Structural damage assessment method based on distributed vibration data and convolutional self-encoding deep learning

A technology of convolutional self-encoding and vibration data, which is applied in the direction of neural learning methods, neural architecture, and measurement acceleration, can solve the problems of weak damage identification and evaluation ability, and achieve the effect of saving computing power and strong robustness

Active Publication Date: 2021-07-23
SOUTHEAST UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this supervised learning method can classify the type and degree of structural damage, this method is based on the known or predicted damage state of the v

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
  • Structural damage assessment method based on distributed vibration data and convolutional self-encoding deep learning
  • Structural damage assessment method based on distributed vibration data and convolutional self-encoding deep learning
  • Structural damage assessment method based on distributed vibration data and convolutional self-encoding deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The implementation of the damage score of the present invention will be further described below in conjunction with the drawings of the description.

[0058] The first step is to obtain measured data through sensors and health monitoring systems.

[0059] attached figure 1 Shown is a typical steel structure frame, which has 4 floors, 2×2 spans, and a height of 3.6m. Among them, the additional mass of each floor is 4000kg, 4140kg, 4000kg, 3000kg respectively. by arranging as attached Figure 2-6 The 15 accelerometers shown monitor the acceleration-dispersed vibration data of the structure under environmental excitations. The sampling frequency of the sensor is 200Hz. By removing the support and loosening the node bolts, the structural states with different damage degrees were simulated with five working conditions from strong to weak, as shown in the attached image 3 shown, and record the acceleration-dispersed vibration data of the corresponding sensors.

[0060]...

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 structural damage assessment method based on distributed vibration data and convolutional self-encoding deep learning, and the method comprises the following steps: S1, selecting acceleration response monitoring points, and arranging an acceleration sensor at each monitoring point; s2, acquiring monitoring data of n acceleration sensors in a normal use state of the structure, and performing data preprocessing to form a data set for deep learning network training; s3, constructing a convolutional self-encoding deep learning network suitable for the data set in the step S2; s4, preprocessing massive structure monitoring data in a normal use state according to the step S2, and inputting the preprocessed data into a convolutional auto-encoder for training to obtain a deep learning network file; and S5, evaluating a structural damage state through a data reconstruction correlation function. According to the method, the data does not need to be pre-classified, the structure damage state is quantified in real time by using the real-time vibration monitoring data, and the score is given.

Description

technical field [0001] The invention belongs to the field of structural health monitoring vibration data damage assessment, in particular to a structural damage assessment method based on distributed vibration data and convolutional self-encoding deep learning. Background technique [0002] The structural safety and damage assessment of buildings and bridges has always been a problem that has attracted much attention in the field of structural safety and disaster prevention and mitigation engineering at home and abroad. Due to the dynamic extreme effects of vehicles, pedestrians, cargo loads, typhoons, and earthquakes during the service of bridges or buildings / structures, various macroscopic or microscopic damages will inevitably occur on the interior and surface of the structure, resulting in internal materials and structures. Deterioration or changes in stress distribution, etc. If these invisible damages (such as cracks, fatigue fractures, etc.) and the internal changes ...

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): G06F30/27G06N3/04G06N3/08G01H17/00G01P15/00
CPCG06F30/27G06N3/08G01H17/00G01P15/00G06N3/048G06N3/045
Inventor 郭彤张敏特宗跃然刘中祥韩达光
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