Material identification of loose particles in sealed electronic devices using PCA and SVM

Abstract The existence of loose particles left inside the sealed electronic devices is one of the main factors affecting the reliability of the whole system. It is important to identify the particle material for analyzing their source. The conventional material identification algorithms mainly rely on time, frequency and wavelet domain features. However, these features are usually overlapped and redundant, resulting in unsatisfactory material identification accuracy. The main objective of this paper is to improve the accuracy of material identification. First, the principal component analysis (PCA) is employed to reselect the nine features extracted from time and frequency domains, leading to six less correlated principal components. And then the reselected principal components are used for material identification using a support vector machine (SVM). Finally, the experimental results show that this new method can effectively distinguish the type of materials including wire, aluminum and tin particles.

[1]  Guofu Zhai,et al.  Research on Feature Extraction of Remnant Particles of Aerospace Relays , 2007 .

[2]  Peter E. William,et al.  Identification of bearing faults using time domain zero-crossings , 2011 .

[3]  Wang Changhong,et al.  Particle impact noise detection in sealed relays based on neural network , 2003, Proceedings of the Forty-Ninth IEEE Holm Conference on Electrical Contacts, 2003..

[4]  L. J. Scaglione.  Neural network application to particle impact noise detection , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[5]  Mikael Johnson.  Waveform based clustering and classification of AE transients in composite laminates using principal component analysis , 2002 .

[6]  B. L. Luk,et al.  Evaluation of tile–wall bonding integrity based on impact acoustics and support vector machine , 2008 .

[7]  D. R. Salgado,et al.  An approach based on current and sound signals for in-process tool wear monitoring , 2007 .

[8]  Li Xiaohua,et al.  Estimation of Crowd Density Based on Wavelet and Support Vector Machine , 2006 .

[9]  Mahmoud Omid,et al.  Development of pistachio sorting system using principal component analysis (PCA) assisted artificial neural network (ANN) of impact acoustics , 2010, Expert Syst. Appl..

[10]  Jung-Ryul Lee,et al.  Review of pyroshock wave measurement and simulation for space systems , 2012 .

[11]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[12]  Serdar Iplikci,et al.  Support vector machines based neuro-fuzzy control of nonlinear systems , 2010, Neurocomputing.

[13]  Anthony Gachagan,et al.  Particle sizing using passive ultrasonic measurement of particle wall impact vibrations , 2008 .

[14]  George S. Moschytz,et al.  A New Framework and Computer Program for Quantitative EMG Signal Analysis , 1984, IEEE Transactions on Biomedical Engineering.

[15]  Theodoros Loutas,et al.  On the characterization of continuous fibres fracture by quantifying acoustic emission and acousto-ultrasonics waveforms , 2004 .

[16]  Chih-Jen Lin,et al.  A Comparison of Methods for Multi-class Support Vector Machines , 2015 .

[17]  Tianyou Chai,et al.  On-line principal component analysis with application to process modeling , 2012, Neurocomputing.

[18]  Guofu Zhai,et al.  Research on Vibration Test Conditions in Particle Impact Noise Detection , 2006 .

[19]  Zhang Hui,et al.  Dynamic model of particle impact noise detection , 2004, 30th Annual Conference of IEEE Industrial Electronics Society, 2004. IECON 2004.

[20]  Maria Mirgkizoudi,et al.  Reliability testing of electronic packages in harsh environments , 2010, 2010 12th Electronics Packaging Technology Conference.

[21]  S. K. Tso,et al.  Impact-acoustics-based health monitoring of tile-wall bonding integrity using principal component analysis , 2006 .

[22]  Kevin C. McGill,et al.  Automatic Decomposition of the Clinical Electromyogram , 1985, IEEE Transactions on Biomedical Engineering.

[23]  M. Ahmadi,et al.  Identification of damage modes in polypropylene/epoxy composites by using principal component analysis on AE signals extracted from Mode I delamination , 2012 .

[24]  V. Nagesh,et al.  Automatic detection and elimination of periodic pulse shaped interferences in partial discharge measurements , 1994 .

[25]  Rui Chen,et al.  Detection and material identification of loose particles inside the aerospace power supply via stochastic resonance and LVQ network , 2012 .

[26]  Hui Zhang,et al.  Research on Auto-detection for Remainder Particles of Aerospace Relay Based on Wavelet Analysis , 2007 .

[27]  Hui Zhang,et al.  Research on particle impact noise detection standards , 2008, IEEE Transactions on Aerospace and Electronic Systems.

[28]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.