Research On Application Of Wavelet Transforms To Solder Joints Diagnoses

With surface mounting technology (SMT) to a higher density, smaller size, more complex mixture of PCB-depth development, the solder joints acting as connecting bridges between the board and components play a decisive role. SMT assembly processes are stepped by solder paste printing, component placement, post reflow, and defects arising from solder paste printing process and post reflow processes take a critical part. It is important to discover solder joint defects in a timely manner for the assurance of board's quality.Because the destructive testing damages the electronic device in some respects, so it is not adapt to carry out in pipelining. It is an exigent requirement for nowadays electronic industry to design non destructive ,effective and low-cost testing methods and technology. In view that most of methods are so dependent that recognition rates strongly tie to their illumination systems and limited number of defected solder joints could be obtained ,this thesis proposes a method of solder joints inspection based on both Wavelet Transform (WT) and least squares support vector machines (LS-SVM).Main work this paper completed are: completing wavelet feature extraction and geometric feature extraction from given solder joints by applying the WT algorithm and series of image processing algorithms, these two kinds of features and their combined feature are seletced to the inputs of LS-SVM on the implementation of the identification, at the same time their respective advantages are made; Designing two LS-SVM detection models and bringing in cross-validation and grid search method to obtain their optimal training parameters, eventually these two models are applied in pot detection; experimental analyses proves that the second one does better. Additionally, in light of image's noise and fuzzy made by CCD camera, adopting two image preprocessing methods, and noises are suppressed effectively.