Science China Technological Sciences

, Volume 62, Issue 9, pp 1512–1519 | Cite as

Automated X-ray recognition of solder bump defects based on ensemble-ELM

  • Lei SuEmail author
  • LingYu WangEmail author
  • Ke Li
  • JingJing Wu
  • GuangLan Liao
  • TieLin Shi
  • TingYu Lin


Solder bumps realize the mechanical and electrical interconnection between chips and substrates in surface mount components, such as flip chip, wafer level packaging and three-dimensional integration. With the trend to smaller and lighter electronics, solder bumps decrease in dimension and pitch in order to achieve higher I/O density. Automated and nondestructive defect inspection of solder bumps becomes more difficult. Machine learning is a way to recognize the solder bump defects online and overcome the effect caused by the human eye-fatigue. In this paper, we proposed an automated and nondestructive X-ray recognition method for defect inspection of solder bumps. The X-ray system captured the images of the samples and the solder bump images were segmented from the sample images. Seven features including four geometric features, one texture feature and two frequency-domain features were extracted. The ensemble-ELM was established to recognize the defects intelligently. The results demonstrated the high recognition rate compared to the single-ELM. Therefore, this method has high potentiality for automated X-ray recognition of solder bump defects online and reliable.

automated recognition solder bump X-ray ensemble-ELM 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



