Optimization Under Uncertainty Versus Algebraic Heuristics: A Research Method for Comparing Computational Design Methods
| Autor: | Christiaan J. J. Paredis, William R. Binder |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
Mathematical optimization 021103 operations research Theoretical computer science Computer science Probabilistic-based design optimization 0211 other engineering and technologies 02 engineering and technology 020901 industrial engineering & automation Computational design Algebraic number Algebra over a field Design methods Heuristics Research method |
| Zdroj: | Volume 2B: 43rd Design Automation Conference. |
| Popis: | In this paper, we introduce a research method for comparing computational design methods. This research method addresses the challenge of measuring the difference in performance of different design methods in a way that is fair and unbiased with respect to differences in modeling abstraction, accuracy and uncertainty representation. The method can be used to identify the conditions under which each design method is most beneficial. To illustrate the research method, we compare two design methods for the design of a pressure vessel: 1) an algebraic approach, based on the ASME pressure vessel code, which accounts for uncertainty implicitly through safety factors, and 2) an optimization-based, expected-utility maximization approach which accounts for uncertainty explicitly. The computational experiments initially show that under some conditions the algebraic heuristic surprisingly outperforms the optimization-based approach. Further analysis reveals that an optimization-based approach does perform best as long as the designer applies good judgment during uncertainty elicitation. An ignorant or overly confident designer is better off using safety factors. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|