Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Integrated strength testing method based on neural network technology

A neural network and strength testing technology, applied in the direction of testing the hardness of materials, using sonic/ultrasonic/infrasonic waves to analyze solids, etc., can solve the problems of structural damage, increase the degree of structural damage, inaccurate test results, etc., to reduce damage and damage, The effect of reducing damage and accurate and reliable test results

Inactive Publication Date: 2008-11-12
SOUTHEAST UNIV
View PDF0 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As far as the number of core samples is concerned, too little can not fully reflect the strength of the measured concrete, and too much will increase the damage of the structure
Therefore, a little carelessness will cause inaccurate test results, cause structural damage, etc.
Although there is currently a method to determine the optimal number of drilled cores based on mathematical statistics theory, there is no standard for determining the parameters such as confidence and estimation accuracy in this method. In addition, manual analysis is required based on the number of core samples due to the estimation accuracy. Obtained by calculation, which greatly reduces the efficiency and operability of the ultrasonic-rebound-drilling core comprehensive strength measurement method based on mathematical statistics theory

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
  • Integrated strength testing method based on neural network technology
  • Integrated strength testing method based on neural network technology
  • Integrated strength testing method based on neural network technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention proposes a comprehensive strength testing method based on neural network technology, that is, ultrasonic-rebound-drilling core comprehensive strength testing method, such as figure 1shown. This method determines the coring position according to the structural analysis results, and then uses neural network technology, one of the most active frontier research topics in the world, to determine the optimal number of core samples. Neural network technology is a theoretical mathematical model of the human brain and its activities. It is composed of a large number of processing units interconnected in an appropriate way. It is a large-scale nonlinear adaptive system. The neural network not only simulates the biological nervous system in form, but also has some basic characteristics of the brain. From the perspective of the form of the system, from the neuron itself to the connection mode, it basically works in a similar way to the biological nervous syst...

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 comprehensive strength testing method of the neural network technique, which combines the advantages of three strength testing methods: supersonic, rebounding and core drilling, thus solving various disadvantages of the existing single strength testing technique. The basic principle of the comprehensive strength testing method includes that: firstly, the strength of structural concrete is tested in full dimensions with the supersonic-rebounding comprehensive method, and then the R-N-C benchmark curve is properly corrected by the core drilling method, wherein, the determination of the optimum drilling core number is solved by the neural network technique. Concrete materials are degraded to different extends as large quantity of engineering structures are being influenced by such factors as environmental corrosion and temperature change, and the method of the invention can, on the basis of ensuring accurate and reliable test results, greatly reduce the structural damages caused by the core drilling strength testing method, improve the analysis efficiency and operability of the supersonic-rebounding-core drilling comprehensive strength testing method, so the method of the invention has wide application prospects in the strength testing of various concrete works .

Description

technical field [0001] The invention relates to an ultrasonic-rebound-drilling comprehensive strength measurement method based on neural network technology, which is especially suitable for accurate strength testing of concrete structures widely used in engineering structures. Background technique [0002] At present, there are many methods for concrete strength testing of engineering structures, such as drilling core sampling method, rebound method, ultrasonic method, ultrasonic-rebound comprehensive method, nail shooting method, needle penetration method, after-installation pull-out method, compression method, etc. Shearing method and shock echo method etc. These methods have their own characteristics, and can solve the detection problem of structural concrete to a certain extent, but because concrete is a complex structural system composed of multi-phase composite materials, and the strength of concrete is also restricted by the test conditions. , is a comprehensive inde...

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): G01N29/04G01N3/52
Inventor 王浩张竞男李爱群王晨
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
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com