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

Building spoil particle size distribution rapid identification method based on convolutional neural network

A convolutional neural network and construction spoil technology, which is applied in the field of rapid identification of the particle size distribution of construction spoil, and achieves the effects of good reproducibility of results, improved comprehensive utilization, and clear thinking.

Active Publication Date: 2020-06-05
TONGJI UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for quickly identifying particle size distribution of building spoils based on convolutional neural networks in order to overcome the defects in the above-mentioned prior art, which can realize long-distance rapid detection and effective recording of spoil distribution. Easy to operate, strong reproducibility, and wide coverage, it is helpful to quickly and reliably test the particle size distribution of construction spoils, effectively improve the efficiency of testing and processing, speed up the pre-treatment process of construction spoil recycling, and make up for the cumbersome operation of traditional methods , the shortcomings of large errors

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
  • Building spoil particle size distribution rapid identification method based on convolutional neural network
  • Building spoil particle size distribution rapid identification method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] like figure 1 A method for quickly identifying the particle size distribution of construction spoil based on convolutional neural network is shown, which specifically includes the following steps:

[0070] 1) Take the construction spoil soil samples from the construction site, bake them at a constant temperature of 110°C for 40 hours, put the soil samples into a mortar and grind them thoroughly;

[0071] 2) Screening the ground building spoil with a fine sieve with an aperture of 1mm;

[0072] 3) Weigh 10.00 g of the soil sample passing through the 1mm sieve hole in step 2) and dilute it in the glass dish to be tested as the sample to be tested;

[0073] 4) Take the original image of the spoil particle distribution after microscopic imaging in the glass dish, and perform grayscale processing to convert it into a grayscale image;

[0074] 5) Select an appropriate threshold, convert the obtained grayscale image into a binary image, set all the pixel values ​​of the back...

Embodiment 2

[0080] A fast identification method of particle size distribution of construction spoil based on convolutional neural network,

[0081] 1) Dry the construction spoil sample at 105°C for 24 hours to constant weight, remove the construction waste different from the characteristics of the spoil sample, and then go through the process of grinding and sieving to obtain the pretreated construction waste whose particle size is not greater than 1mm. soil sample;

[0082] 2) Prepare the pretreated construction spoil sample in step 1) into an 8wt% dilute solution and boil it for 1 hour, then observe it with a video camera under a microscope, keep the particles in the pretreated sample in a dispersed state, and adjust the particle imaging The axial position of the particle is taken and photographed to obtain multiple microscopic images of particles;

[0083] 3) Perform grayscale processing on the particle microscopic image in step 2) to obtain a grayscale image, then select an appropria...

Embodiment 3

[0104] In this embodiment, in step 1), the drying temperature is 110° C., and the drying time is 48 hours;

[0105] After the construction spoil sample and the construction spoil to be tested are pretreated in step 1) in this embodiment, the acid-base detection is carried out. The test results show that the construction spoil samples and the construction spoil to be tested are acidic soils, so step 2 ) in the preparation of dilute solution of the dispersant are all selected 0.3N NaOH solution.

[0106] In addition, the boiling time in step 2) is 1.2h.

[0107] All the other are with embodiment 2.

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 relates to a building spoil particle size distribution rapid identification method based on a convolutional neural network, and the method comprises the steps: carrying out the processing of a to-be-tested building spoil image based on a pre-trained building spoil particle size distribution identification convolutional neural network model, and obtaining the particle size distribution of to-be-tested building spoil, wherein the building spoil image is a binary image obtained by preprocessing building spoil to be tested, dispersing the preprocessed building spoil in a solution toobtain a dilute solution, and then sequentially shooting and processing the image to obtain a binary image. Compared with the prior art, according to the invention, artificial intelligence is combinedwith a traditional geotechnical test; a non-direct contact detection means is adopted, remote rapid detection and effective recording of the particle size distribution of the building spoil are achieved, the method has the advantages of being convenient to operate, simple, practical, good in result reproducibility, high in test precision and the like, a reliable and effective pretreatment mode isprovided for resource utilization of the building spoil, and high popularization value and environmental benefits are achieved.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and relates to a method for quickly recognizing particle size distribution of building spoil based on a convolutional neural network. Background technique [0002] Construction spoil mainly refers to all kinds of solid waste mainly waste soil generated during the construction (including excavation, demolition, repair or decoration) of various buildings (structures), pipe networks, roads and bridges. With the rapid development of my country's economy, housing and subway construction have brought great changes to our living and working environment, but at the same time of rapid development, the output of construction spoils has also increased significantly. Considering that the particle size distribution of construction spoils can not only reflect its depositional environment, but also determine the mechanical and hydraulic properties of soil samples (collapsibility...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06K9/62G01N15/02G06N3/04G06N3/08
CPCG06T7/0004G01N15/0205G01N15/0211G06T2207/10016G06T2207/10056G06T2207/20081G06T2207/20088G06T2207/30132G06N3/08G06N3/045G06F18/241
Inventor 肖建庄柏美岩王春晖高琦
Owner TONGJI 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