Design and Analysis Approach for Factorials with Observable Noise Factors in Robust Design.pdfVIP

Design and Analysis Approach for Factorials with Observable Noise Factors in Robust Design Lisa M. Hughes and James R. Simpson Department of Industrial and Manufacturing Engineering Florida AM University – Florida State University College of Engineering Tallahassee, Florida 32310 Abstract Recent literature has proposed integrating observed noise variables into a factorial design structure as an alternative robust design strategy. Because noise factors are often difficult to control or randomize, observing their values may be useful. This research compares existing alternatives involving unreplicated fractional factorial designs and observable noise factors. Keywords: Robust design; Unreplicated fractional factorial designs; Observable noise factors 1. Introduction Engineers and scientists are becoming increasingly aware of the benefits of using designed experimentation as a tool for understanding their system or process. The quality paradigm of many businesses has shifted from “defect inspecting” and problem solving to designing quality directly into the product or process (Tsai 1996). It has become obvious that the more that is known about a particular process via experimentation, the greater the chances are for obtaining improved quality of products and systems. Thus, improved quality often implies increased profitability. Common problems in practice involve experimentation in the presence of noise variables. For the purposes of experimentation, some noise factors can be controlled while others are uncontrollable in all phases, (i.e., experimentation, production, actual use). Noise fa