Electronic component X-ray inspection defect automatic identification method

Abstract

The invention discloses an electronic component X-ray inspection defect automatic identification method. The method comprises the following steps: preprocessing an X-ray image; marking a sample manually in a semi-automatic or automatic manner, and dividing defect types of to-be-detected electronic components into three types, namely cavity defects, consistency defects and angle defects, according to the packaging and defect forms of electronic components; and detecting four types of cavity defects by using a semantic segmentation method based on a convolutional neural network. The convolutional neural network is trained through a large number of samples, accurate segmentation of various cavity defects is realized, and the automatic defect identification efficiency is greatly improved. Meanwhile, a welding area, a sealing area and the like of a chip are detected through a gray projection method, and the qualification of the chip is judged according to corresponding judgment criteria. The problems that automatic calculation cannot be carried out and judgment is carried out purely by manpower in the prior art are solved, and the interference problem of cavities in a welding interface of a substrate and a tube shell in a hybrid integrated circuit is solved.

Description

technical field [0001] The invention relates to the technical field of automatic identification of defects in X-ray inspection of electronic components, in particular to a method for automatic identification of defects in X-ray inspection of electronic components. Background technique [0002] Military electronic components are the basic components of national defense military electronic systems, mainly including microelectronic devices such as semiconductor discrete devices and integrated circuits, as well as special devices such as relays and sensors. Military electronic components are the material guarantee of information systems such as nuclear, aviation, aerospace, ships, weapons, and electronics. Their stability and reliability directly affect the functions and performance indicators of information systems. [0003] Packaging defects of military electronic components is one of the main factors affecting their quality. X-ray inspection is a means of non-destructive tes...

AI Technical Summary

Problems solved by technology

[0006] At present, the defect detection of electronic components in China mainly focuses on the related research of printed circuit board (PCB) solder joint defect detection, mounted component detection and SMT surface packaging, etc., and the detection of component chip images few methods

Images