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

An intelligent recognition method for patch defects of printed circuit boards based on image processing

A printed circuit and image processing technology, which is applied in the field of intelligent identification of printed circuit board patch defects based on image processing, can solve the problems of misjudgment of patch defects and excessive sensitivity of nuances, and achieve the effect of improving the yield

Active Publication Date: 2022-02-15
WUHAN FINEMEMS
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Based on the technical problems existing in the background technology, the present invention proposes an intelligent identification method for printed circuit board patch defects based on image processing, which has the characteristics of accurately and efficiently identifying circuit board patch defects and classifying and identifying defects, and solves the problem of The existing image comparison method is too sensitive to subtle differences, which may easily cause misjudgment of patch defects

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
  • An intelligent recognition method for patch defects of printed circuit boards based on image processing
  • An intelligent recognition method for patch defects of printed circuit boards based on image processing
  • An intelligent recognition method for patch defects of printed circuit boards based on image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Such as Figure 4 shown. Insufficient overlap defect: One end of the chip component deviates too much from one of the two terminals, too little or no contact at all, and insufficient overlap at the end will directly affect the conduction of the component. The cause of the defect may be misalignment of the placement machine.

[0040] recognition methods:

[0041] First, obtain the top view and side view of the printed circuit board including terminals and chip components after patching;

[0042] Perform grayscale processing on the acquired image to obtain a grayscale image. The grayscale processing adopts any one of the maximum value method, the average value method, and the weighted average method; smoothing the grayscale image, which is also called fuzzy processing, It is a simple and frequently used image processing method. The smoothing process of this method uses the existing and common Gaussian filter;

[0043] Use the Canny edge detection method to perform edge...

Embodiment 2

[0049] recognition methods:

[0050] Such as Figure 5 shown. Component side anti-defect: the plane of the chip component is not parallel to the plane of the two terminals, and the overlapping contact between the two terminals and the chip component is not 100%, the cause of this defect may be the terminal surface or the metal of the chip component The surface is not completely wet;

[0051] First, obtain the top view and side view of the printed circuit board including terminals and chip components after patching;

[0052] Perform grayscale processing on the acquired image to obtain a grayscale image. The grayscale processing adopts any one of the maximum value method, the average value method, and the weighted average method; smoothing the grayscale image, which is also called fuzzy processing, It is a simple and frequently used image processing method. The smoothing process of this method uses the existing and common Gaussian filter;

[0053] Use the Canny edge detectio...

Embodiment 3

[0058] Such as Figure 6 shown. Component riser defect: one end of the chip component is connected to the terminal, the other end is not in contact with the other terminal, and is in a "lifted" state, resulting in the chip component not being connected to the terminal. The cause of this defect may be the terminal The surface or the metal surface of the chip component is not completely wet, and the pressure of the placement machine is unbalanced.

[0059] recognition methods:

[0060] First, obtain the top view and side view of the printed circuit board including terminals and chip components after patching;

[0061] Perform grayscale processing on the acquired image to obtain a grayscale image. The grayscale processing adopts any one of the maximum value method, the average value method, and the weighted average method; smoothing the grayscale image, which is also called fuzzy processing, It is a simple and frequently used image processing method. The smoothing process of t...

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 present invention relates to the technical field of circuit board defect identification, in particular to an image processing-based intelligent identification method for patch defects of printed circuit boards. The edge detection method obtains the edge of the image; enters the terminal coordinates to obtain the outline and coordinate point sequence of the chip component; and calculates the difference between the coordinate point sequence of the chip component and the coordinate point of the qualified chip component, when the difference When the defect threshold is exceeded, there is a defect, otherwise the patch is qualified. The present invention uses the convolutional neural network algorithm, Canny edge detection, and the coordinate positioning of terminals and chip components to determine whether there is a defect in the patch, and uses different algorithms to determine different types of defects, and responds to defects in a timely manner while also outputting the results. The cause of the defect allows the staff to adjust the processing equipment including the placement machine in time to improve the yield and remove defective products in time.

Description

technical field [0001] The invention relates to the technical field of circuit board defect identification, in particular to an image processing-based intelligent identification method for patch defects of printed circuit boards. Background technique [0002] Chip resistors, that is, chip fixed resistors, are one of the metal glass glaze resistors. In the production of chip resistors, metal powder and glass glaze powder are mixed, and printed on the substrate by screen printing to make a finished product. Printed circuit board patches have subtle differences in patch position, angle, solder joint shape and other characteristics, but relative to the size of the patch, the influence of such subtle differences cannot be ignored. However, traditional image recognition methods, such as image contrast methods, are too sensitive to subtle differences and are prone to misjudgment. However, other morphological image recognition algorithms, such as wavelet transform and Hough transf...

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 Patents(China)
IPC IPC(8): G06T7/00G06T7/13G06T5/00G06T5/20G06N3/04G06N3/08
CPCG06T7/0004G06T7/13G06T5/002G06T5/007G06T5/20G06N3/08G06T2207/20081G06T2207/20084G06T2207/20192G06T2207/30141G06N3/045
Inventor 王小平曹万熊波陈明艳
Owner WUHAN FINEMEMS