Robust Design: Goal Formulations and a Comparison of Metamodeling Methods

Abstract

Abstract In this paper, through theoretical analysis, we point out the limitations of goal formulations in previous methods for approximation-based robust design. Based on different philosophies and mathematical deduction, we propose three new methods to formulate robust design goals. Using a single variable function, we compare and contrast the use of response surface models and kriging models for approximating non-random, deterministic computer analyses in robust design with large variances of design variables in a highly nonlinear design space. Our preliminary conclusions are: 1) kriging models perform better than response surface models in a large design space with a high degree of nonlinearity, and 2) more robust solutions are achievable with kriging models than with response surface models.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 21 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.