Steel structure damage detection method based on full-connection neural network and transmissibility function

A neural network and damage detection technology, applied in biological neural network model, neural architecture, electrical and digital data processing, etc., can solve problems such as inaccuracy and incomplete damage detection of steel structures, and achieve high engineering adaptability and damage recognition rate. Improve the effect of high recognition rate

Pending Publication Date: 2020-12-25
ZHEJIANG UNIV OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the author's previous research, a steel structure damage detection method based on the transfer rate function and wavelet analysis successfully identified the dam

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
  • Steel structure damage detection method based on full-connection neural network and transmissibility function
  • Steel structure damage detection method based on full-connection neural network and transmissibility function
  • Steel structure damage detection method based on full-connection neural network and transmissibility function

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The structure will be further described below in conjunction with the accompanying drawings of the description.

[0034] refer to Figure 1 to Figure 7 , a steel structure damage detection method based on fully connected neural network and transfer rate function, including the following steps:

[0035] S1. According to the damage information of the steel structure, the steel structure model is partitioned, and the simulation analysis of each position is carried out;

[0036] S2. Through the steel structure dynamics calculation and analysis model in step S1, perform damage simulation analysis on each position to obtain the input samples of the fully connected neural network, and the damage simulation is realized by changing the mass or stiffness of a certain position of the steel structure;

[0037] S3. Design a fully connected neural network model, and use the sample data in step S2 to perform network training and cross-validation parameter adjustment;

[0038] S4. Pe...

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 steel structure damage detection method based on combination of a full-connection neural network and a transmissibility function, and the method comprises the steps: carryingout the transient analysis of a steel structure frame structure model through ANSYS software, obtaining the node accelerations of a steel structure frame structure under different damage positions and damage degrees, and obtaining the variable quantity of the transmissibility function through MATLAB software; obtaining a damage index value of each detection position of the steel structure by taking the variable quantity of the transmissibility function as an input parameter of the full-connection neural network; furthermore, carrying out experimental verification through a steel structure frame damage detection experiment. Results show that compared with a traditional transmissibility function method, the new method has the advantages that the steel structure damage recognition rate of all the positions is averagely improved by 26.3%, the damage conditions of all the positions of the steel structure can be recognized more accurately and comprehensively, and the damaged positions of the steel structure are accurately positioned.

Description

technical field [0001] The invention belongs to the field of steel structure damage detection, and in particular relates to a steel structure damage detection method based on the combination of a fully connected neural network and a transfer rate function. Background technique [0002] Large-scale steel structures (such as bridges or multi-storey buildings) are prone to cracks due to internal stress at the welds of steel structures during their service life, and bolts are prone to loosening at the joints of steel structures due to impact loads. In order to ensure the safety and reliability of these structures To prevent catastrophic accidents, early and reliable damage detection and health assessment are extremely important, while ultrasonic, eddy current, X-ray and magnetic flux leakage testing may involve high cost and intermittent exploration. [0003] The transmissibility function refers to the ratio of the frequency domain response or the energy ratio between two differ...

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): G06F30/27G06F30/17G06F30/23G06K9/62G06N3/04G06F119/14
CPCG06F30/27G06F30/17G06F30/23G06F2119/14G06N3/045G06F18/214
Inventor 艾青林徐巧宁林小贝
Owner ZHEJIANG UNIV OF TECH
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