Adaptive sequential sampling for surrogate model generation with artificial neural networks

Eason, John P.; Cremaschi, Selen

doi:10.1016/j.compchemeng.2014.05.021

Cited by 230 publications

(114 citation statements)

References 25 publications

Supporting

Mentioning

114

Contrasting

Order By: Relevance

“…This criteria becomes especially important for process synthesis and design applications as these problems generally have high number of input/output dimensions. A recent contribution by Eason and Cremaschi (2014) discusses potential impacts of exploration and exploitation in surrogatemodel construction, and introduces two algorithms that adaptively locate new input/output pairs for surrogate model construction and scale well to high dimensions.…”

Section: Surrogate Models For Process Synthesis and Designmentioning

confidence: 99%

A perspective on process synthesis: Challenges and prospects

Cremaschi

2015

Computers & Chemical Engineering

Self Cite

View full text Add to dashboard Cite

a b s t r a c tThis paper gives the author's perspective on some of the open questions and opportunities in process synthesis focusing on separation systems as the application. Driven by energy and environmental concerns and challenged by introduction of new raw materials, this author anticipates significant advances in: (1) novel approaches that integrate experimental studies and process synthesis activities, and multiscale and surrogate models for accurately capturing the behavior of these unconventional mixtures, (2) systematic generation of alternatives for processing these mixtures, and (3) global, robust, and stochastic optimization for identifying the optimum alternative. This paper is an extended version of a conference

show abstract

Section: Surrogate Models For Process Synthesis and Designmentioning

confidence: 99%

A perspective on process synthesis: Challenges and prospects

Cremaschi

2015

Computers & Chemical Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…In general, there is no rigorous, all‐encompassing analysis of surrogate model selection, sampling strategy, and underlying model; however, several groups actively pursuing various pieces of this puzzle, e.g., Boukouvala et al. , Nuchitprasittichai and Cremaschi , Eason and Cremaschi , Sikorski et al. , Cozad et al.…”

Section: Surrogate Modelingmentioning

confidence: 99%

Overview of Surrogate Modeling in Chemical Process Engineering

McBride

Sundmacher

2019

Chemie Ingenieur Technik

211

108

View full text Add to dashboard Cite

The ability to accurately model and simulate chemical processes has been paramount to the growing success and efficiency in process design and operation. These improvements usually come with increasing complexity of the underlying models leading to substantial computational effort in their use. It may also occur that the structure of the model is sometimes unknown making optimization and study difficult. To circumvent these issues, mathematically simpler models, commonly known as surrogate models, have been designed and used to successfully replace these complex, underlying models with much success. This technique has seen increasing use within the chemical process engineering field and this article summarizes some popular surrogates and their recent use in this area.

show abstract

“…ANN fits any complex nonlinear functions, given sufficient complexity of the trained network . ANN has been applied successfully to many areas in chemical engineering, such as cracking furnace modelling and optimization, optimization of CO 2 capture cost using ANN surrogate models, optimization of industrial urea reactors, frictional pressure drop of tapered bubble columns, and estimation of gas‐oil minimum miscibility pressure using PSO‐ANN …”

Section: Introductionmentioning

confidence: 99%

“…To choose the next sampling points, they proposed a sample‐point quality parameter that simultaneously considers the Euclidean distance between the candidate points and their nearest neighbour, and the estimated predictor variance for a larger number of candidates is randomly generated during design space. The variance of different predictors from K‐ folds cross‐validation may arise from the undesirable oscillatory behaviour of ANNs rather than the highly nonlinear behaviour of the system, because the behaviour of ANN may exhibit undesirable oscillatory behaviour between sample points . In addition, steep peaks or valleys of a complex process may be missed by adaptive sampling based on prediction variance when undesirable oscillatory behaviour is insignificant but its nonlinear characteristics are significant.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Sampling for Surrogate Modelling with Artificial Neural Network and its Application in an Industrial Cracking Furnace

Jin

et al. 2016

Can J Chem Eng

View full text Add to dashboard Cite

In surrogate modelling, a simple functional approximation of a complex system model is always constructed to reduce the computational expense, and the selection of a suitable surrogate model and a sampling method are key to obtaining a surrogate model for a complex system. To construct an appropriate surrogate model, three methods of adaptive surrogate modelling that use artificial neural networks (ANN) are developed by incorporating a new mechanism for automatically determining the number of hidden nodes and/or a new prediction error-based mixed adaptive sampling method. In the automatic determination, the number of hidden nodes can adaptively change according to the effective rate of parameters in the ANN during the adaptive surrogate modelling process. As a result, an improper number of hidden nodes determined by the empirical method can be avoided. The prediction error-based mixed adaptive sampling method is capable of finding the strong nonlinear behaviour of the underlying system, which is easily missed by the traditional prediction variance-based sampling method. The three methods and the previous method for adaptive surrogate modelling that use ANN are tested and compared in terms of replicating the behaviours of three types of challenge functions to determine the efficacy of the developed methods. Furthermore, these methods are used in an engineering problem of surrogate modelling for a cracking reaction simulator to validate the efficacy of the developed methods.

show abstract

Adaptive sequential sampling for surrogate model generation with artificial neural networks

Cited by 230 publications

References 25 publications

A perspective on process synthesis: Challenges and prospects

A perspective on process synthesis: Challenges and prospects

Overview of Surrogate Modeling in Chemical Process Engineering

Adaptive Sampling for Surrogate Modelling with Artificial Neural Network and its Application in an Industrial Cracking Furnace

Contact Info

Product

Resources

About