An Experiment to Compare Taguchi's Product Array and the Combined Array

• Autores: J. Kunert, C. Auer, M. Erdrügge, R. Ewers
• Localización: Journal of quality technology: A quarterly journal of methods applications and related topics, ISSN 0022-4065, Vol. 39, Nº. 1, 2007, págs. 17-34
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • ]In robust parameter design, experimenters try to optimize the process by moving the mean to the target value and simultaneously reducing the variance. Taguchi proposed the use of a product array where the same array of noise factors is run for each combination of design factors. Other statisticians proposed using a combined array of design and noise factors to analyze the interaction between both types of factors. In the experiment discussed here, both designs are done simultaneously, and the product array found an effect on the variance that cannot be seen from the combined array. An explanation might be that the effect on the variance cannot be attributed to a small number of low-order interactions.