Date of Award


Document Type


Degree Name

Master of Science in Systems Engineering


Department of Systems Engineering and Management

First Advisor

John M. Colombi, PhD.


Quantifying an expected improvement when considering moderate-complexity changes to a process is time consuming and has potential to overlook stochastic effects. By modeling a process as a Numerical Design Structure Matrix (NDSM), simulating the proposed changes, and evaluating performance, quantification can be rapidly accomplished to understand stochastic effects. This thesis explores a method to evaluate complex process changes within Six Sigma DMAIC process improvement to identify the most desirable outcome amongst several improvement options. A tool to perform the modeling and evaluation is developed. This process evaluation tool is verified for functionality, then is demonstrated against generic processes, a case study, and a real world Continuous Process Improvement event. The application of modeling and simulation to improve and control a process is found to be a positive return on investment under moderate complexity or continuous improvement events. The process evaluation tool is demonstrated to be accurate in prediction, scalable in complexity and fidelity, and capable of simulating a wide variety or evaluation types. Experimentation identifies the importance of understanding the evaluation criteria prior to “Measurement” in DMAIC, which increases the consistency of process improvement efforts.

AFIT Designator


DTIC Accession Number