Probabilistic-based design optimization

It has been widely recognized that optimization methodologies should account for the stochastic nature of random parameters in products, systems and processes. These stochastic natures can be described by their probabilistic information. The engineering problems that must deal with uncertainty are of different types: 1) sensitivity analysis under uncertainty, 2) process capability studies, 3) reliability assessment, 4) reliability optimization, 5) process design optimization under uncertainty. The last two problems of this list can be solved with optimization methodologies based on probabilistic theory, which can be grouped into two main categories: reliability-based design optimization (RBDO) and robust design optimization (RDO).

RBDO methods attempt to find the optimum design with allowance of a specific risk and target reliability level which account for the various sources of uncertainty.[1] RDO methods primarily seek to maximize the performance and simultaneously to minimize the sensitivity of the performance with respect to random parameters.[2]

See also

Robust optimization

References

  1. ↑ Strano, M. (2006). "Optimization under uncertainty of sheet-metal-forming processes by the finite element method". Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture 220 (8): 1305–1315. doi:10.1243/09544054JEM480.
  2. ↑ Dan M. Frangopol and Kurt Maute, Life-cycle reliability-based optimization of civil and aerospace structure, Computers and Structures, (2003) 81: 397–410
This article is issued from Wikipedia - version of the Saturday, August 29, 2015. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.