Vol.:(0123456789) 1 3
Research in Engineering Design
https://doi.org/10.1007/s00163-020-00336-7
ORIGINAL PAPER
Managing computational complexity using surrogate models:
a critical review
Reza Alizadeh
1
· Janet K. Allen
1
· Farrokh Mistree
2
Received: 12 August 2018 / Revised: 4 March 2020 / Accepted: 9 March 2020
© Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract
In simulation-based realization of complex systems, we are forced to address the issue of computational complexity. One
critical issue that must be addressed is the approximation of reality using surrogate models to replace expensive simulation
models of engineering problems. In this paper, we critically review over 200 papers. We fnd that a framework for selecting
appropriate surrogate modeling methods for a given function with specifc requirements has been lacking. Having such a
framework for surrogate model users, specifcally practitioners in industry, is very important because there is very limited
information about the performance of diferent models before applying them on the problem. Our contribution in this paper
is to address this gap by creating practical guidance based on a trade-of among three main drivers, namely, size (how
much information is necessary to compute the surrogate model), accuracy (how accurate the surrogate model must be) and
computational time (how much time is required for the surrogate modeling process). Using the proposed guidance a huge
amount of time is saved by avoiding time-consuming comparisons before selecting the appropriate surrogate model. To
make this contribution, we review the state-of-the-art surrogate modeling literature to answer the following three questions:
(1) What are the main classes of the design of experiment (DOE) methods, surrogate modeling methods and model-ftting
methods based on the requirements of size, computational time, and accuracy? (2) Which surrogate modeling method is
suitable based on the critical characteristics of the requirements of size, computational time and accuracy? (3) Which DOE
is suitable based on the critical characteristics of the requirements of size, computational time and accuracy? Based on these
three characteristics, we fnd six diferent qualitative categories for the surrogate models through a critical evaluation of the
literature. These categories provide a framework for selecting an efcient surrogate modeling process to assist those who wish
to select more appropriate surrogate modeling techniques for a given function. It is also summarized in Table 4 and Figs. 2,
3. MARS, response surface models, and kriging are more appropriate for large problems, acquiring less computation time
and high accuracy, respectively. Also, Latin Hypercube, fractional factorial designs and D-Optimal designs are appropriate
experimental designs. Our contribution is to propose a qualitative evaluation and a mental model which is based on quantita-
tive results and fndings of authors in the published literature. The value of such a framework is in providing practical guide
for researchers and practitioners in industry to choose the most appropriate surrogate model based on incomplete information
about an engineering design problem. Another contribution is to use three drivers, namely, computational time, accuracy,
and problem size instead of using a single measure that authors generally use in the published literature.
Keywords Surrogate model · Model selection · Meta model · Computational complexity · Design · Response surface
Abbreviations
ANN Artifcial Neural Network
CCD Central composite design
CFD Computational fuid dynamics
CPU Central processing unit
DOE Design of experiments
DST Dempster–Shafer theory
EA Evolutionary algorithm
FD Factorial design
FEA Finite element analysis
FFD Fractional factorial design
GSME Generalized mean square error
KRG Kriging
LS Least squares
MAE Mean absolute error
MAPE Mean absolute percentage error
* Janet K. Allen
janet.allen@ou.edu
Extended author information available on the last page of the article