Skip to main navigation Skip to search Skip to main content

Multi-Regional Surrogate Model Selection (MRSMS) approach for the analysis and optimal fitting of univariate responses

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

1 Scopus citations

Abstract

This study focuses on the development of a Multi-Regional Surrogate Model Selection (MRSMS) approach for the optimal fitting and analysis of univariate responses. Using a library of simple curve fitting and regression models, the proposed approach can be used to provide surrogate model recommendations at each section of the response based on the user specified selection of the residual error metric and its corresponding data fit range. The efficacy of the proposed approach is validated using the Henry Hub Natural Gas price dataset and its fitting performance is compared with Piecewise Linear (PL), Neural Network (NN) and Support Vector Regression (SVR) models. It was found that proposed MRSMS approach outperformed the fitting performance of the considered models.

Original languageEnglish
Title of host publicationComputer Aided Chemical Engineering
PublisherElsevier B.V.
Pages925-930
Number of pages6
DOIs
StatePublished - Jul 30 2022
Externally publishedYes

Publication series

NameComputer Aided Chemical Engineering
Volume49
ISSN (Print)1570-7946

Keywords

  • Optimal Data Fitting
  • Piecewise Linear Model
  • Surrogate Model
  • Univariate Responses

Fingerprint

Dive into the research topics of 'Multi-Regional Surrogate Model Selection (MRSMS) approach for the analysis and optimal fitting of univariate responses'. Together they form a unique fingerprint.

Cite this