A framework for expert system development in statistical quality control

Abstract We have proposed a framework for developing expert systems for statistical process control applications. The knowledge base is partitioned into three sets: domain-independent, analysis rules, which determne whether or not the sample observations indicate a lack-of-control; intrpretive rules, which analyze the patterns in the chart in terms of process changes; and domain-dependent diagnostic rules, which assist in determining assignable causes and corrective action. This structure allows some portability between applications and customizing to specific applications.