Increasing Superstructure Optimization Capacity Through Self-Learning Surrogate Models

Simulation-based optimization models are widely applied to find optimal operating conditions of processes. Often, computational challenges arise from model complexity, making the generation of reliable design solutions difficult. We propose an algorithm for replacing non-linear process simulation mo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Julia Granacher, Ivan Daniel Kantor, François Maréchal
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	superstructure optimization surrogate models active learning energy systems process design mathematical programming Technology T Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/fc8e64d0cca34a4e968769333a745d00
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fc8e64d0cca34a4e968769333a745d00
record_format	dspace
spelling	oai:doaj.org-article:fc8e64d0cca34a4e968769333a745d002021-11-04T04:41:21ZIncreasing Superstructure Optimization Capacity Through Self-Learning Surrogate Models2673-271810.3389/fceng.2021.778876https://doaj.org/article/fc8e64d0cca34a4e968769333a745d002021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fceng.2021.778876/fullhttps://doaj.org/toc/2673-2718Simulation-based optimization models are widely applied to find optimal operating conditions of processes. Often, computational challenges arise from model complexity, making the generation of reliable design solutions difficult. We propose an algorithm for replacing non-linear process simulation models integrated in multi-level optimization of a process and energy system superstructure with surrogate models, applying an active learning strategy to continuously enrich the database on which the surrogate models are trained and evaluated. Surrogate models are generated and trained on an initial data set, each featuring the ability to quantify the uncertainty with which a prediction is made. Until a defined prediction quality is met, new data points are continuously labeled and added to the training set. They are selected from a pool of unlabeled data points based on the predicted uncertainty, ensuring a rapid improvement of surrogate quality. When applied in the optimization superstructure, the surrogates can only be used when the prediction quality for the given data point reaches a specified threshold, otherwise the original simulation model is called for evaluating the process performance and the newly obtained data points are used to improve the surrogates. The method is tested on three simulation models, ranging in size and complexity. The proposed approach yields mean squared errors of the test prediction below 2% for all cases. Applying the active learning approach leads to better predictions compared to random sampling for the same size of database. When integrated in the optimization framework, simpler surrogates are favored in over 60% of cases, while the more complex ones are enabled by using simulation results generated during optimization for improving the surrogates after the initial generation. Significant time savings are recorded when using complex process simulations, though the advantage gained for simpler processes is marginal. Overall, we show that the proposed method saves time and adds flexibility to complex superstructure optimization problems that involve optimizing process operating conditions. Computational time can be greatly reduced without penalizing result quality, while the continuous improvement of surrogates when simulation is used in the optimization leads to a natural refinement of the model.Julia GranacherIvan Daniel KantorIvan Daniel KantorFrançois MaréchalFrontiers Media S.A.articlesuperstructure optimizationsurrogate modelsactive learningenergy systemsprocess designmathematical programmingTechnologyTChemical technologyTP1-1185ENFrontiers in Chemical Engineering, Vol 3 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	superstructure optimization surrogate models active learning energy systems process design mathematical programming Technology T Chemical technology TP1-1185
spellingShingle	superstructure optimization surrogate models active learning energy systems process design mathematical programming Technology T Chemical technology TP1-1185 Julia Granacher Ivan Daniel Kantor Ivan Daniel Kantor François Maréchal Increasing Superstructure Optimization Capacity Through Self-Learning Surrogate Models
description	Simulation-based optimization models are widely applied to find optimal operating conditions of processes. Often, computational challenges arise from model complexity, making the generation of reliable design solutions difficult. We propose an algorithm for replacing non-linear process simulation models integrated in multi-level optimization of a process and energy system superstructure with surrogate models, applying an active learning strategy to continuously enrich the database on which the surrogate models are trained and evaluated. Surrogate models are generated and trained on an initial data set, each featuring the ability to quantify the uncertainty with which a prediction is made. Until a defined prediction quality is met, new data points are continuously labeled and added to the training set. They are selected from a pool of unlabeled data points based on the predicted uncertainty, ensuring a rapid improvement of surrogate quality. When applied in the optimization superstructure, the surrogates can only be used when the prediction quality for the given data point reaches a specified threshold, otherwise the original simulation model is called for evaluating the process performance and the newly obtained data points are used to improve the surrogates. The method is tested on three simulation models, ranging in size and complexity. The proposed approach yields mean squared errors of the test prediction below 2% for all cases. Applying the active learning approach leads to better predictions compared to random sampling for the same size of database. When integrated in the optimization framework, simpler surrogates are favored in over 60% of cases, while the more complex ones are enabled by using simulation results generated during optimization for improving the surrogates after the initial generation. Significant time savings are recorded when using complex process simulations, though the advantage gained for simpler processes is marginal. Overall, we show that the proposed method saves time and adds flexibility to complex superstructure optimization problems that involve optimizing process operating conditions. Computational time can be greatly reduced without penalizing result quality, while the continuous improvement of surrogates when simulation is used in the optimization leads to a natural refinement of the model.
format	article
author	Julia Granacher Ivan Daniel Kantor Ivan Daniel Kantor François Maréchal
author_facet	Julia Granacher Ivan Daniel Kantor Ivan Daniel Kantor François Maréchal
author_sort	Julia Granacher
title	Increasing Superstructure Optimization Capacity Through Self-Learning Surrogate Models
title_short	Increasing Superstructure Optimization Capacity Through Self-Learning Surrogate Models
title_full	Increasing Superstructure Optimization Capacity Through Self-Learning Surrogate Models
title_fullStr	Increasing Superstructure Optimization Capacity Through Self-Learning Surrogate Models
title_full_unstemmed	Increasing Superstructure Optimization Capacity Through Self-Learning Surrogate Models
title_sort	increasing superstructure optimization capacity through self-learning surrogate models
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/fc8e64d0cca34a4e968769333a745d00
work_keys_str_mv	AT juliagranacher increasingsuperstructureoptimizationcapacitythroughselflearningsurrogatemodels AT ivandanielkantor increasingsuperstructureoptimizationcapacitythroughselflearningsurrogatemodels AT ivandanielkantor increasingsuperstructureoptimizationcapacitythroughselflearningsurrogatemodels AT francoismarechal increasingsuperstructureoptimizationcapacitythroughselflearningsurrogatemodels
_version_	1718445249074823168

Increasing Superstructure Optimization Capacity Through Self-Learning Surrogate Models

Ejemplares similares