Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Machine learning-based image recognition algorithm for aviation aluminum alloy surface cracking

An aluminum alloy surface and machine learning technology, applied in the field of image recognition algorithms based on machine learning, can solve problems that do not meet the real-time requirements in the aviation field, are easily ignored, and have a large time cost, so as to prevent aircraft structure failure and reduce Security incidents, high-precision effects

Pending Publication Date: 2020-12-01
CIVIL AVIATION UNIV OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing algorithms need to spend a lot of time in practical applications, which do not meet the real-time requirements of the aviation field
In order to improve the accuracy and real-time performance of crack image recognition, this project studied the cracks of aluminum alloy specimen (AA7075) in normal temperature salt solution, and found the following problems: (1) Because some cracks are very small, it is very difficult to It is difficult to determine the initiation position of the crack; (2) There are various noises on the surface of the test piece, which interferes with the accuracy of the crack identification results; (3) The thinnest part of the crack top is usually only 1 pixel, which is easy to be ignored

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
  • Machine learning-based image recognition algorithm for aviation aluminum alloy surface cracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.

[0018] refer to figure 1 , an image recognition algorithm based on machine learning for surface cracking of aerospace aluminum alloys, including the following steps:

[0019] S1. Use an adaptive filtering algorithm based on semi-supervised learning to process the image, which specifically includes two parts of learning content: the first learning process, firstly filter every 50 gray values ​​from 0-255, and compare To analyze all the learning results and determine the best gray value interval, we use 500 samples, of which 200 are used as learning samples and 300 are used as testing samples. Divide 255 pixels equally every 50 pixels into 52 gray values, 0, 50, 100, ...

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 the technical field of aviation aluminum alloy, in particular to a machine learning-based image recognition algorithm for aviation aluminum alloy surface cracking, which comprises the following steps: S1, processing an image by adopting a semi-supervised learning-based adaptive filtering algorithm; s2, segmenting the image by adopting a morphological processing method, anddetermining the initiation edge of the crack; s3, introducing a morphological concept into a connected algorithm of region growth based on image growth to locate the position of a crack; the method aims at overcoming the defects of poor accuracy and real-time performance of aircraft surface material crack image recognition in the aviation field in the prior art. The crack recognition algorithm ishigh in speed and high in precision, can monitor whether cracks appear on the aluminum alloy material on the surface of the aircraft and the lengths of the cracks in real time, and can prevent aircraft structure failure and reduce safety accidents caused by aircraft surface material failure.

Description

technical field [0001] The invention relates to the technical field of aviation aluminum alloys, in particular to a machine learning-based image recognition algorithm for surface cracking of aviation aluminum alloys. Background technique [0002] Aviation aluminum alloy has the advantages of low density and high strength, and is widely used in some important load-bearing structures of aircraft such as skin, fuselage, landing gear, bulkhead, wing rib, etc. Aluminum alloy materials are highly sensitive to the environment, and are prone to localized corrosion such as pitting corrosion, intergranular corrosion, and exfoliation corrosion during service. Stress corrosion cracking of aerospace aluminum alloys is one of the important failure modes of aircraft aluminum alloy structures, which brings great hidden dangers to the safe operation of aircraft. Aiming at the stress corrosion cracking of aviation aluminum alloys in salt solution, analyzing the laws of crack initiation and p...

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 Applications(China)
IPC IPC(8): G06K9/34G06T7/155G06T7/187
CPCG06T7/155G06T7/187G06V10/267
Inventor 徐俊洁邓武赵慧敏宋英杰
Owner CIVIL AVIATION UNIV OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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