Abstract：There exist a great amount of uncertain factors in actual engineering. In order to involve these uncertain factors in analytical model, it has been expressed as convex variables. In addition, the convex model was further classified into hyper-ellipsoidal model and interval model. After pointing out the intrinsic difference between these two kinds of models, the principle for applying which one of the models within the analysis has indicated according to the available testing points. After standardized the convex variables, the difference and relation between the two models for the optimization and solution process have presented. With the analysis mentality available from hyper-ellipsoidal model, the basic method about robust optimization for interval model was emphasized. After classification for the interval variables within the optimization process, the characteristics of robust optimization were highlighted with different constraint condition. Using target-performance-based analytical scheme, the algorithm, solution step and convergence criteria for robust optimization have presented with only one reliability index. Numerical examples and engineering problems are used to demonstrate the effectiveness and correctness of the proposed approach.
2014, Vol. 35 
