Lead bonding welding spot defect positioning and classifying method

Abstract

The invention discloses a lead bonding welding spot defect positioning and classifying method. The method comprises the following steps: 1) obtaining a bonded welding spot image by using an industrialcamera; 2) carrying out initial positioning on an area where a welding spot is located by utilizing an algorithm based on pixel neighborhood variance; 3) removing redundant non-welding-spot areas byusing a gray projection algorithm; 4) performing primary extraction on a region where the welding spot is located by using a region growing algorithm, and performing defect segmentation by using a level set method on the basis; 5) extracting linearly separable main characteristics of the welding spots by utilizing kernel principal component analysis; and 6) sending the extracted main features to arandom forest classifier for defect type classification, and giving welding parameter adjustment suggestions according to multi-classification results. Compared with other welding spot detection technologies, the lead bonding welding spot defect positioning and classifying method based on image processing and machine learning has the advantages of being high in precision, high in speed, high in intelligent level and the like, and has great application prospects in actual electronic industrial production.

Description

technical field [0001] The invention relates to the technical field of wire bonding solder joint defect location and classification, in particular to a wire bonding solder joint defect location and classification method based on image processing and machine learning. Background technique [0002] In the fields of scientific research and engineering applications, ultrasonic bonding has always played a very important role. Ultrasonic bonding is that the head of a welding tool with ultrasonic energy is pressed against the surface of the metal wire to be bonded with a certain pressure, and the vibration brought by the ultrasonic energy causes the metals in contact with each other to rub against each other and finally bond together tightly. The quality of solder joints directly determines the quality and reliability of chip manufacturing. For the detection of solder joints, the method widely used at home and abroad is to obtain the appearance of solder joints by imaging with ind...

AI Technical Summary

Problems solved by technology

For the detection of solder joints, the method widely used at home and abroad is to obtain the appearance of solder joints by imaging with industrial cameras, but the resolution of the collected original solder joint images is relatively high and contains a large number of background areas, so it is necessary to extract the area where the solder joints are located , the general methods include optical flow method, feature description method and gray level consistency matching (NCC) algorithm, but the above methods are only good for solder joint images with regular geometric shapes, and generally require similar machine vision problems. Design special algorithms according to actual scenarios

Images