Dynamic statistical control of manufacturing test

A method for controlling manufacturing tests in real time by statistically predicting test behavior is described. This statistical prediction is used to eliminate certain tests in sequential testing. Analytic methods for clustering tests for more efficient execution and an algorithm for predictive testing are presented. A relational database using structured-query-language system, called SQL/DB2 is proposed; its structure allows efficient retrieval of the information needed for test prediction, test clustering, and predictive testing. A test-system architecture based on personal computers is presented.<
>