A Hybrid Relationship Modeling Scheme for Parametric Design Considering Uncertainties
This research introduces a new scheme to model different types of relationships in parametric design considering uncertainties. First a hybrid parameter relationship network is developed to associate the parameters through their relationships. In this hybrid parameter relationship network, in addition to the deterministic parameters and relationships, non-deterministic parameters (e.g., random parameters and fuzzy parameters) and non-deterministic relationships (e.g., neural network relationships and fuzzy relationships) can also be modeled. Propagation of parameter values and their uncertainties through this hybrid parameter relationship network is then investigated. Two optimization mechanisms, probability based design optimization and possibility based design optimization, are employed to identify the optimal design considering objective random uncertainties and subjective fuzzy uncertainties. A computer tool has been implemented and used for the optimal design of a solid oxide fuel cell (SOFC) system.