Automated development of process time estimating models
This research has examined the cost estimating and cost modeling research literature
and identified the benefits and limitations of existing practices. Particular emphasis has
been placed on the methods available for developing cost models at the early stages of
product and process development where data from which to develop models is scarce.
Shortfalls in existing practices have been identified as well as potential methods of
resolving these limitations. Of these methods Virtual Manufacturing appears to offer the
greatest potential for resolving issues with lack of data availability by enabling such data
to be generated.
Detailed trials have, therefore, been undertaken to examine the effectiveness of Virtual
Manufacturing in terms of its ability to generate valid data in the quantities required to
ensure accurate cost models can be developed. In addition, the research has involved the
use of Data Mining techniques to identify the cost estimating relationship's within the
data output from the Virtual Manufacturing trials. Here the aim has been to investigate
the potential use of Data Mining techniques to fully automate the data analysis stage of
the cost model development process.