Process-Oriented Basis Representations for Multivariate Process Diagnosis and Control

摘要

Statistical methods for process control do not provide engineering tools for diagnosis: rather, they characterize and monitor the randomness inherent in manufactured products to identify time periods or production batches which show atypical characteristics. The production engineer must then diagnose the cause or causes of these irregularities. Many production problems have characteristic signatures that can be detected in the multivariate quality vector. Each signature is a basis element in the process-oriented basis. Process-oriented basis coefficients can be monitored using SPC methods, providing process-related diagnostics and control.