A Learning Shell for Iterative Design (L’SID): Concepts and Applications

A software shell called Learning Shell for Iterative Design,' L'SID, has been developed in conjunction with a simple data matrix, the learn table.' Histories of design are utilized in aiding the acceleration of routine design problems. The class of problems addressed are non-convex, noninvertible and with multiple performance criteria. The design parameters can be of any definable type; continuous, integer or nonordered feature based. L'SID is domain independent and highly modular. The ability of L'SID to aid deterministic methods is shown statistically with two example problems (extrusion die and airfoil). Results also show the ability of the technique to surmount nonconvexity in design space and computational noise related to roundoff.

[1]  S. Ashley,et al.  Engineous explores the design space , 1992 .

[2]  M. J. Siclari,et al.  Hybrid finite volume approach to Euler solutions for supersonic flows , 1990 .

[3]  S. F. Shen,et al.  Pressure drop of polymeric melts in conical converging flow: Experiments and predictions , 1986 .

[4]  Louis I. Steinberg,et al.  Initial design strategies for iterative design , 1992 .

[5]  Masoud Rais-Rohani,et al.  Integrated aerodynamic-structural design of a transport wing , 1989 .

[6]  Yogesh Jaluria,et al.  Multivariant finite elements for three-dimensional simulation of viscous incompressible flows , 1992 .

[7]  J. Sobieszczanski-Sobieski,et al.  Sensitivity of control-augmented structure obtained by a system decomposition method , 1991 .

[8]  David C. Brown,et al.  An Approach to Expert Systems for Mechanical Design. , 1983 .

[9]  Jack Mostow,et al.  Automated reuse of design plans , 1989, Artif. Intell. Eng..

[10]  John R. Dixon,et al.  A review of research in mechanical engineering design. Part I: Descriptive, prescriptive, and computer-based models of design processes , 1989 .

[11]  Sherif Aly,et al.  Stochastic optimization applied to CFD shape design , 1995 .

[12]  Louis I. Steinberg,et al.  EVEXED and MEET for Mechanical Design: Testing Structural Decomposition and Constraint Propagation , 1996, Artif. Intell..

[13]  Sanjay Goel,et al.  Integration of artificial intelligence and numerical optimization techniques for the design of complex aerospace systems , 1992 .