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

Weld defect ultrasound phased array sector scanned image feature extraction method

A technology of welding defects and ultrasonic phase control, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as long learning time, large data dimension, complex classification model, etc.

Inactive Publication Date: 2013-08-28
HARBIN INST OF TECH
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problems of the existing welding defect classification and recognition research technology that directly adopts defect ultrasonic phased array sector scanning images for recognition, resulting in too large data dimensions, complex classification models, and long learning time, the invention provides a welding Feature Extraction Method of Defect Ultrasonic Phased Array Sector Scanning Image

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
  • Weld defect ultrasound phased array sector scanned image feature extraction method
  • Weld defect ultrasound phased array sector scanned image feature extraction method
  • Weld defect ultrasound phased array sector scanned image feature extraction method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0057] Specific implementation mode one: reference figure 2 , the ultrasonic phased array sector scanning detection is carried out on the welding sample, the initial angle of the sector scanning detection is 30°, the end angle is 70°, and the scanning step is 0.25°.

[0058] refer to image 3 , the specific process of a welding defect ultrasonic phased array sector scanning image feature extraction method described in this embodiment is as follows:

[0059] Step 1. Take n defect images, each defect image contains p data, where p=k×l×t, k is the number of ultrasonic A signals in each defect image, l is the data contained in each ultrasonic A signal, t is the echo amplitude and defect three-dimensional coordinate information contained in the data, so a total of n×p data are obtained, and the defect image data matrix X is as follows:

[0060] X = x 11 ...

Embodiment

[0076] Embodiment: the feature extraction process of welding defect sector scan image is as follows:

[0077] 200 images were selected from the ultrasonic phased array sector scan images of pores, cracks, incomplete fusion and incomplete penetration defects, and a total of 800 images of the four defects. Each defect image contains 161 beams of ultrasonic A signals, and each beam of ultrasonic A signals contains 1520 points of data, and each point of data contains four pieces of information, including defect echo amplitude and three-dimensional coordinates, so that the amount of data contained in each defect image is 978880, the data matrix X of 800 defect images is as follows:

[0078]

[0079] The covariance matrix Σ of the calculated defect image data matrix is:

[0080]

[0081] Then get the eigenvalue λ of the covariance matrix Σ, and arrange it from large to small as:

[0082] λ = [31.1, 4.5, ..., 0.00001]

[0083] The calculated orthonormal eigenvector correspondi...

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 provides a weld defect ultrasound phased array sector scanned image feature extraction method and belongs to the technical field of weld defect research. The weld defect ultrasound phased array sector scanned image feature extraction method solves the problems that when weld defects are classified and identified, defect ultrasound phased array sector scanned images are directly utilized to conduct defect identification, image data are large in dimensionality, a disaggregated model is complex, and learning time is long. The weld defect ultrasound phased array sector scanned image feature extraction method mainly includes the steps of setting up a defect image data array by using the weld defect ultrasound phased array sector scanned images, calculating a covariance array of the defect image data array, solving a feature value and a feature vector of the covariance array, determining the number of main components of each defect image, and setting up a weld defect feature expression function. The weld defect ultrasound phased array sector scanned image feature extraction method keeps a large amount of information of the defect images, represents the type of defects, ensures a correct identification rate of the disaggregated model, reduces dimensionality of defect image data, and greatly improves the learning speed of the disaggregated model.

Description

technical field [0001] The invention relates to an image feature extraction method of ultrasonic phased array sector scanning of welding defects, which belongs to the technical field of welding defect research. Background technique [0002] Before studying the intelligent recognition of welding defects, it is necessary to extract the features of ultrasonic phased array sector scanning images of defects (hereinafter referred to as defect images). Feature extraction is one of the key steps in defect classification and identification. Its principle is to select the most representative features and reduce the dimensionality of defect image data. Due to the diversity of defect shapes in the weld, the shape, size and texture of the defects in the sector scanning image are complex, which makes feature extraction more difficult. If feature extraction is not performed, the sector scan image is directly used. For defect recognition, the dimensionality of the defect image data is too ...

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): G06K9/46
Inventor 栾亦琳刚铁冯吉才张秉刚孙涛
Owner HARBIN INST OF TECH
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