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

Bridge inhaul cable surface defect real-time recognition system and method based on deep learning

A bridge cable and deep learning technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve the problems of inaccurate recognition and low precision, improve precision and accuracy, reduce work intensity, reduce The effect of repetitive work

Pending Publication Date: 2020-12-18
SOUTHEAST UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above problems, the present invention discloses a system and method for real-time identification of surface defects of bridge cables based on deep learning, which solves the problems of inaccurate and low-precision identification of surface defects of cables, and at the same time realizes detection of cable defects by combining detection robots Real-time detection and rating

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
  • Bridge inhaul cable surface defect real-time recognition system and method based on deep learning
  • Bridge inhaul cable surface defect real-time recognition system and method based on deep learning
  • Bridge inhaul cable surface defect real-time recognition system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. It should be noted that the words "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to the directions in the drawings, and the words "inner" and "outer ” refer to directions towards or away from the geometric center of a particular part, respectively.

[0040] Such as figure 1 , 2 , 3, the present embodiment provides a system and method for real-time identification of surface defects of bridge cables based on deep learning, the real-time identification system includes a detection robot for bridge cables, four detection cameras, an image splitter, Transmission unit, remote host, four detection cameras are used to obtain 360-d...

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 bridge inhaul cable surface defect real-time recognition system and method based on deep learning. The bridge inhaul cable surface defect real-time recognition system comprises a detection robot, four detection cameras installed on the detection robot, an image divider, an image transmission unit and a remote host. The method comprises the following steps: 1, acquiring ato-be-detected inhaul cable surface defect data set through an identification system device, marking inhaul cable defect objects, and establishing a data set; 2, sending the inhaul cable defect data set into a Mask-RCNN deep learning network to be trained, and a weight file is generated; 3, running the detection robot on the inhaul cable, and obtaining a current inhaul cable image by a detection camera, synthesizing the current inhaul cable image into a picture and sending the picture to the remote host through a picture transmission unit. 4, receiving the image for identification test, and loading the weight obtained by training bya remote host; 5, acquiring an inhaul cable defect recognition image through a Mask-RCNN network, and performing image processing by the remote host to obtain adefect pixel image. and 6, outputting and storing the original image and the defect identification image by the remote host, and marking defect rating information in the original image.

Description

technical field [0001] The invention belongs to the field of flaw detection robots and non-destructive testing, and specifically relates to a system and method for real-time identification of surface defects of bridge cables based on deep learning. Background technique [0002] Cable-stayed bridges are mainly composed of towers under compression, cables under tension and girders under bending. During the normal operation of the stay cable, the stay cable will be repeatedly affected by the dynamic load of the bridge deck, wind and rain vibration, sunshine and corrosive gas, and it is easy to cause damage to the outer sheath, local steel wire corrosion and other diseases. The damage of the cable sheath causes the internal steel wires to be exposed to the air, and the oil stains attached to the surface of the cable stays may penetrate into the interior of the cables and accelerate the corrosion of the steel wires. If maintenance is not performed regularly, the steel wires will ...

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): G06K9/00G06K9/34G06K9/62G06N3/04
CPCG06V20/10G06V10/267G06N3/045G06F18/214
Inventor 王兴松李杰田梦倩
Owner SOUTHEAST 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