Fair-faced concrete surface pore analysis method based on convolutional neural network

A convolutional neural network and fair-faced concrete technology, applied in the field of materials engineering, can solve problems such as low efficiency and large human error, achieve high efficiency, stable image quality, and fill in the lack of acceptance quality standards.

Pending Publication Date: 2020-06-19
SOUTHEAST UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Purpose of the invention: Aiming at the problems that existing clear-water concrete surface pore analysis technology relies on artificial prior knowledge, has

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
  • Fair-faced concrete surface pore analysis method based on convolutional neural network
  • Fair-faced concrete surface pore analysis method based on convolutional neural network
  • Fair-faced concrete surface pore analysis method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0034] Example 1

[0035] Aiming at the problems that the existing clear-water concrete surface pore analysis relies on manual prior knowledge, low efficiency, and large human error, the present invention provides a method for analyzing the surface pores of clear-water concrete based on convolutional neural networks. The analysis method is as follows: using volume A neural network algorithm is used to establish a recognition and analysis model of pores on the surface of fair-faced concrete; the image of the appearance of clear-water concrete to be recognized is taken, input into the model, and the image of recognized and calibrated pores is output, as well as three pore analysis metrics: pore area ratio , stomatal pore size distribution, stomatal distribution uniformity.

[0036] Wherein, the establishment of described fair-faced concrete surface pore identification calibration model comprises the following steps:

[0037] (s1) collecting the image of the fair-faced concrete ...

Example Embodiment

[0044] Example 2

[0045] figure 1 Shown is the overall block diagram of the air hole analysis method on the surface of fair-faced concrete based on convolutional neural network of the present invention, comprising the following steps:

[0046] 101. Establish a calibration model for the recognition and calibration of pores on the surface of clear-water concrete: use the convolutional neural network to conduct deep learning on the feature information of the surface image of clear-water concrete, and establish a recognition and calibration model for pores on the surface of clear-water concrete. Specifically include the following steps:

[0047] 1011. Fair-faced concrete image acquisition: Under different on-site construction conditions, use drones to take aerial photos of the clear-faced concrete on the construction site to obtain comprehensive, full-coverage, high-definition and high-stable images; for enclosure structures and walls that are too close, human Neither drones no...

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 fair-faced concrete surface pore analysis method based on a convolutional neural network, and the method comprises the steps: firstly collecting an appearance image of a fair-faced concrete material, and generating a data set needed by machine learning for training; then performing deep learning on the data set by adopting a convolutional neural network algorithm, and establishing a model capable of automatically identifying and calibrating surface pores of bare concrete; and finally, for a to-be-identified image, carrying out pore identification and calibration by utilizing the model, and analyzing from three aspects of pore area ratio, pore diameter distribution and pore distribution uniformity on the basis of a result. According to the invention, automatic identification is carried out on bare concrete surface pores based on machine learning and a convolutional neural network; objective quantitative indexes and digital analysis are provided for evaluation and acceptance of fair-faced concrete in building construction, and the problems that traditional fair-faced concrete appearance quality acceptance consumes manpower resources and is large in personalerror and low in efficiency are solved.

Description

technical field [0001] The invention belongs to material engineering, and in particular relates to a method for analyzing pores on the surface of fair-faced concrete, in particular to a method for analyzing pores on the surface of clear-water concrete based on a convolutional neural network. Background technique [0002] Fair-faced concrete is one-time forming without any decoration. The natural state formed by the combination of the natural texture of the concrete itself and the well-designed open joints, Zen joints and tension bolt holes is used as the architectural expression of the decorative surface. It is widely used in Industrial buildings, high-rise civil engineering, public buildings and municipal bridges. Clear-water concrete is the most advanced expression-form in the concrete material, and what it shows is the most essential a kind of aesthetic feeling, embodiment be the grade of " wearing no make-up during an audience with the emperor ". Fair-faced concrete has...

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): G06T7/62G06T7/00G06N3/04G06N3/08
CPCG06T7/62G06T7/0002G06N3/084G06T2207/30132G06N3/045
Inventor 钱春香郝哲昕
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap