This paper describes the use of approximation in Collaborative Optimization (CO) method, one of the Multidisciplinary Design Optimization (MDO) techniques. The approximation is used to model the result of a disciplinary design, optimal discrepancy function value, as a function of the interdisciplinary target variables passed from system level to the discipline. The optimal discrepancy function value is used to examine the interdisciplinary compatibility constraint (discrepancy function = 0) duringthe system level optimization. However, the peculiar shape of the compatibility constraint makes it difficult to exploit well–developed conventional approximation methods. This paper introduces the combination of neural network classification and kriging to resolve this problem. In addition, for the purpose of enhancing the accuracy of the approximation, the approximation is continuously updated using the information obtained from the system level optimization. This iterative process is continued until acceptable convergence is achieved.

Multidisciplinary Design Optimization(MDO) method that considers principles in various fields affecting big scale structure and system design at the same time is used. Because most variables are connected many engineering phenomena under the classic optimized design method(all-in-one design approach), it is hard to judge the meaning of final design solution obtained, and there are cases where all variables converge before reaching the optimal design value in large-scale design problems with many variables. Collaborative Optimization (CO) method, the most advanced MDO approach, is used to efficiently solve these optimum problems, to efficiently analyze design problems involving numerous design variables and constraints and in which various engineering phenomena occur. However, the application of the MDO problem to CO introduces a number of numerical problems by destroying the numerical properties of the original optimal design problem. Therefore, this study researches one solution by listing the problems of CO after organizing various approaches of MDO.