Abstract
A feature extraction for latent fault detection and failure modes classification method of board-level package subjected to vibration loadings is presented for prognostics and health management (PHM) of electronics using adaptive spectrum kurtosis and kernel probability distance clustering. First, strain response data of electronic components is filtered by empirical mode decomposition (EMD) method based on maximum spectrum kurtosis (SK), and fault symptom vector is developed by computing and reconstructing the envelope spectrum. Second, nonlinear fault symptom data is mapped and clustered in sparse Hilbert space using Gaussian radial basis kernel probabilistic distance clustering method. Finally, the current state of board level package is estimated by computing the membership probability of its envelope spectrum. The experimental results demonstrated that the method can detect and classify the latent failure mode of board level package effectively before it happened.
Similar content being viewed by others
References
Chen X F, He Z J, Li B, et al. An efficient wavelet finite element method in fault prognosis of incipient crack. Sci China Tech Sci, 2006, 49: 89–101
Steinberg D S. Vibration Analysis for Electronic Equipment. 2nd ed. New York: Wiley-Interscience, 1988
Medjaher K, Skima H, Zerhouni N. Condition assessment and fault prognostics of microelectromechanical systems. Microelectron Reliab, 2014, 54: 143–151
Lall P, Lowe R, Goebel K. Extended Kalman filter models and resistance spectroscopy for prognostication and health monitoring of leadfree electronics under vibration. IEEE T Reliab, 2012, 61: 858–871
Gu J, Barker D, Pecht M. Prognostics implementation of electronics under vibration loading. Microelectron Reliab, 2007, 47: 1849–1856
Wu M L. Vibration-induced fatigue life estimation of ball grid array packaging. J Micromech Microeng, 2009, 19: 065005
Che F X, Pang J H L. Vibration reliability test and finite element analysis for flip chip solder joints. Microelectron Reliab, 2009, 49: 754–760
Lall P, Gupta P, Goebel K. Decorrelated feature space and neural nets based framework for failure modes clustering in electronics subjected to mechanical shock. IEEE T Reliab, 2012, 61: 884–899
Tu K N, Tian T. Metallurgical challenges in microelectronics 3D IC packaging technology for future consumer electronic products. Sci China Tech Sci, 2013, 56: 1740–1748
Han C, Oh C M, Hong W S. Prognostics model development of BGA assembly under vibration environment. IEEE T Comp Pack Man, 2012, 2: 1329–1334
Delmonte N, Giuliani F, Cova P. Finite element modeling and characterization of lead-free solder joints fatigue life during power cycling of surface mounting power devices. Microelectron Reliab, 2013, 53: 1611–1616
Alam M A, Azarian M H, Osterman M, et al. Prognostics of failures in embedded planar capacitors using model-based and data-driven approaches. J Intel Mat Syst Str, 2011, 22: 1293–1303
Yao W, Basaran C. Electromigration damage mechanics of lead-free solder joints under pulsed DC: A computational model. Comp Mater Sci, 2013, 71: 76–88
Lall P, Gupta P, Angral A. Anomaly detection and classification for PHM of electronics subjected to shock and vibration. IEEE T Comp Pack Man, 2012, 2: 1902–1918
Kim C U, Bang W H, Xu H, et al. Characterization of solder joint reliability using cyclic mechanical fatigue testing. JOM, 2013, 65: 1362–1373
Otiaba K C, Okereke M I, Bhatti R S. Numerical assessment of the effect of void morphology on thermo-mechanical performance of solder thermal interface material. Appl Therm Eng, 2014, 64: 51–63
Lall P, Lowe R. Comparison of Prognostic health management algorithms for assessment of electronic interconnect reliability under vibration. J Electron Packaging, 2014, 136: 041013
Sheng H, Zheng Z, Enrico Z, et al. Condition assessment for the performance degradation of bearing based on a combinatorial feature extraction method. Digit Signal Process, 2014, 27: 159–166
Chen B Q, Zhang Z S, Zi Y Y, et al. A pseudo wavelet system-based vibration signature extracting method for rotating machinery fault detection. Sci China Tech Sci, 2013, 56: 1294–1306
Yang Y C, Satish N. Structural damage identification via a combination of blind feature extraction and sparse representation classification. Mech Syst Signal Pr, 2014, 45: 1–23
Shao R P, Hu W T, Wang Y Y, et al. The fault feature extraction and classification of gear using principal component analysis and kernel principal component analysis based on the wavelet packet transform. Measurement, 2014, 54: 118–132
Chen Y M, Zi Y Y, Cao H R, et al. A data-driven threshold for wavelet sliding window denoising in mechanical fault detection. Sci China Tech Sci, 2014, 57: 589–597
Abdenour S, Hubert R, Guy C, et al. Prognosis of bearing failures using hidden markov models and the adaptive neuro-fuzzy inference system. IEEE T Ind Electron, 2014, 61: 2864–2874
Sachin K, Tommy W S, Michael P, Chow, Michael Pecht. Approach to fault identification for electronic products using mahalanobis distance. IEEE T Instrum Meas, 2010, 59: 2055–2064
Zhang C L, He Y G, Yuan L F, et al. A novel approach for analog circuit fault prognostics based on improved RVM. J Electron Test, 2014, 30: 343–356
Kappaganthu K, Nataraj C. Feature selection for fault detection in rolling element bearings using mutual information. J Vib Acoust, 2011, 133: 061001
Lee J H, Seo J S. Application of spectral kurtosis to the detection of tip vortex cavitation noise in marine propeller. Mech Syst Signal Pr, 2013, 40: 222–236
González de la Rosa J J, Sierra-Fernández J M, Agüera-Pérez A, et al. An application of the spectral kurtosis to characterize power quality events. Int J Elec Power, 2013, 49: 386–398
Wang S B, Jia H K, Li L A, et al. Experimental investigation on cumulative propagation of thin film buckling under cyclic load. Sci China Tech Sci, 2011, 54: 1371–1375
Antoni J. The spectral kurtosis: A useful tool for characterizing non-stationary signals. Mech Syst Signal Pr, 2006, 20: 282–307
Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc London Ser A, 1998, 454: 903–995
Peng Z K, Peter W T, Chu F L. An improved Hilbert-Huang transform and its application in vibration signal analysis. J Sound Vib, 2005, 286: 187–205
Ben-Israel A, Iyigun C. Probabilistic D-clustering. J Classif, 2008, 25: 5–26
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tang, W., Jing, B., Huang, Y. et al. Feature extraction for latent fault detection and failure modes classification of board-level package under vibration loadings. Sci. China Technol. Sci. 58, 1905–1914 (2015). https://doi.org/10.1007/s11431-015-5854-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11431-015-5854-8