Continuous equipment diagnosis using evidence integration: an LPCVDapplication
Chang, N.H.; Spanos, C.J.
Semiconductor Manufacturing, IEEE Transactions on
Volume 4, Issue 1, Feb 1991 Page(s):43 - 51
Digital Object Identifier 10.1109/66.75851
Summary:A diagnostic system that employs the Dempster-Shafer (D-S)
evidential reasoning technique to conduct malfunction diagnosis on
semiconductor manufacturing equipment has been developed. This is
accomplished by combining the continuous stream of information that
originates from maintenance status records, from real-time sensor
measurements, and from the differences between inline measurements and
values predicted by equipment models. Using this information, equipment
malfunctions are analyzed and their causes are inferred through the
resolution of qualitative and quantitative constraints. The qualitative
constraints describe the normal operation of the equipment. The
quantitative constraints are numerical models that apply to the
manufacturing step in question. These models are specifically created
and characterized through experimentation and statistical analysis, and
they can be updated to reflect equipment aging. The violation of these
constraints is linked to the evaluation of continuous belief functions
for the calculation of the belief associated with the various types of
failure. The belief functions encapsulate the experience of many
equipment maintenance specialists. Once created, the belief functions
can be fine-tuned automatically, drawing from historical maintenance
records. These records are stored in symbolic form to facilitate this
task, and they must be updated to track equipment changes over time. A
prototype of this diagnostic system was implemented in an
object-oriented programming environment. The effectiveness of this
technique was demonstrated on a low-pressure chemical vapor deposition
(LPCVD) reactor used for the deposition of undoped polysilicon
View citation and abstract |
Cart
