Conventionally, parameter design is carried out prior to tolerance design for economic considerations. However, this noncombined (two-step) design strategy cannot guarantee an economic and quality product for some quality characteristics. The rapid development of new products, and the planning and early implementation of product development are the important keys to competitiveness. This paper presents an approach based on the techniques of orthogonal arrays, computer simulation, and statistical methods. It also adopts a cost function that represents the combined impact of assigned parameters and tolerance values. This cost function is the sum of the tolerance cost and the quality loss. Computer simulation generates a set of experimental data by following the experimental design suggested by the orthogonal array. The orthogonal array experiment enables an engineer to generate experimental data required for statistical analysis with less experimental effort. Based on the experimental data and cost function, a set of response values are found for statistical analysis, and for detecting the critical assignment of parameter and tolerance values. As a result, a combined robust parameter and tolerance design for quality improvement and cost reduction can be achieved effectively at an early stage of design and planning.
Article PDF
Similar content being viewed by others
Use our pre-submission checklist
Avoid common mistakes on your manuscript.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Jeang, A., Chang, CL. Combined Robust Parameter and Tolerance Design Using Orthogonal Arrays. Int J Adv Manuf Technol 19, 442–447 (2002). https://doi.org/10.1007/s001700200046
Issue Date:
DOI: https://doi.org/10.1007/s001700200046