Abstract: Through this paper we present a method for automatic
generation of ontological model from any data source using Model
Driven Architecture (MDA), this generation is dedicated to the
cooperation of the knowledge engineering and software engineering.
Indeed, reverse engineering of a data source generates a software
model (schema of data) that will undergo transformations to generate
the ontological model. This method uses the meta-models to validate
software and ontological models.
Abstract: This research presents the development of simulation
modeling for WIP management in semiconductor fabrication.
Manufacturing simulation modeling is needed for productivity
optimization analysis due to the complex process flows involved
more than 35 percent re-entrance processing steps more than 15 times
at same equipment. Furthermore, semiconductor fabrication required
to produce high product mixed with total processing steps varies from
300 to 800 steps and cycle time between 30 to 70 days. Besides the
complexity, expansive wafer cost that potentially impact the
company profits margin once miss due date is another motivation to
explore options to experiment any analysis using simulation
modeling. In this paper, the simulation model is developed using
existing commercial software platform AutoSched AP, with
customized integration with Manufacturing Execution Systems
(MES) and Advanced Productivity Family (APF) for data collections
used to configure the model parameters and data source. Model
parameters such as processing steps cycle time, equipment
performance, handling time, efficiency of operator are collected
through this customization. Once the parameters are validated, few
customizations are made to ensure the prior model is executed. The
accuracy for the simulation model is validated with the actual output
per day for all equipments. The comparison analysis from result of
the simulation model compared to actual for achieved 95 percent
accuracy for 30 days. This model later was used to perform various
what if analysis to understand impacts on cycle time and overall
output. By using this simulation model, complex manufacturing
environment like semiconductor fabrication (fab) now have
alternative source of validation for any new requirements impact
analysis.
Abstract: In this paper, the implementation of a rule-based
intuitive reasoner is presented. The implementation included two
parts: the rule induction module and the intuitive reasoner. A large
weather database was acquired as the data source. Twelve weather
variables from those data were chosen as the “target variables"
whose values were predicted by the intuitive reasoner. A “complex"
situation was simulated by making only subsets of the data available
to the rule induction module. As a result, the rules induced were
based on incomplete information with variable levels of certainty.
The certainty level was modeled by a metric called "Strength of
Belief", which was assigned to each rule or datum as ancillary
information about the confidence in its accuracy. Two techniques
were employed to induce rules from the data subsets: decision tree
and multi-polynomial regression, respectively for the discrete and the
continuous type of target variables. The intuitive reasoner was tested
for its ability to use the induced rules to predict the classes of the
discrete target variables and the values of the continuous target
variables. The intuitive reasoner implemented two types of
reasoning: fast and broad where, by analogy to human thought, the
former corresponds to fast decision making and the latter to deeper
contemplation. . For reference, a weather data analysis approach
which had been applied on similar tasks was adopted to analyze the
complete database and create predictive models for the same 12
target variables. The values predicted by the intuitive reasoner and
the reference approach were compared with actual data. The intuitive
reasoner reached near-100% accuracy for two continuous target
variables. For the discrete target variables, the intuitive reasoner
predicted at least 70% as accurately as the reference reasoner. Since
the intuitive reasoner operated on rules derived from only about 10%
of the total data, it demonstrated the potential advantages in dealing
with sparse data sets as compared with conventional methods.