Fault detection and classification in linear integrated circuits: an application of discrimination analysis and hypothesis testing
Benjamin R. Epstein, M. Czigler, Steven R. Miller · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · 1993
The standard multivariate techniques of hypothesis testing and discrimination analysis have been applied to detect and classify faults in a variety of linear IC designs. These techniques are potentially useful for tracking IC failures during processing or for assessing failure mechanisms of ICs once the circuits are in field use. The results indicate that the statistical methods investigated potentially yield low detection and classification error rates.>