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

Underground structure crack disease discrimination method based on deep learning algorithm

An underground structure and deep learning technology, applied in the field of crack discrimination, can solve the problems of relying on manual labor, low accuracy, and low efficiency, and achieve the effect of avoiding errors and high accuracy

Pending Publication Date: 2022-06-03
CCCC ROAD & BRIDGE CONSULTANTS +2
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: The purpose of the present invention is to provide a method for discriminating cracks and diseases in underground structures based on deep learning algorithms, so as to solve the problems of manual crack detection, low efficiency and low accuracy

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
  • Underground structure crack disease discrimination method based on deep learning algorithm
  • Underground structure crack disease discrimination method based on deep learning algorithm
  • Underground structure crack disease discrimination method based on deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with the accompanying drawings.

[0036] The underground structure crack disease discrimination method based on deep learning algorithm disclosed by the present invention comprises the following steps:

[0037] (1) Automatic crack image recognition based on Mask R-CNN deep learning algorithm

[0038] First prepare the data set required for crack detection, collect more than 20,000 images containing cracks, 227×227 pixels with RGB channels. Perform data preprocessing on the images in the data set, perform operations such as magnification, rotation, cropping, and grayscale on the images to remove useless information and make the crack image features more prominent, such as figure 1 shown;

[0039] Use the Labelme image annotation tool to annotate the images in the data set, and the annotated data of two cracks in the crack sample are as follows: figure 2 shown;

[0040] Divide the data set: first di...

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

PropertyMeasurementUnit
Widthaaaaaaaaaa
Login to View More

Abstract

The invention discloses an underground structure crack disease discrimination method based on a deep learning algorithm, and the method comprises the following steps: obtaining optimized initial parameters based on a Mask R-CNN deep learning algorithm, carrying out the deep learning of a large number of underground structure crack images, obtaining an intelligent recognition model of image cracks, and achieving the automatic recognition of any crack. For automatically identified cracks, a skeleton extraction algorithm and a function fitting method are adopted to obtain geometric characteristic parameters such as the length and width of the cracks; and in combination with crack generation reason analysis, underground structure damage grade judgment based on combination consideration of multiple factors such as crack types, the number of cracks in unit area, the maximum crack width and the longest crack length is proposed. The method can effectively realize the intelligentization of crack disease detection of the underground structure, and has the advantages of long distance, no contact, rapidness, convenience and high accuracy.

Description

technical field [0001] The invention relates to crack discrimination, in particular to a method for discriminating cracks and diseases of underground structures based on a deep learning algorithm. Background technique [0002] With the continuous advancement of underground engineering construction, more and more underground structures will enter the stage of inspection and maintenance, and the maintenance and management tasks of underground structures will be extremely difficult in the future. In the regular inspection, the inspection of cracks (that is, cracks) is in the first place. Crack inspection items include location, length, width and development. The traditional crack detection is mainly done by manpower. The surveyor must be close to the crack surface. When the space is limited, it must rely on the help of scaffolding and other tools to complete it. The efficiency is low, the cost of manpower and material resources is high, and the measurement accuracy is low. Ta...

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): G06V20/10G06V10/774G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/2415G06F18/214
Inventor 朱磊李东彪沈才华刘向阳闫星志
Owner CCCC ROAD & BRIDGE CONSULTANTS
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