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

Concrete beam damage rapid evaluation method based on generative adversarial network

A concrete beam and network technology, which is applied in biological neural network models, neural learning methods, image analysis, etc., can solve the problems of inability to calculate and evaluate beam damage degree, stay, and inability to obtain concrete beam damage evolution performance parameters, etc. Time-consuming, labor-intensive, uneconomical, and automated

Pending Publication Date: 2022-08-02
TONGJI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these methods are very effective for crack detection and segmentation, the information captured about the damage stays only on the surface of the structure
They do not have access to the damage evolution and related performance parameters inside the concrete beams, and thus cannot calculate and assess the damage degree of the beams

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
  • Concrete beam damage rapid evaluation method based on generative adversarial network
  • Concrete beam damage rapid evaluation method based on generative adversarial network
  • Concrete beam damage rapid evaluation method based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. The technical solution of the present invention is described by taking two concrete beams with different reinforcement as an example.

[0050]The design idea of ​​the present invention is as follows: obtain the crack image of the concrete beam and the corresponding numerical calculation damage cloud map, construct the data set of the concrete beam, train the confrontation generation network, and carry out the application after the performance index evaluation is qualified; input a new image of the beam crack taken on site , and directly generate the damage cloud map with numerical calculation information through the trained network; after obtaining the damage cloud map, extract pixels of different colors to quantify the damage, build the mapping relationship between the load and the color ratio, and evaluate the damage stage of the beam.

[0051] 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 aims to provide a concrete beam damage rapid evaluation method based on a generative adversarial network. According to the technology, firstly, a numerical damage stress cloud picture is generated from a real crack image on a concrete beam, and then damage is quantified and the damage stage of the beam is evaluated by adopting a pure vision method. A traditional method for evaluating the damage of the concrete beam needs a component tension and compression experiment or finite element modeling calculation, time and labor are consumed, and the method is not economical, however, according to the frame provided by the invention, damage information of a real world and numerical calculation can be obtained at the same time only through a concrete beam crack image shot on site, and the method is very practical. And an engineer is greatly helped to quickly evaluate the damage of the concrete beam.

Description

technical field [0001] The invention belongs to the field of structural component damage monitoring in structural health monitoring, in particular to a rapid assessment technology for structural component damage based on deep learning and computer vision. Background technique [0002] Concrete beams have been widely used as main components in existing buildings, and its damage greatly affects the stability of the entire structure, so the assessment of its damage is essential to maintain the safety of buildings. The performance evolution of beams can be obtained directly through experiments, but it is time-consuming, labor-intensive and uneconomical to obtain the damage information of each beam through experiments. In structural health monitoring, finite element analysis software such as Abaqus is mostly used to simulate and evaluate concrete beams. By establishing and calculating the numerical model of the concrete beam, the method can obtain various parameters of material ...

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): G06F30/23G06F30/27G06T7/00G06N3/04G06N3/08G06F111/10
CPCG06F30/23G06F30/27G06T7/0002G06N3/08G06F2111/10G06T2207/30108G06T2207/10028G06T2207/20081G06T2207/20084G06N3/045Y02P90/30
Inventor 孔庆钊祁彦之袁程李培振
Owner TONGJI UNIV