Liao, Kuo-WeiKuo-WeiLiaoHa, ChristopherChristopherHa2026-01-082026-01-082006-09-06https://scholars.lib.ntu.edu.tw/handle/123456789/735194Deterministic optimization process does not consider variability in design variables/parameters and generally drives the optimum design to the vicinity of the imposed constraint boundary. However, when the inevitable variability in design variables/parameters Is taken into consideration, the probability of failure for the deterministic optimum design significantly increases. Reliability-based design optimization (RBDO) incorporates probabilistic analysis into optimization process so that an optimum design has great chance of staying in the feasible design space when variability in design variables/parameters is considered. One of the biggest drawbacks of using the RBDO approach is high computational cost that is often impractical to use in industries. In search of the most suitable RBDO method for industrial applications, we, first, evaluated several existing RBDO approaches such as the double-loop RBDO, the Sequential Optimization and Reliability Assessment (SORA), the Response Surface Method (RSM) in detail. Then, we proposed a more practical RBDO approach called Sequential Optimization with Mean Value based Reliability Analysis (SOMVRA) by combining some of the existing RBDO techniques. The effectiveness of the proposed RBDO approach is demonstrated vising a industry problem. It should be noted that the RSM is a very attractive approach for engineers, but it is very difficult to obtain an accurate surrogate model for a complex problem. Therefore, it should be used carefully. Copyright © 2006 by the American Institute of Aeronautics and Astronautics, Inc. All rights reserved.enHydraulic CylindersNumerical AnalysisIndustrial ApplicationsFinite Element ModelingComputer Aided EngineeringMechanical PropertiesNastranProbability DistributionStress DistributionCentral Composite Designs[SDGs]SDG9conference paper10.2514/6.2006-7096