Abstract
In many cases, a design related simulation environment may be very large, com-prising many codes running in series, parallel, or both, each requiring anywhere from several seconds, to several hours for a single trial run. This may not be a practical or even feasible option when thousands of potential solutions have to be explored. Therefore, the use of a surrogate modeling is proposed to represent a modeling and simulation environment, and increase the efficiency of the exploration of alternatives and the quantification of their uncertainty many times fold. A surrogate model, also known as a metamodel, is a mathematical representation of a portion of a more complex or sophisticated analysis tool. It is generated based on a rigorous statistical regression of inputs and response metrics. These models allow for rapid calculation of responses by employing equations to relate independent variables to those responses. This chapter will cover two types of surrogate models polynomial Response Surface Equations (RSE), and Artificial Neural Networks (ANN).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A 2-level orthogonal array is an array that has two settings for each factor (the minimum and maximum values) and each case is uncorrelated with any of the other cases. Examples include some Taguchi arrays and some fractional factorial designs such as Plackett–Burman designs. If the number of factors is too large to efficiently find an orthogonal array, select a number of cases from the 2-level full factorial.
References
DARPA Neural Network Study (1988) Tech. rep., M.I.T. Lincoln Laboratory, Lexington, MA, 1988.
Demuth H, Beale M (2004) MATLAB: neural network toolbox user’s guide version 4. The MathWorks, Inc.
Frame M, Mandelbrot B, Neger N (2005, April) “Fractal Geometry.” Yale University. http://classes.yale.edu/fractals/CA/NeuralNets/NeuralNets.html.
Johnson C (2005, June) Function approximating neural network generation system (FANNGS) documentation version 1.2.
Kirby MR (2001, May) A methodology for technology identification, evaluation, and selection in conceptual and preliminary aircraft design. Ph.D. Dissertation, Georgia Institute of Technology
Montgomery DC (1976) Design and analysis of experiments. Wiley, New York.
Myers RH, Montgomery DC (1995) Response surface methodology: process and product optimization using designed experiments. Wiley, New York.
SAS Institute Inc (2013) Using JMP 11. Cary, NC: SAS Institute Inc.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag London
About this chapter
Cite this chapter
Ender, T., Balestrini-Robinson, S. (2015). Surrogate Modeling. In: Loper, M. (eds) Modeling and Simulation in the Systems Engineering Life Cycle. Simulation Foundations, Methods and Applications. Springer, London. https://doi.org/10.1007/978-1-4471-5634-5_17
Download citation
DOI: https://doi.org/10.1007/978-1-4471-5634-5_17
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-4471-5633-8
Online ISBN: 978-1-4471-5634-5
eBook Packages: Computer ScienceComputer Science (R0)