Unlock instant, AI-driven research and patent intelligence for your innovation.

A dynamic early warning method and system for slope crack changes with convolutional neural network

A convolutional neural network and dynamic early warning technology, applied in the direction of biological neural network models, neural architectures, instruments, etc., can solve the problems of high monitoring cost, high cost, and limited monitoring range, so as to improve collection efficiency, increase collection range, The effect of ensuring safety

Active Publication Date: 2022-04-08
GUIZHOU CONSTR SCI RES & DESIGN INST OF CSCEC
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Although the existing method can accurately obtain the relative change of slope slippage and analyze the slippage area through the relationship between measuring points, this method still has high monitoring costs and limited monitoring range. For super-large slopes, the cost of this method will increase significantly with the increase of the monitoring range; at the same time, since most of the monitoring equipment is located in the field, it is difficult to guarantee the stability of the equipment protection and equipment life for many years. There have been a large number of application results in geological disaster monitoring and municipal slope monitoring, but the cost of using existing methods is still high. For units that are responsible for safety management and control, the pressure is heavy. In recent years, with the development of high-definition and ultra-high-definition camera technology And the rapid development of deep learning technology based on neural network, the design of slope crack recognition and early warning system based on image recognition technology has also become possible

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
  • A dynamic early warning method and system for slope crack changes with convolutional neural network
  • A dynamic early warning method and system for slope crack changes with convolutional neural network
  • A dynamic early warning method and system for slope crack changes with convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] refer to Figure 1 ~ Figure 4 , which is the first embodiment of the present invention, this embodiment provides a dynamic early warning method for changes in slope cracks in a convolutional neural network, including:

[0039] S1: Install video surveillance equipment on the opposite side of the slope. refer to figure 2 ,It should be noted:

[0040] 1 is the slope body, 2 is the slope crack, 3 is the video camera support and lightning rod, 4 is the data acquisition box, 5 is the fixed angle connection bracket, 6 is the high-definition camera and the protective cover, and 7 is the enlarged area map of the crack.

[0041] S2: Timing processing is performed on the pictures taken by the video surveillance equipment. What needs to be explained in this step includes:

[0042] Obtain the R, G, and B values ​​of each point in the 1080*1080 pixel area of ​​the captured picture, and convert it into a grayscale image. The conversion formula is as follows:

[0043] R g =(R h...

Embodiment 2

[0085] refer to Figure 5 , which is the second embodiment of the present invention. This embodiment is different from the first embodiment in that it provides a dynamic early warning system for changes in slope cracks in a convolutional neural network, including:

[0086] The sampling module 100 is used to take high-definition images for data analysis and change comparison, and to collect data for later work.

[0087] The data processing center module 200 is connected and arranged on the lower surface of the sampling module 100, which is used to receive, store and calculate the data collected by the sampling module 100. The data center module 200 includes a computing unit 201, a database 202 and an input-output management unit 203. The unit 201 is connected with the acquisition module 100, and is used to receive the image data information acquired by the sampling module 100 for calculation and processing, to calculate the gray value, and to compare the amplitude of the gray a...

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 method and system for dynamic early warning of slope crack changes through a convolutional neural network, comprising: installing video monitoring equipment on the opposite side of the slope; timing processing of pictures taken by the video monitoring equipment; using convolutional neural network The network image recognition algorithm judges whether there are new cracks in the slope in the processed pictures, and conducts deep learning on multiple pictures to identify the location and change of the cracks; combined with distance measurement and trigonometric function relationship, determine the The scope of slipping of the slope and the deformation situation of the preliminary estimate are given and early warning is given. The invention improves the collection range and collection efficiency of the same slope data, and can calibrate the deformation range of the slope under the accurate data identification method, so as to automatically warn management personnel and ensure the safety of the slope during operation.

Description

technical field [0001] The invention relates to the technical field of slope crack monitoring and early warning during the operation period, in particular to a dynamic early warning method and system for slope crack changes using a convolutional neural network. Background technique [0002] As we all know, slopes that have been built for a period of time may have decreased safety equipment and gradually intensified slope safety hazards. However, in the existing monitoring system, deformation monitoring points are mainly arranged in areas where slopes may slip. Optical or Beidou satellite positioning technology is used for deformation monitoring, so as to carry out monitoring and early warning. [0003] Although the existing method can accurately obtain the relative change of slope slippage and analyze the slippage area through the relationship between measuring points, this method still has high monitoring costs and limited monitoring range. For super-large slopes, the cost...

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 Patents(China)
IPC IPC(8): G06V20/52G06V20/10G06V10/26G06V10/82G06N3/04G06F16/583G01N21/88
CPCG06F16/583G01N21/8851G01N2021/8887G06V20/52G06V10/26G06N3/045
Inventor 池汇海庹斌李东旭杨林袁超殷才华
Owner GUIZHOU CONSTR SCI RES & DESIGN INST OF CSCEC