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

Warp and weft intersection positioning method for weaving ceramic-based composite material

A composite material and positioning method technology, which is applied in the direction of material analysis, material analysis, and image data processing using wave/particle radiation. Wide, improve the recognition accuracy, simple operation effect

Active Publication Date: 2020-09-25
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current recognition of woven CMCs XCT slices is generally the whole slice input and the mesostructure classification, and there will be inaccurate recognition of the intersection of warp and weft yarns.
[0004] In summary, there is no report on the positioning method of the intersection position of warp and weft yarns in XCT slices of woven CMCs.

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
  • Warp and weft intersection positioning method for weaving ceramic-based composite material
  • Warp and weft intersection positioning method for weaving ceramic-based composite material
  • Warp and weft intersection positioning method for weaving ceramic-based composite material

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The present invention is described in further detail now in conjunction with accompanying drawing.

[0056] first part:

[0057] Step 1. Construct a plain weave dataset for training the support vector machine algorithm, with a total of M sheets and a size of [Size_X, Size-Y]. All the pictures in the dataset are named in the format of "T_Cla.jpg". Such as figure 1 As shown, T is a positive integer representing the number of pictures, which is incremented sequentially from 0; Cla is the number representing the category of the picture, with a value of 0 or 1, 1 belongs to the picture at the intersection, and 0 is the picture at the non-intersection. In the embodiment, there are 200 pictures in the data set, and the size is [150, 120].

[0058] Step 2. According to the principle of random allocation of the data set, extract the training set and test set with a ratio of 4:1, 160 and 40 respectively.

[0059] Step 3. The directional gradient histogram algorithm uses the f...

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 warp and weft intersection positioning method for weaving a ceramic-based composite material. Firstly, a direction gradient histogram is combined with a support vector machine to locate an area, containing warp and weft intersection positions, of a whole XCT slice; each positioned cross area can be positioned for multiple times at the same time, so that whether the crossareas are the same area or not is calculated according to the overlapping area ratio, inaccurate cross positions are removed and recognized according to the accuracy of each frame, and multiple sub-images containing warp and weft cross positions are output. Afterwards, lines of corresponding angles of warp and weft yarns in the sub-pictures are obtained through Hough transform, multiple vertexes of the warp and weft yarn intersection positions are obtained according to the straight line intersection principle, and four vertexes of a warp and weft yarn intersection area are extracted from the vertexes according to the characteristics of the intersection positions. The warp and weft intersection positioning method provided by the invention can further improve the identification accuracy of the warp and weft intersection, can be used for CMCs continuous XCT slices of plain weaving, 2.5 D weaving and other types, and is wide in application range and simple to operate.

Description

technical field [0001] The invention belongs to the field of mesostructure identification of woven ceramic matrix composite materials, and in particular relates to a method for locating intersections of warp and weft yarns of woven ceramic matrix composite materials. Background technique [0002] Ceramic matrix composites (CMCs, Ceramic Matrix Composites) are composed of continuous reinforced fiber bundles, interface and matrix. Compared with metal matrix composites, they have the characteristics of low density, better temperature resistance and corrosion resistance. Ideal candidate material for end pieces. Braided CMCs with complex preform structures have attracted extensive attention due to their excellent interlaminar shear resistance, impact resistance, and fracture toughness. [0003] X-ray computed tomography (XCT, X-ray computed tomography) is a non-destructive testing technology, which has the characteristics of not destroying the object but can clearly observe the ...

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): G06T7/70G06K9/46G06K9/62G01N23/046
CPCG06T7/70G01N23/046G06T2207/10116G06T2207/20081G06T2207/30124G06V10/50G06F18/2411
Inventor 贾蕴发高希光宋迎东于国强方光武张盛董洪年
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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