Abstract
To improve the printed circuit board (PCB) manufacturing process, it is important to have an automatic inspection system that classifies information regarding defects in solder joints. This paper proposes a quality decision system for solder joint defect classification on a PCB. An experiment was conducted to demonstrate the application of this technique. The results showed that the inspection accuracy reached 94%, which is superior to the results achieved by other methods. The results of this study provide an effective solution for the inspection of the solder joint quality.
Keywords
This research was supported by the National Science Council of Taiwan, Project Number NSC 90-2218-E-131-012 and NSC 91-2218-E-131-005.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
This research was supported by the National Science Council of Taiwan, Project Number NSC 90-2218-E-131-012 and NSC 91-2218-E-131-005.
References
Chu CC, Jiang BC, Wang CC (2008) Modified gamma correlation method to enhance BGA surface image for surface defect inspection. Int J Prod Res 46(8):2165–2178
Jiang BC, Wang YM, Wang CC (2001) Bootstrap sampling techniques applied to PCB golden fingers defect classification study. Int J Prod Res 39(10):2215–2230
Jiang BC, Tasi SL, Wang CC (2002) Machine-vision based grey relational theory applied to IC marking inspection. IEEE Trans Semicond Manuf 15(4):531–539
Jiang BC, Wang CC, Chen PL (2004) Logistic regression tree applied to classify PCB golden finger defects. Int J Adv Manuf Technol 24(7):496–502
Jiang BC, Wang CC, Hau YN (2007) Machine vision and background remover-based approach for PCB solder joints inspection. Int J Prod Res 45(2):451–464
Jiang BC, Wang CC, Chen HJ, Chu CC (2010) Automatic bubble defect inspection for microwave communication substrates using multi-threshold technique based co-occurrence matrix. Int J Prod Res 48(8):2361–2371
Ko KW, Cho HS (2000) Solder joints inspection using a neural network and fuzzy rule-based classification method. IEEE Trans Electron Pack Manuf 23(2):93–103
Mardai KV (1970) Measures of multivariate skewness and kurtosis with applications. Biometrika 36:519–530
Oyeleye OU, Lehtihet EA (1999) Automatic visual inspection of surface mount solder joint defects. Int J Prod Res 37:1217–1242
Ripley BD (1996) Pattern recognition and neural networks. Cambridge University Press, New York
Smith SP, Jain AK (1988) A test to determine the multivariate normality of a dataset. IEEE Trans Pattern Anal Mach Intell 10:757–761
Wang CC, Jiang BC (2001) PCB solder joints defects detection and classification using machine vision. Int J Ind Eng 8(4):359–368
Wang CC, Jiang BC, Chou YS, Chu CC (2011) Multivariate analysis techniques-based image enhancement model for electronic products inspection. Int J Prod Res 49(15):2999–3021
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, CC. (2013). Machine Vision-Aided Quality Decision System for Solder Joint Defect Evaluation. In: Qi, E., Shen, J., Dou, R. (eds) The 19th International Conference on Industrial Engineering and Engineering Management. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37270-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-37270-4_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37269-8
Online ISBN: 978-3-642-37270-4
eBook Packages: Business and EconomicsBusiness and Management (R0)