Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-fuzzy reasoning cascaded primer side defect classification and damage degree analysis method

A technology of fuzzy reasoning and defect classification, applied in reasoning methods, image analysis, image data processing, etc., can solve problems such as low precision, complex production process, high false detection rate and missed detection rate of primer, and improve speed and accuracy , avoid mutual interference, and eliminate the effect of false detection

Active Publication Date: 2021-07-09
XIANGTAN UNIV
View PDF11 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the production process of the primer, due to the complex production process and numerous production links, the produced primer inevitably has appearance defects such as gaps, scratches, pitting, impurities, light oxidation, heavy oxidation, and poor size.
[0004] In this case, the traditional method of detecting primer appearance defects by observing the appearance of the primer with the naked eye is easily affected by subjective factors such as human visual fatigue and emotion, which easily leads to a high false detection rate and missed detection rate of the primer. , and the traditional method has low efficiency and low precision

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
  • Multi-fuzzy reasoning cascaded primer side defect classification and damage degree analysis method
  • Multi-fuzzy reasoning cascaded primer side defect classification and damage degree analysis method
  • Multi-fuzzy reasoning cascaded primer side defect classification and damage degree analysis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The block diagram of the technical solution of the present invention is as figure 1 As shown, the specific steps are:

[0019] S100. Obtain the image I by thresholding the primer side image I 1 , to I 1 Use the run method to extract the area, length, width and gray value of each connected region in the image, where the area of ​​the i-th connected region is represented by S F Express, long with L D Indicates that W is used for wide H Indicates that the average gray value is represented by A GV Represent, and calculate the aspect ratio of the i-th connected region as L D / W H ;

[0020]

[0021] In the formula, x and y are the horizontal and vertical coordinates of the pixel, and 75 is the threshold;

[0022] S200. To Image I 1 Carry out expansion operation to get pitting weight image I 2 , using the run-length method to extract I 2 The area of ​​each connected region in the image, where the area of ​​the i-th connected region is denoted as S D ; The conne...

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 multi-fuzzy reasoning cascaded primer side defect classification and damage degree analysis method. The method comprises the following steps: firstly, acquiring an image I1 from a primer side image I by adopting a threshold method, extracting the area, length, width and gray average value of each connected region in the I1 by adopting a run-length method, and calculating a length-width ratio; secondly, performing expansion operation on the image I1 to obtain a pocking mark weight image I2, and extracting the area of each connected region in the I2 and the number of scatter points in the I1 corresponding to each connected region in the I2; and finally, fuzzifying the extracted data, sending the fuzzified data into a multi-fuzzy reasoning cascade system, sequentially classifying hard spots and non-hard spots, scratches and non-scratches, and heavy oxidation, light oxidation and impurities, and evaluating the damage degree of the hard spots and non-hard spots, scratches and non-scratches, heavy oxidation, light oxidation and impurities. The invention has the advantages that a plurality of fuzzy reasoning classifiers are combined to realize defect classification and damage degree analysis, mutual interference among multiple defects is avoided, the classification precision is improved, and the primer defect false detection condition caused by subjectivity and the like in manual detection is eliminated.

Description

technical field [0001] The invention relates to a primer defect analysis method based on a multi-fuzzy reasoning cascade system, in particular to a primer side defect classification and damage degree analysis method. Background technique [0002] Bullets are an indispensable part of weapons and equipment. Optimizing the production process of weapons and equipment and improving the yield rate will help improve the input-output ratio and ensure the needs of real-time combat. Among them, the primer is the key ignition part at the bottom of the bullet. The primer has the characteristics of long storage time, high ignition stability and safe use. It is widely used in the ignition device at the bottom of various bullets and guns. [0003] The primer is cylindrical as a whole, and the shell material is H68 copper. The inside of the shell is filled with primer, and it is covered and pressed with a paper circle brushed with shellac paint. In the production process of the primer, due...

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): G06T7/00G06T7/11G06T7/136G06T7/155G06T7/187G06T7/62G06T7/60G06N5/04
CPCG06T7/0004G06T7/11G06T7/136G06T7/155G06T7/187G06T7/62G06T7/60G06N5/048
Inventor 李赛斯周佳慧罗校萱朱江田淑娟刘馨文
Owner XIANGTAN UNIV