

[0038] Then place the robot in a certain beam section and collect information according to the designed inspection route. During the inspection, the camera and other sensors in the navigation module and the step control of the stepper motor are used to accurately perceive the time course position of its movement. When collecting, adjust the angle of the multi-degree-of-freedom gimbal, use auxiliary equipment such as fill lights to ensure that the ambient light source remains relatively consistent, and record the position during collection. After collecting the information of a beam segment, move to the next beam segment to collect.

[0039] After the image training se...

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 relates to a steel box beam inspection method using a collecting robot and a deep learning algorithm. The method comprises the following steps: 1) determining a patrol route of the collecting robot and performing navigation walking; 2) enabling the collecting robot to collect apparent information inside the steel box beam on the patrol route in real time; 3) using deep learning algorithm using crack for identification and localization to achieve identification and localization. Compared with the prior art, the method has the advantages of good automation, high efficiency, convenient shooting, high precision and high recognition precision.

Description

technical field [0001] The invention relates to the field of steel box girder crack monitoring, in particular to a steel box girder inspection method using a collection robot and a deep learning algorithm. Background technique [0002] At present, the detection of cracks in steel box girders of bridges mostly relies on manual inspection, and the cracks in steel box girders are identified and located by visual inspection or magnetic particle method. This kind of manual inspection has a long detection cycle and cannot respond to cracks in steel box girders in time. Moreover, the criteria for judging cracks are more subjective, and the recognition accuracy is lower. Contents of the invention [0003] The purpose of the present invention is to provide a steel box girder patrol inspection method using a collection robot and a deep learning algorithm in order to overcome the above-mentioned defects in the prior art. [0004] The purpose of the present invention can be achieved...

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): G06K9/00G06K9/20G05D1/02G06N3/08
CPCG05D1/0246G06N3/08G06V20/20G06V10/10
Inventor 江宸宇谭振业萧子泽王达磊
Owner TONGJI UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com