Welding spot defect identifying method

Abstract

The invention provides a welding spot defect identifying method which comprises a step of performing characteristic extraction on the acquired welding spot image information and a step of identifying the welding spot defect according to the ways of identifying, fuzzy inference, neutral network according to the characteristics and the like, and specifically comprises the following steps of: 1) obtaining a sample for training an artificial neural network according to the principle of an orthogonal test based on the welding spot shape theory; 2) training the artificial neural network by use of an improved neural network algorithm to obtain a network for predicting the possibility of various defects of the welding spots; and 3) performing image processing on the actual welding spot, extracting the shape quality characteristic as the input of the trained artificial neural network, and performing forward calculation by use of the trained network to realize identification of the welding spot defect. In the invention, as the BP neural network is improved and the genetic algorithm is introduced into the neural network algorithm training, the defects of slow convergence, easy trap in local optimal solution and the like of the neural network are solved, and the network performance is improved to some degree so as to realize defect identification of complicated welding spots.

Description

technical field [0001] The invention relates to microelectronic packaging and assembly technology, in particular to a method for identifying solder joint defects. Background technique [0002] Solder joint defect identification technology is to rely on advanced optical or electromagnetic technology to collect image information of solder joints without destroying the actual solder joint shape, process the collected image information of solder joints, and extract the information that affects the shape of solder joints. Some important features of these information, and various analysis, processing, differentiation and identification of this information, to confirm its solder joint defects. At present, for the defect identification of solder joints, it is mainly through feature extraction of the collected image information of solder joints, and then using methods such as threshold discrimination, fuzzy reasoning and neural networks to identify solder joint defects. However, the ...

AI Technical Summary

Problems solved by technology

At present, for the defect identification of solder joints, it is mainly through feature extraction of the collected image information of solder joints, and then using methods such as threshold discrimination, fuzzy reasoning and neural networks to identify solder joint defects. However, the neural network has a convergence Slow and easy to fall into local optimal solution and other defects

Images