Mahalanobis Distance and Projection Pursuit Analysis for Health Assessment of Electronic Systems

This paper presents a Mahalanobis distance and projection pursuit analysis based prognostic and diagnostic approach for early detection of anomalies in electronic products and systems. These have been used to detect deviations in system performance from normal operation, and are efficient at characterizing products with short field histories. A case study is presented to demonstrate that an "abnormal" system can be distinguished from a "normal" system and that a new system can be characterized based on existing baselines from different computer models.

[1]  N. Vchare,et al.  Enabling electronic prognostics using thermal data , 2006 .

[2]  N. Vichare,et al.  Prognostics Implementation Methods for Electronics , 2007, 2007 Annual Reliability and Maintainability Symposium.

[3]  Khiang-Wee Lim,et al.  On-Line Process Monitoring and Fault Isolation Using PCA , 2005, Proceedings of the 2005 IEEE International Symposium on, Mediterrean Conference on Control and Automation Intelligent Control, 2005..

[4]  Jie Zhang,et al.  Process performance monitoring using multivariate statistical process control , 1996 .

[5]  S. Joe Qin,et al.  Reconstruction-Based Fault Identification Using a Combined Index , 2001 .

[6]  J. E. Jackson,et al.  Control Procedures for Residuals Associated With Principal Component Analysis , 1979 .

[7]  Michael Pecht,et al.  Environment and Usage Monitoringof Electronic Products for Health Assessment and Product Design , 2007 .

[8]  Subir Chowdhury,et al.  The Mahalanobis-taguchi System , 2000 .

[9]  Michael Pecht,et al.  Methods for Binning and Density Estimation of Load Parameters for Prognostics and Health Management , 2006 .

[10]  Brendt Wohlberg,et al.  Incorporating invariants in Mahalanobis distance based classifiers: application to face recognition , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[11]  Zhihuan Song,et al.  Fault detection behavior and performance analysis of principal component analysis based process monitoring methods , 2002 .

[12]  Haifeng Chen,et al.  Failure detection and localization in component based systems by online tracking , 2005, KDD '05.

[13]  Chiman Kwan,et al.  An Enhanced Prognostic Model for Intermittent Failures in Digital Electronics , 2007, 2007 IEEE Aerospace Conference.