Advanced Methods for the Analysis of Semiconductor Manufacturing Process Data - Advanced Techniques in Knowledge Discovery and Data Mining - page 27

2. Advanced Methods for the Analysis of
Semiconductor Manufacturing Process Data
Andreas Konig 1 and Achim Gratz 2
1 Technische Universitat Kaiserslautern, Kaiserslautern D-67663, Germany;
email: [e-mail]
2 Infineon Technologies Dresden GmbH & Co. OHG, D-01076 Dresden,
Germany.
The analysis, control, and optimization of manufacturing processes in the
semiconductor industry are applications with significant economic impact.
Modern semiconductor manufacturing processes feature an increasing num-
ber of processing steps with an increasing complexity of the steps them-
selves to generate a flood of multivariate monitoring data. This exponen-
tially increasing complexity and the associated information processing and
productivity demand impose stringent requirements, which are hard to meet
using state-of-the-art monitoring and analysis methods and tools. This chap-
ter deals with the application of selected methods from soft computing to
the analysis of deviations from allowed parameters or operation ranges, i.e.,
anomaly or novelty detection, and the discovery of nonobvious multivariate
dependencies of the involved parameters and the structure in the data for
improved process control. Methods for online observation and o ine interac-
tive analysis employing novelty classification, dimensionality reduction, and
interactive data visualization techniques are investigated in this feasibility
study, based on an actual application problem and data extracted from a
CMOS submicron process. The viability and feasibility of the investigated
methods are demonstrated. In particular, the results of the interactive data
visualization and automatic feature selection methods are most promising.
The chapter introduces to semiconductor manufacturing data acquisition,
application problems, and the regarded soft-computing methods in a tutorial
fashion. The results of the conducted data analysis and classification exper-
iments are presented, and an outline of a system architecture based on this
feasibility study and suited for industrial service is introduced.
2.1 Introduction
The exponential increase of available computational resources leads to an ex-
plosive growth in the size and complexity of application-specific databases.
In fact, today's industrial sites can produce so much data per day that the
evaluation of potentially beneficial information and even complete storage
become close to impossible. The monitoring of complex processes, for in-
stance, in industrial manufacturing, however, requires online monitoring and
decision making as well as ensuing extraction of nonobvious information and