Pattern matching for variation-source identification in manufacturing processes in the presence of unstructured noise

Abstract

Variation-source identification has received considerable attention from the manufacturing quality improvement community. One widely used method is based on a pattern matching procedure, which identifies process faults by comparing the fault symptom, which is the principal eigenvector of the covariance matrix of the quality measurement, with fault signatures. The presence of unstructured noise as well as the uncertainty due to sampling will cause the direction of the fault symptom to deviate from the corresponding fault signature. The influences of these two effects on pattern matching procedures have previously been studied separately, by assuming either the absence of unstructured noise or the availability of large samples. This paper developes a robust pattern matching procedure that considers both effects simultaneously. Using a machining process as an illustrative example, the paper demonstrates that previous pattern matching procedures can have a remarkably low identification capability when the assumptions are not strictly satisfied. By contrast, our proposed method is more robust, maintaining a good identification probability, and would be a preferable tool for root-cause identification in manufacturing quality improvement.

Keywords:

• Statistical pattern matching
• statistical testing
• unstructured noise
• variation source identification

Acknowledgements

The authors gratefully acknowledge the financial support of NSF under grants DMI-0217481, DMI-0322147, and DMI-0348150, and from the State of Texas Advanced Technology Program under grant 000512-0237-2003. The authors would like to thank the Editors and reviewers for their insightful comments and suggestions, which have significantly improved the paper's quality and readability.