Hammersley Sampling and Support-Vector-Regression-Driven Launch Vehicle Design

Multidisciplinary design optimization of solid-fueled multistage space launch vehicles requires complex highdimensional simulation models. To improve on the ability to efficiently explore and approximate large subspaces of these models, this research develops a new set of experimental designs for metamodeling with support vector regression. We propose to Latinize and improve the orthogonality of Hammersley sequence sampling for creating nearly orthogonal and excellent space-filling designs. Multiple measures are used to assess the quality of designed experiments. The designs are used to create metamodels of trajectory simulation of space launch vehicles using support vector regression. A hybrid genetic algorithm uses metamodels to identify minimum-launch-weight space launch vehicles. This approach resulted in an overall rapid and efficient design optimization scheme.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Peter Winker,et al.  Centered L2-discrepancy of random sampling and Latin hypercube design, and construction of uniform designs , 2002, Math. Comput..

[3]  Ian David Lockhart Bogle,et al.  Handling Uncertainty in the Development and Design of Chemical Processes , 2006, Reliab. Comput..

[4]  Takeshi Tsuchiya,et al.  Optimal Conceptual Design of Two-Stage Reusable Rocket Vehicles Including Trajectory Optimization , 2004 .

[5]  Tarek Elhabian,et al.  Rapid Trajectory Optimization Using Computational Intelligence for Guidance and Conceptual Design of Multistage Space Launch Vehicles , 2005 .

[6]  Peter H. Zipfel,et al.  Modeling and Simulation of Aerospace Vehicle Dynamics , 2001 .

[7]  T. Simpson.  A concept exploration method for product family design , 1998 .

[8]  T. Simpson,et al.  Analysis of support vector regression for approximation of complex engineering analyses , 2005, DAC 2003.

[9]  Timothy W. Simpson,et al.  Sampling Strategies for Computer Experiments , 2001 .

[10]  T Haftka Raphael,et al.  Multidisciplinary aerospace design optimization: survey of recent developments , 1996 .

[11]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[12]  Urmila M. Diwekar,et al.  Improving convergence of the stochastic decomposition algorithm by using an efficient sampling technique , 2004, Comput. Chem. Eng..

[13]  Michael S. Eldred,et al.  OVERVIEW OF MODERN DESIGN OF EXPERIMENTS METHODS FOR COMPUTATIONAL SIMULATIONS , 2003 .

[14]  Urmila M. Diwekar,et al.  An efficient sampling technique for off-line quality control , 1997 .

[15]  Ernst Messerschmid,et al.  Multidisciplinary design tool for system and mission optimization of launch vehicles , 1996 .

[16]  Kenny Q. Ye.  Orthogonal Column Latin Hypercubes and Their Application in Computer Experiments , 1998 .

[17]  Dieter M. Wolf.  TRANSYS: Space transportation system preliminary design software , 1994 .

[18]  T. M. Cioppa,et al.  Efficient nearly orthogonal and space-filling experimental designs for high-dimensional complex models , 2002 .

[19]  Takeshi Tsuchiya,et al.  Spaceplane Trajectory Optimization with Vehicle Size Analysis , 1998 .

[20]  Janet Peterson,et al.  Initial Application and Evaluation of a Promising New Sampling Method for Response Surface Generation: Centroidal Voronoi Tessellation * , 2003 .

[21]  Timothy W. Simpson,et al.  Sampling Strategies for Computer Experiments: Design and Analysis , 2001 .