Material Identification of Particles in Space-Borne Electronic Equipments Based on Principal Component Analysis - Intelligent Computing for Sustainable Energy and Environment - page 460

Material Identification of Particles
in Space-Borne Electronic Equipments
Based on Principal Component Analysis
Guofu Zhai 1 , Jinbao Chen 1 ,ShujuanWang 1 , Kang Li 2 , and Long Zhang 2
1 School of Electrical Engineering and Automation, Harbin Institute of Technology,
150001, Harbin, P.R. China
[e-mail]
2 School of Electronic, Electrical Engineering and Computer Science,
Queen's University Belfast, Belfast, UK
kli [e-mail]
Abstract. The existence of loose particle left inside the space-borne
electronic equipments is one of the main factors affecting the reliability
of the whole system. It is important to identify the particle material for
analyzing their sources. The conventional material identification algo-
rithms mainly rely on frequency and wavelet domain features. However,
these features are usually overlapped and redundant, resulting in un-
satisfactory material identification accuracy. The main objective of this
paper is to improve the accuracy of material identification. The principal
component analysis (PCA) is employed to reselect the nine features ex-
tracted from time and frequency domains, leading to six less correlated
principal components. The reselected principal components are used for
material identification using support vector machines (SVM). The ex-
perimental results show that this new method can effectively distinguish
the type of materials including wire, aluminum and tin particles.
Keywords: Loose particles, Material identification, Principal compo-
nent analysis, Support vector machine.
1 Introduction
The space-borne electronic equipments are widely used in communication, re-
mote control and scientific experiments in a satellite system. Their reliability
is vital to the success of the mission and safety of personnel and equipments.
However, due to their complex structure and production process, loose particles
may be left inside, such as the wire pieces, aluminum scraps and tin dregs. The
loose particles can be freed and collide randomly, which is caused by vibration
and shock. This can lead to component malfunction, system breakdown, or even
aerospace catastrophes. Therefore, it is critical to investigate the loose parti-
cle detection and identification technologies for the development of aerospace
industry [1].