A simple PLS-based approach for the construction of compact surrogate models

Abstract This work describes a simple algorithm based on partial least square (PLS) to enable the construction of surrogate models using a single tuning parameter. The proposed algorithm is illustrated with the case study of a membrane module for natural gas sweetening, where a mechanistic model is used as data generator. The effect of the tuning parameter is analysed, and it is shown that this parameter captures the trade-off between the surrogates’ accuracy and their complexity (number of terms). The algorithm performance is also compared with four different approaches from the literature, showing a similar performance.

[1]  Riccardo Leardi,et al.  Application of genetic algorithm–PLS for feature selection in spectral data sets , 2000 .

[2]  Kimito Funatsu,et al.  GA Strategy for Variable Selection in QSAR Studies: GA-Based PLS Analysis of Calcium Channel Antagonists , 1997, J. Chem. Inf. Comput. Sci..

[3]  D. Massart,et al.  Elimination of uninformative variables for multivariate calibration. , 1996, Analytical chemistry.

[4]  Matthias Wessling,et al.  Modeling Gas Permeation by Linking Nonideal Effects , 2013 .

[5]  Christodoulos A. Floudas,et al.  ARGONAUT: AlgoRithms for Global Optimization of coNstrAined grey-box compUTational problems , 2017, Optim. Lett..

[6]  Tahir Mehmood,et al.  A review of variable selection methods in Partial Least Squares Regression , 2012 .

[7]  I. Grossmann,et al.  An algorithm for the use of surrogate models in modular flowsheet optimization , 2008 .

[8]  Agnar Höskuldsson,et al.  COVPROC method: strategy in modeling dynamic systems , 2003 .

[9]  Jianqing Fan,et al.  Sure independence screening for ultrahigh dimensional feature space , 2006, math/0612857.

[10]  David C. Miller,et al.  Learning surrogate models for simulation‐based optimization , 2014 .

[11]  N. Zheng,et al.  Global Optimization of Stochastic Black-Box Systems via Sequential Kriging Meta-Models , 2006, J. Glob. Optim..

[12]  Atharv Bhosekar,et al.  Advances in surrogate based modeling, feasibility analysis, and optimization: A review , 2018, Comput. Chem. Eng..

[13]  Christos T. Maravelias,et al.  Surrogate‐based superstructure optimization framework , 2011 .