This thesis explores the impact of different experimental design strategies for the development of quantile regression based metamodels of computer simulations. In this research, the objective is to compare the resulting predictive accuracy of five experimental design strategies, each of which is used to develop metamodels of a computer simulation of a semiconductor manufacturing facility. The five examined experimental design strategies include two traditional experimental design strategies, sphere packing and I-optimal, along with three hybrid design strategies, which were developed for this research and combine desirable properties from each of the more traditional approaches. The three hybrid design strategies are: arbitrary, centroid clustering, and clustering hybrid. Each of these strategies is analyzed and compared based on common experimental design space, which includes the investigation of four densities of design point placements three different experimental regions to predict four different percentiles from the cycle time distribution of a semiconductor manufacturing facility. Results confirm that the predictive accuracy of quantile regression metamodels depends on both the location and density of the design points placed in the experimental region. They also show that the sphere packing design strategy has the best overall performance in terms of predictive accuracy. However, the centroid clustering hybrid design strategy, developed for this research, has the best predictive accuracy for cases in which only a small number of simulation resources are available from which to develop a quantile regression metamodel.

In the industry of manufacturing, each gas turbine engine component begins in a raw state such as bar stock and is routed through manufacturing processes to define its final form before being installed on the engine. What is the follow-up to this part? What happens when over time and usage it wears? Several factors have created a section of the manufacturing industry known as aftermarket to support the customer in their need for restoration and repair of their original product. Once a product has reached a wear factor or cycle limit that cannot be ignored, one of the options is to have it repaired to maintain use of the core. This research investigated the study into the creation and application of repair development methodology that can be utilized by current and new manufacturing engineers of the world. Those who have been in this field for some time will find the process thought provoking while the engineering students can develop a foundation of thinking to prepare for the common engineering problems they will be tasked to resolve. The examples, figures and tables are true issues of the industry though the data will have been changed due to proprietary factors. The results of the study reveals, under most scenarios, a solid process can be followed to proceed with the best options for repair based on the initial discrepancy. However, this methodology will not be a "catch-all" process but a guidance that will develop the proper thinking in evaluation of the repair options and the possible failure modes of each choice. As with any continuous improvement tool, further research is needed to test the applicability of this process in other fields.