Data mining for manufacturing control: an application in optimizing IC tests

TLDR: A decision-theoretic approach to DLFT is described in which historical test data is mined to create a probabilistic model of patterns of die failure and this model is combined with greedy value-of-information computations to decide in real time which die to test next and when to stop testing.

Abstract: We describe an application of machine learning and decision analysis to the problem of die-level functional tests in integrated circuit manufacturing. Integrated circuits (ICs) are fabricated on large wafers that can hold hundreds of individual chips (die). In current practice, large and expensive machines test each of these die to check that they are functioning properly (die-level functional test or DLFT), and then the wafers are cut up, and the good die are assembled into packages and connected to the package pins. Finally, the resulting packages are tested to ensure that the final product is functioning correctly. The purpose of the die-level functional test is to avoid the expense of packaging bad die and to provide rapid feedback to the fabrication process by detecting die failures. The challenge for a decision-theoretic approach is to reduce the amount of DLFT (and the associated costs) while still providing process feedback. We describe a decision-theoretic approach to DLFT in which historical test data is mined to create a probabilistic model of patterns of die failure. This model is combined with greedy value-of-information computations to decide in real time which die to test next and when to stop testing. We report the results of several experiments that demonstrate the ability of this procedure to make good testing decisions, to make good stopping decisions, and to detect anomalous die. Based on experiments with historical test data from Hewlett-Packard, the resulting system has the potential to improve profits on mature IC products.