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

Asphalt pavement water damage detection method based on map gray scale adaptive selection

A detection method and self-adaptive technology, which are applied in the detection of asphalt pavement water damage based on the adaptive selection of atlas gray scale, and the field of asphalt pavement water damage, which can solve the problem of not considering the impact, accurate detection of water damage, and inability to accurately locate the water damage area. and its depth

Active Publication Date: 2020-04-17
CHANGAN UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] GPR is an effective detection method for water damage defects, but the existing dielectric constant test method based on GPR electromagnetic waves cannot accurately locate the water damage area and its depth, so the accurate detection of water damage is still a difficult problem
The invention patent proposed by the author (a water damage identification method based on the time-frequency statistical characteristics of ground penetrating radar signals, 201910100046.3) uses GPR data to realize the detection and automatic analysis of water damage through machine learning, but does not consider bridge deck paving. Influence of deck seams
GPR atlas can be effectively used to judge water damage. However, the characteristics of water damage defects are obviously different from the existing hyperbolic characteristics. Therefore, it is urgent to establish an automatic identification method for water damage defect atlas, improve the intelligence of GPR detection, and provide pavement Intelligent maintenance provides effective detection methods

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
  • Asphalt pavement water damage detection method based on map gray scale adaptive selection
  • Asphalt pavement water damage detection method based on map gray scale adaptive selection
  • Asphalt pavement water damage detection method based on map gray scale adaptive selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0105] This embodiment provides a kind of asphalt pavement water damage detection method, such as Figure 1 to Figure 3 shown, follow the steps below:

[0106] Step 1: Obtain the water damage atlas dataset through the GPR pavement survey:

[0107]Step S11, GPR pavement survey and data collection: use the GPR system to collect on-site data on the asphalt pavement, and during the process of on-site data collection, determine the damaged area of ​​the pavement where there is bleeding or whitening;

[0108] In step S11, during the on-site data collection process, the sampling parameters require that the sampling distance be 1.6 GHz, and the sampling frequency be 10 to 20 times the main frequency of the antenna.

[0109] These markers will appear as small squares above the GPR map, such as figure 2 The mark "□" in the radar map in the middle corresponds to the water damage defect area, and the GPR map corresponding to these marks is used as the true value of water damage to dete...

Embodiment 2

[0163]This embodiment provides a method for adaptive selection of ground penetrating radar maps for water damage detection, such as Figure 9 As shown, the method adaptively selects the ground penetrating radar map according to the contrast of the ground penetrating radar map, and the method is carried out according to the following steps:

[0164] Step 1, read the preprocessed GPR data:

[0165] After preprocessing the GPR data, randomly generate radar atlases with different contrasts within the set contrast value range, and construct an initial random atlas dataset. The size of the initial random atlas dataset is N pictures, and the initial random atlas The map data set is used to determine whether it contains the target;

[0166] The method for obtaining the GPR data is as follows: using the GPR system to collect on-site data on the asphalt pavement, during the process of on-site data collection, determine the damage area where the road surface appears whitish or whitish, ...

Embodiment 3

[0233] This example presents a water damage detection method for asphalt pavement based on the adaptive selection of the map gray scale, such as Figure 1 to Figure 17 As shown, this method is basically the same as the asphalt pavement water damage detection method in Example 1, the only difference is that in step S12, "set the contrast of the GPR spectrum and intercept the GPR spectrum according to the length of 5-6m" is replaced by "choose a suitable Contrast GPR spectrum and intercept the GPR spectrum according to the length of 5-6m".

[0234] The method adopted in the selection of the GPR spectrum of suitable contrast is the ground-penetrating radar spectrum adaptive selection method;

[0235] The adaptive selection method of the ground penetrating radar spectrum is the same as the water damage detection method for asphalt pavement used for water damage detection described in Embodiment 2.

[0236] The identification models described in Embodiment 1 and Embodiment 2 are t...

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 provides an asphalt pavement water damage detection method based on map gray scale adaptive selection, and the method is carried out according to the following steps: 1, obtaining a water damage map data set through GPR pavement investigation, and the selection of a GPR map with a proper contrast ratio is a ground penetrating radar map adaptive selection method; step 2, picture resolution adjustment; directly scaling the resolution of the damaged initial atlas data set to 224 * 224 to obtain a BD data set; 3, inputting the data set into an recognition model; inputting the BD dataset obtained in the step 2 into a recognition model, and executing the step 4 after the recognition model performs operation; and 4, outputting a water damage result. According to the method, the problem that existing GPR data analysis depends on artificial experience to screen the atlas is solved, the atlas detection model is effectively combined, automatic selection and recognition of the atlasof GPR data at each position can be achieved, and automatic and intelligent work based on GPR target detection is truly achieved.

Description

technical field [0001] The invention belongs to the field of road maintenance, relates to asphalt pavement water damage, in particular to a detection method for asphalt pavement water damage based on self-adaptive selection of map gray scale. Background technique [0002] Ground Penetrating Radar (GPR) is an instrument that uses radar pulse waves to detect and image conditions below the surface. Its principle is to use antennas to transmit and receive high-frequency electromagnetic waves to detect the material properties of the medium. GPR uses high-frequency and usually polarized radio waves to transmit waves below the surface. When the electromagnetic waves hit objects buried under the surface or reach the boundary of dielectric constant changes, the reflected waves received by the antenna will be recorded. The signal difference of the reflected echo. Because GPR can carry out continuous, rapid and non-damage detection, GPR has been applied in road traffic at present, suc...

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): G01S13/88G01S13/89G01S7/41
CPCG01S13/885G01S13/89G01S7/41G06V10/12G06V10/82G06V10/40G01S7/417G01V3/12G01V3/15G06V10/42G01N27/221
Inventor 张军陶君
Owner CHANGAN 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