  1. 1.
    Tu K N, Tian T. Metallurgical challenges in microelectronic 3D IC packaging technology for future consumer electronic products. Sci China Technol Sci, 2013, 56: 1740–1748CrossRefGoogle Scholar
  2. 2.
    Mustafa M, Suhling J C, Lall P. Experimental determination of fatigue behavior of lead free solder joints in microelectronic packaging subjected to isothermal aging. MicroElectron Reliability, 2016, 56: 136–147CrossRefGoogle Scholar
  3. 3.
    Li J, Liao H, Ge D, et al. An electromechanical model and simulation for test process of the wafer probe. IEEE Trans Ind Electron, 2017, 64: 1284–1291CrossRefGoogle Scholar
  4. 4.
    Li J, Tian Q, Zhang H, et al. Study on dipping mathematical models for solder flip-chip bonding in microelectronics packaging. IEEE Trans Ind Inf, 2018, 1Google Scholar
  5. 5.
    Zhang J, Wang X, Zhu Y, et al. Molecular dynamics simulation of the melting behavior of copper nanorod. Comput Mater Sci, 2018, 143: 248–254CrossRefGoogle Scholar
  6. 6.
    Li J, Liu L, Deng L, et al. Interfacial microstructures and thermodynamics of thermosonic Cu-wire bonding. IEEE Electron Device Lett, 2011, 32: 1433–1435CrossRefGoogle Scholar
  7. 7.
    Lu X N, Shi T L, Wang S Y, et al. Intelligent diagnosis of the solder bumps defects using fuzzy c-means algorithm with the weighted coefficients. Sci China Technol Sci, 2015, 58: 1689–1695CrossRefGoogle Scholar
  8. 8.
    Fan M, Wei L, He Z, et al. Defect inspection of solder bumps using the scanning acoustic microscopy and fuzzy svm algorithm. MicroElectron Reliability, 2016, 65: 192–197CrossRefGoogle Scholar
  9. 9.
    Shih T I, Lin Y C, Duh J G, et al. Electrical characteristics for Sn-Ag-Cu solder bump with Ti/Ni/Cu under-bump metallization after temperature cycling tests. J Elec Materi, 2006, 35: 1773–1780CrossRefGoogle Scholar
  10. 10.
    Cheng S, Huang C M, Pecht M. A review of lead-free solders for electronics applications. MicroElectron Reliability, 2017, 75: 77–95CrossRefGoogle Scholar
  11. 11.
    Xiao C, He H, Li J, et al. An effective and efficient numerical method for thermal management in 3d stacked integrated circuits. Appl Thermal Eng, 2017, 121: 200–209CrossRefGoogle Scholar
  12. 12.
    Su L, Shi T, Liu Z, et al. Nondestructive diagnosis of flip chips based on vibration analysis using pca-rbf. Mech Syst Signal Processing, 2017, 85: 849–856CrossRefGoogle Scholar
  13. 13.
    Kuo C F J, Wu H C. Application of robust color composite fringe in flip-chip solder bump 3-d measurement. Optics Lasers Eng, 2017, 91: 261–269CrossRefGoogle Scholar
  14. 14.
    Brand S, Czurratis P, Hoffrogge P, et al. Extending acoustic microscopy for comprehensive failure analysis applications. J Mater Sci-Mater Electron, 2011, 22: 1580–1593CrossRefGoogle Scholar
  15. 15.
    Liao G, Du L, Su L, et al. Using RBF networks for detection and prediction of flip chip with missing bumps. MicroElectron Reliability, 2015, 55: 2817–2825CrossRefGoogle Scholar
  16. 16.
    Su L, Shi T, Xu Z, et al. Defect inspection of flip chip solder bumps using an ultrasonic transducer. Sensors, 2013, 13: 16281–16291CrossRefGoogle Scholar
  17. 17.
    Hervé M B, Moraes M, Almeida P, et al. Functional test of mesh-based nocs with deterministic routing: Integrating the test of interconnects and routers. J Electron Test, 2011, 27: 635–646CrossRefGoogle Scholar
  18. 18.
    Su L, Liao G, Shi T, et al. Intelligent diagnosis of flip chip solder bumps using high-frequency ultrasound and a naive bayes classifier. insight, 2018, 60: 264–269CrossRefGoogle Scholar
  19. 19.
    Lu X N, Liu F, He Z Z, et al. Defect inspection of flip chip package using sam technology and fuzzy c-means algorithm. Sci China Technol Sci, 2018, 61: 1426–1430CrossRefGoogle Scholar
  20. 20.
    Ong T Y, Samad Z, Ratnam M M. Solder joint inspection with multi-angle imaging and an artificial neural network. Int J Adv Manuf Technol, 2008, 38: 455–462CrossRefGoogle Scholar
  21. 21.
    Chai T C, Wong B S, Bai W M, et al. A novel defect detection technique using active transient thermography for high density package and interconnections. In: Proceedings of the 53rd Electronic Components and Technology Conference. New Orleans, 2003. 920–925Google Scholar
  22. 22.
    Lu X, Liao G, Zha Z, et al. A novel approach for flip chip solder joint inspection based on pulsed phase thermography. NDT E Int, 2011, 44: 484–489CrossRefGoogle Scholar
  23. 23.
    Semmens J E, Kessler L W. Application of acoustic frequency domain imaging for the evaluation of advanced micro electronic packages. MicroElectron Reliability, 2002, 42: 1735–1740CrossRefGoogle Scholar
  24. 24.
    Zhang G M, Zhang C Z, Harvey D M. Sparse signal representation and its applications in ultrasonic NDE. Ultrasonics, 2012, 52: 351–363CrossRefGoogle Scholar
  25. 25.
    Brand S, Czurratis P, Hoffrogge P, et al. Automated inspection and classification of flip-chip-contacts using scanning acoustic microscopy. MicroElectron Reliability, 2010, 50: 1469–1473CrossRefGoogle Scholar
  26. 26.
    Tang W, Jing B, Huang Y F, et al. Feature extraction for latent fault detection and failure modes classification of board-level package under vibration loadings. Sci China Technol Sci, 2015, 58: 1905–1914CrossRefGoogle Scholar
  27. 27.
    Liu S, Ume I C, Achari A. Defects pattern recognition for flip-chip solder joint quality inspection with laser ultrasound and interferometer. IEEE Trans Electron Packag Manufact, 2004, 27: 59–66CrossRefGoogle Scholar
  28. 28.
    Zhang L Z, Ume I C, Gamalski J, et al. Study offlip chip solder joint cracks under temperature cycling using a laser ultrasound inspection system. IEEE Trans Comp Packag Technol, 2009, 32: 120–126CrossRefGoogle Scholar
  29. 29.
    Erdahl D S, Allen M S, Ume I C, et al. Structural modal analysis for detecting open solder bumps on flip chips. IEEE Trans Adv Packag, 2008, 31: 118–126CrossRefGoogle Scholar
  30. 30.
    Liu J, Shi T, Xia Q, et al. Flip chip solder bump inspection using vibration analysis. Microsyst Technol, 2012, 18: 303–309CrossRefGoogle Scholar
  31. 31.
    Shen J, Chen P, Su L, et al. X-ray inspection oftsv defects with self-organizing map network and otsu algorithm. MicroElectron Reliability, 2016, 67: 129–134CrossRefGoogle Scholar
  32. 32.
    Wang F L, Wang F. Rapidly void detection in tsvs with 2-d x-ray imaging and artificial neural networks. IEEE Trans Semicond Manufact, 2014, 27: 246–251CrossRefGoogle Scholar
  33. 33.
    Holler M, Guizar-Sicairos M, Tsai E H R, et al. High-resolution nondestructive three-dimensional imaging of integrated circuits. Nature, 2017, 543: 402–406CrossRefGoogle Scholar
  34. 34.
    Huang G B, Zhou H M, Ding X J, et al. Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B, 2012, 42: 513–529CrossRefGoogle Scholar

Copyright information

© Science China Press and Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Jiangsu Key Laboratory of Advanced Food Manufacturing Equipment and TechnologyJiangnan UniversityWuxiChina
  2. 2.State Key Laborotary of Digital Manufacturing Equipment and TechnologyHuazhong University of Science and TechnologyWuhanChina
  3. 3.School of Mechanical EngineeringZhejiang UniversityHangzhouChina
  4. 4.National Center for Advanced PackagingWuxiChina

Personalised recommendations