The inherent reliability of product is primarily determined in the design stage, and therefore, design engineers are required to be able to design reliability into the product in an efficient manner.
Especially, the product should be designed such that its reliability is robust to various noise factors encountered in production and field environments. The Taguchi method can be effectively used for this purpose. However, there exist only a few attempts to integrate the Taguchi method with reliability design, and in addition, the existing works do not sufficiently consider the robustness and/or the distinction between noise and acceleration factors.
This thesis develops a unified approach to robust reliability design for the cases of accelerated life and degradation tests. First, an experimental structure for assigning not only acceleration but also noise factors is presented. Second, an optimal setting of design parameters is determined based on the reliabilities at the use condition, which are estimated using the results from accelerated conditions. Third, reliabilities are transformed into `efforts' using an effort function which reflects the degree of difficulty involved in improving the reliability. Finally, an optimal setting of design parameters is determined based on the mean and standard deviation of effort values. In addition, the flexibility and effectiveness of the proposed approach are illustrated with examples.