Simulation has its downsides, though. DES modeling may be hard for nonspecialists to grasp. This is an important drawback because understanding the methodology behind results often is a prerequisite to stakeholder "buy in." The effort needed for data collection and analysis also is a significant hurdle. Simulation frequently demands collection of large amounts of data to obtain valid models of the system. Furthermore, the data collected must be analyzed and transformed into statistical distributions. The techniques involved often require the knowledge of a statistics or simulation expert. The substantial effort associated with data collection and analysis frequently translates into huge investments in time, resources and money for initial implementation of simulation modeling methodologies. Then, once developed, the model must undergo validation and verification to ensure its usefulness and accuracy — this also necessitates a sizable time investment.
Add DES To Your Toolset
Chemical makers definitely should consider DES. It's a powerful tool in areas such as supply chain analysis and process improvement. DES enables decision-makers to obtain accurate results that take into account the uncertainty, dynamic behavior and distributed nature of supply chain environments. Simulation also complements Six Sigma by providing the next level of statistical rigor, accuracy and robustness required for many complex Six Sigma efforts, and can result in improved Six Sigma project cycle times.
DAYANA COPE, Ph.D., is an operations research analyst for Eastman Chemical Company, Kingsport, Tenn. E-mail her at firstname.lastname@example.org.
1 Ferrin, D.M., Miller, M.J., and Muthler, D., "Lean Sigma and Simulation, So What's the Correlation," Proceedings, 2005 Winter Simulation Conference, Orlando (2005).
2. Luce, K., Trepanier, L., Ciochetto, F., and Goldman, L., "Simulation and Optimization as Effective DFSS Tools," Proceedings, 2005 Winter Simulation Conference, Orlando (2005).