2nd Electronics System-Integration Technology Conference, 2008

Anomaly Detection in Electronic Products

Abraham Tomy Michael
Sachin Kumar
Sony Mathew
Michael Pecht

Prognostics Health Management Group
Center for Advanced Life Cycle Engineering (CALCE)
Department of Mechanical Engineering
University of Maryland
College Park, MD 20742

Abstract:

Anomalous and intermittent behavior is a leading concern for electronics manufacturers of electronic products. Yet it is often not possible to replicate such behavior, let alone determine the root cause of faults. This paper presents an approach to identify anomalous behavior using a simple Mahalanobis Distance approach. A case study of experiments conducted on a field returned electronic product is presented.

Full Text