Zümray DOKUR, Tamer ÖLMEZ, Ceren TÜRER AKDENİZ

Detection of BGA solder defects from X-ray images using deep neural networkneural network

In the literature it is observed that complex image processing operations are used in the classification of Ball Grid Array (BGA) X-ray images, however high classification results were not achieved. In recent years, it has been shown that deep learning methods are very successful especially in classification problems. In this study, a new deep neural network (DNN) model is proposed to classify the BGA X-ray images. The proposed DNN model contains feature extractor layers and a minimum distance classifier. Since the proposed network consists of less number of layers (4 convolution layers and 1 fully connected layer), determination of the hyper-parameters of the network and training of the network are accomplished in a short time. BGA X-ray images are categorized into 4 classes according to the conditions of the solder joints: normal, short-circuit, bonding defect and void defect. The dataset used in this study is comprised of 67, 76, 53 and 76 images for these classes, respectively. 80% of all data is allocated for the training set and the remaining 20% is allocated for the test set. Compared with the existing methods in the literature, a very high success rate of 97% is achieved for the classification of BGA X-ray images with the proposed method

PDF

___

[1] IPC-A-610 Revision G. Acceptability of Electronic Assemblies. London, UK: IPC Press, 2017. ISBN: 978-1-61193- 334-5.
[2] Roh YJ, Ko KW, Cho HS, Kim HC, Joo HN et al. Inspection of ball grid array (BGA) solder joints using X-ray cross-sectional images. SPIE Conference on Machine Vision Systems for Inspection and Metrology VIII, vol. 3836; Boston, USA; 1999. pp. 168-178.
[3] Sumimoto T, Maruyama T, Yoshiharu A, Goto S, Mondou M, et al. Development of image analysis for detection of defects of BGA by using X-ray images. Proceedings of the 20th IEEE Instrumentation and Measurement Technology Conference; Colorado, USA; 2003. pp. 1131-1136.
[4] Ma J-Q, Kong F-H, Ma P-J, Su XH. Detection of defects at BGA solder joints by using X-ray imaging. The Fourth International Conference on Machine Learning and Cybernetics; Guangzhou, China; 2005. pp. 5139-5143.
[5] Laghari MS, Hijer R, Khuwaja GA. Efficient techniques for BGA solder joint identification in low resolution X-ray images. IEEE GCC Conference and Exhibition; United Arab Emirates; 2011. pp. 128-131.
[6] Peng SH, Nam HD. Void defect detection in ball grid array X-ray images using a new blob filter. Journal of Zhejiang University SCIENCE C (Computers, Electronics) 2012; 13 (11): 840-849.
[7] Sumimoto T, Maruyama T, Azuma Y, Goto S, Mondou M et al. Detection of defects of BGA by tomography imaging. Journal of Systemics, Cybernetics and Informatics 2013; 3: 10-14.
[8] Laghari MS, Memon QA. Identification of faulty BGA solder joints in X-ray images. International Journal of Future Computer and Communication 2015; 4 (2): 122-125.
[9] Sankaran V, Kalukin AR, Kraft RP. Improvements to X-ray laminography for automated inspection of solder joints. IEEE Transaction on Components Packaging and Manufacturing Technology-Part C 1998; 21 (2): 148-154
[10] Erkaymaz O, Ozer M, Perc M. Performance of small-world feedforward neural networks for the diagnosis of diabetes. Applied Mathematics and Computation 2017; 311: 22-28.
[11] Fister I, Suganthan PN, Fister Jr I, Kamal SM, Al-Marzouki FM et al. Artificial neural network regression as a local search heuristic for ensemble strategies in differential evolution. Nonlinear Dynamics 2016; 84: 895-914