A Hierarchical Statistical Sensitivity Analysis Method for Complex Engineering Systems Design

摘要: Statistical sensitivity analysis (SSA) is playing an increasingly important role in engineering design, especially with the consideration of uncertainty. However, it not straightforward to apply SSA design complex systems due both computational and organizational difficulties. In this paper, facilitate application those that follow hierarchical modeling structures, a statistical (HSSA) method containing top-down strategy for aggregation approach evaluating global index (GSSI) developed. The HSSA introduced invoke critical submodels based on significance submodel performances. A simplified formulation GSSI studied represent effect lower-level input higher-level model response by aggregating results across intermediate levels. sufficient condition under which provides accurate solution derived. To improve accuracy general situation, modified proposed including adjustment coefficient (AC) capture impact nonlinearities upper-level models. efficiency, same set samples used SSAs evaluate AC. examined through mathematical examples three-level vehicle suspension design.