摘要
In order to express information on the quality grade of product designed, thetarget value of product quality design was described with a fuzzy number in this paper. Analternative to Taguchi's, the robustness application design method has been recently presented.However, neither Taguchi's method nor the alternative method is capable of dealing satisfactorilywith the frequently encountered situations in which all the noise variables cannot be studiedsimultaneously. Based on the ideas from response surface modeling, linear models theory, and randomeffects models, we provide a method for estimation in the robustness application design method inproduct quality applications. With this new method used, the high-quality ratio of the productdesigned could be increased, and the ability to resist the influence of various disturbing factorsand noise factors could be enhanced.
In order to express information on the quality grade of product designed, thetarget value of product quality design was described with a fuzzy number in this paper. Analternative to Taguchi's, the robustness application design method has been recently presented.However, neither Taguchi's method nor the alternative method is capable of dealing satisfactorilywith the frequently encountered situations in which all the noise variables cannot be studiedsimultaneously. Based on the ideas from response surface modeling, linear models theory, and randomeffects models, we provide a method for estimation in the robustness application design method inproduct quality applications. With this new method used, the high-quality ratio of the productdesigned could be increased, and the ability to resist the influence of various disturbing factorsand noise factors could be enhanced.
