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

Method for detecting disease of metro shield tunnel based on deep learning

A tunnel disease, subway shield technology, applied in the direction of optical testing flaws/defects, measuring devices, scientific instruments, etc., to achieve online real-time data processing, fast real-time transmission, and solve the effect of limited image transmission distance

Inactive Publication Date: 2019-09-10
ZHEJIANG UNIV
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The present invention overcomes the shortcomings of traditional manual inspection methods and provides a method for detecting defects in subway shield tunnels based on deep learning

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
  • Method for detecting disease of metro shield tunnel based on deep learning
  • Method for detecting disease of metro shield tunnel based on deep learning
  • Method for detecting disease of metro shield tunnel based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0054] With reference to the accompanying drawings, figure 1 The codes in represent respectively:

[0055] 1 - frame,

[0056] 2 - seat,

[0057] 3 - headlights,

[0058] 4 - camera and camera stand,

[0059] 5 - Controller,

[0060] 6——Display and Host

[0061] A method for detecting defects of subway shield tunnels based on deep learning of the present invention, the specific implementation steps are as follows:

[0062] A. Set up a camera and take a video;

[0063] A1. Point the camera to the tunnel damage test area;

[0064] A2. Repeatedly adjust the lens focal length, aperture size and magnification of the camera, etc., so that the complete damage appears in the display field of view;

[0065] A3. Adjust the exposure time and gain value of the camera to obtain a clear image of the area to be tested in the tunnel and make it locat...

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

A method for detecting disease of a metro shield tunnel based on deep learning comprises the following specific implementation steps of A, camera set-up and shooting; B, over-fitting processing of data in a surveying area; C, evaluation and revision of a model; D, identification and location of tunnel damages; and E, automatic online monitoring and real-time storage of tunnel damages in the surveying area. The method provided by the invention has the advantages of 1, solving the shortcomings of low efficiency, low degree of digitization, and informatization and automation unfavorable to detection of the traditional manual inspection; 2, solving the problem that the image transmission distance is limited in the traditional tunnel damage monitoring method, and improving the measurement precision; 3, greatly alleviating recognition errors caused by environmental factors by adding a deep learning algorithm; and 4, transmitting the image information collected by the camera to the computer by using the high-speed Gigabit Ethernet to realize fast real-time transmission and immediate processing of the data online, so that the monitoring video can be viewed combined with the real-time stress state of the cable, and the event full information playback can be realized.

Description

technical field [0001] The invention relates to a method for real-time monitoring of shield damage. Background technique [0002] In recent years, with the continuous development of subway shield tunneling technology, the shield method, as an efficient underground construction method, has become the main construction method of underground and underwater tunnel projects in most cities in my country. However, at present, most of the segments in China are made of concrete segments, which may be damaged and damaged in the process of production, transportation, construction and service. The current manual inspection method has low efficiency and low degree of digitalization, which is not conducive to the informatization and automation of inspection; and with the increase of tunnel history and the continuous rise of labor costs, the use of manual inspection is increasingly unable to meet the needs of inspection and maintenance. [0003] 1. Damage research of general tunnel and sh...

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): G01N21/88G01B11/24
CPCG01B11/24G01N21/8851G01N2021/8883G01N2021/8887
Inventor 叶肖伟丁杨金涛陈鹏宇
Owner ZHEJIANG 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