WSC 2005 Final Abstracts

Simulation and Optimization as Effective Six Sigma and Dfss Tools
Karl Lucie, Lucie Trepanier, Fred Ciochetto, and Lawrence Goldman (Decisioneering, Inc.)

Abstract:
Simulation and optimization techniques can provide Design for Six Sigma (DFSS) practitioners with reduced reliance on physical prototypes, rapid time-to-market, minimal defects and post-design rework. These advantages lead to quantifiable benefits within the product development life-cycle, in terms of time and cost. Through one case study, this paper will provide Six Sigma, Process Excellence and Lean practitioners with the rationale for spreadsheet simulation and optimization in DFSS initiatives. Discussion topics include the role of simulation and optimization in the DMADV methodology, disadvantages of not quantifying uncertainty in DFSS projects, differences between deterministic and stochastic optimization, and tradeoff considerations when running optimizations. Practical techniques for efficiently identifying robust, high quality solutions are demonstrated through the use of Monte Carlo simulation and optimization.

The Use of Discrete Event Simulation in a Design for Six Sigma Project
Michael J. Seifert (Capital One services, Inc.)

Abstract:
This paper describes how a risk event to customer satisfaction for a food service facility was identified, validated, and eventually mitigated through the use of a discrete event simulation as part of a Design for Six Sigma project. Further described is how simulation was utilized to identify leading indicators to the risk event, to give pre-warning of the occurrence as well as to perform what if tests to validate mitigation practices and contingency plans. The results presented demonstrate how a simulation model coupled with Six Sigma can design a superior process in regards to predictability and reliability.

Evaluating Proposed Capital and Operational Improvements at a Marine Terminal
Scott J. Bury and Naoko Akiya (The Dow Chemical Company)

Abstract:
Marine terminal operations are complex, and evaluating changes is best done using a simulation tool that captures the dynamics and interactions of the system. We have developed a flexible and robust discrete-event simulation of a marine terminal that handles liquid cargo. We used this simulation to investigate proposed changes generated by a Six Sigma project to reduce congestion at the terminal. Our study provided quantitative data to base decisions on the expected operational and financial impact of the proposed changes. The simulation captured the important details of the system and increased the Six Sigma team’s confidence in their recommendations. The modular architecture of the simulation allows for easy application of the simulation to different terminal simply by changing a few data tables. The structure of the simulation makes it easy for non-modelers to use the tool to perform continuing studies.

Lean Sigma and Simulation, So What’s the Correlation? v2
David M. Ferrin and Martin J. Miller (Business Prototyping Inc) and David Muthler (PWC Consulting)

Abstract:
This paper will explore the fundamental relationships between Lean Sigma and simulation. A basic overview of Lean Sigma includes: 1) Lean Sigma philosophy, 2) Basic tools, 3) Theory of Variation, 4) SPC, 5) Process capabil-ity,6) Lean Sigma infrastructure, and 7) DMAIC and DFSS processes. Simulation will be applied to the appropriate areas of the overview. Improvement in the robustness of the Lean Sigma methodology will be discussed and the strengths of simulation will be presented as capable and preferable enhancements to the Lean Sigma processes. Quotes from Lean Sigma and industry leaders will be presented. Simulation will be presented as an innovation tool enhancing the Lean Sigma DMAIC and DFSS processes.

The Application of Simulation Methodology in a Hospital’s Six Sigma Project
Martin J. Miller (Business Prototyping Inc.) and David M. Ferrin (Business Prototyping, Inc.)

Abstract:
Simulation was recently utilized as the key component of a Six Sigma project at a major hospital in the southeastern United States. The project team used various statistical analysis tools to assess current process performance and measure improvements with process changes. However, simulation provided the best insight into which process changes had the best opportunity to succeed and which would yield little value. This paper briefly discusses the methodology of this project and how simulation provided a better quality solution.

Sensitivity Analysis for Robust Design Experiments
Joseph R. Litko (University of Dayton)

Abstract:
Robust parameter design experiments lead to products and processes that are insensitive to the effects of noise. These experiments reveal the interaction of the noise sources with design or control factors usually allowing creation of products that are relatively immune to noise. Finding truly optimal settings for design factors depends on the noise in the lab being representative of the actual operating environment and assumes potential product users all see the same noise conditions. This paper shows how basic design solutions can be shaped when multiple populations see different noise conditions and when typical assumptions on noise sources are violated.