CDID: A System for Identifying the Root Cause of a Defect in Semiconductor Wafer Fabrication

This paper proposes a system called CDID for diagnosing semiconductor fabrication process. CDID can identify the carry-over defect type that contributed to a defective cluster captured by an in-line inspection tool during a specific fabrication processing step. Let R
_x
be a defective cluster captured by an in-line inspection tool during the fabrication processing step ps
_i
. First, CDID would identify the defect type of R
_x
by comparing the image of R
_x
with the images in reference wafer maps of previous defect clusters captured at ps
_i
. Let d
_j
be the identified defect type. CDID would use rules of inferences for identifying the root cause of d
_j
. CDID would utilizedj as a trigger for the appropriate defect specification rules using the standard rules of inferences. Based on established and well-known causes of defects, CDID composes rule-based defect specifications in the form of propositional logic's premises. The premises are triggered by applying the inference rules. By applying the defect specification rules recursively using the inference rules, CDID can identify the root cause of d
_j
. The quality of CDID has been experimentally evaluated by measuring its prediction accuracy. Results revealed marked prediction accuracy.