Hybrid intelligent models for water activity prediction in complex ionic liquid systems; Journal of Environmental Chemical Engineering; Vol. 13, iss. 6

Dades bibliogràfiques
Parent link:Journal of Environmental Chemical Engineering.— .— Amsterdam: Elsevier Science Publishing Company Inc.
Vol. 13, iss. 6.— 2025.— Article number 120358, 24 p.
Altres autors: Davoodi Sh. Shadfar, Thanh Hung Vo, Wood D. A. David, Makarov N. S. Nikita Sergeevich, Mehrad M. Mohammad, Burnaev E. Evgeny
Sumari:Title screen
Precise prediction of water activity (WA) in ionic liquids (IL) systems is impeded by their complex, nonlinear interactions, and the limitations of traditional thermodynamic models. Machine learning offers an effective alternative for capturing complex property patterns and improving WA predictions. This study develops predictive models for WA using the multilayer extreme learning machine (MELM) and least squares support vector machine algorithms, as well as hybrid versions optimized with particle swarm optimization (PSO) and genetic algorithm, based on a large laboratory dataset. Following data cleaning, the feature selection analysis identified seven key parameters: temperature, pressure, molality of second composition, molality of IL, critical temperature of IL, acentric factor of IL, and critical pressure of IL. A portion of the training data was allocated as validation data using k-fold cross-validation, with the number of folds carefully selected to ensure optimal model performance and prevent overfitting. The results demonstrate that hybrid models in the prediction of the target variable, particularly MELM-PSO, exhibit superior reproducibility, lower error values across the training, validation, and testing phases, and reduced uncertainty and overfitting compared to other models. The proposed WA-prediction models can potentially be applied to various industrial sectors, including energy storage, gas purification, and process control
Текстовый файл
AM_Agreement
Idioma:anglès
Publicat: 2025
Matèries:
Accés en línia:https://doi.org/10.1016/j.matlet.2025.140037
Format: Electrònic Capítol de llibre
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=687136

MARC

LEADER 00000naa0a2200000 4500
001 687136
005 20260629094259.0
090 |a 687136 
100 |a 20260629d2025 k||y0rusy50 ba 
101 0 |a eng 
102 |a NL 
135 |a drcn ---uucaa 
181 0 |a i   |b  e  
182 0 |a b 
183 0 |a cr  |2 RDAcarrier 
200 1 |a Hybrid intelligent models for water activity prediction in complex ionic liquid systems  |f Shadfar Davoodi, Hung Vo Thanh, David A. Wood [et al.] 
203 |a Текст  |b визуальный  |c электронный 
283 |a online_resource  |2 RDAcarrier 
300 |a Title screen 
320 |a References: 83 tit 
330 |a Precise prediction of water activity (WA) in ionic liquids (IL) systems is impeded by their complex, nonlinear interactions, and the limitations of traditional thermodynamic models. Machine learning offers an effective alternative for capturing complex property patterns and improving WA predictions. This study develops predictive models for WA using the multilayer extreme learning machine (MELM) and least squares support vector machine algorithms, as well as hybrid versions optimized with particle swarm optimization (PSO) and genetic algorithm, based on a large laboratory dataset. Following data cleaning, the feature selection analysis identified seven key parameters: temperature, pressure, molality of second composition, molality of IL, critical temperature of IL, acentric factor of IL, and critical pressure of IL. A portion of the training data was allocated as validation data using k-fold cross-validation, with the number of folds carefully selected to ensure optimal model performance and prevent overfitting. The results demonstrate that hybrid models in the prediction of the target variable, particularly MELM-PSO, exhibit superior reproducibility, lower error values across the training, validation, and testing phases, and reduced uncertainty and overfitting compared to other models. The proposed WA-prediction models can potentially be applied to various industrial sectors, including energy storage, gas purification, and process control 
336 |a Текстовый файл 
371 0 |a AM_Agreement 
461 1 |t Journal of Environmental Chemical Engineering  |c Amsterdam  |n Elsevier Science Publishing Company Inc. 
463 1 |t Vol. 13, iss. 6  |v Article number 120358, 24 p.  |d 2025 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
610 1 |a Water activity prediction 
610 1 |a Ionic liquids 
610 1 |a Multilayer extreme learning machine 
610 1 |a Hybrid models 
610 1 |a Particle swarm optimization 
701 1 |a Davoodi  |b Sh.  |c specialist in the field of petroleum engineering  |c Research Engineer of Tomsk Polytechnic University  |f 1990-  |g Shadfar  |9 22200 
701 0 |a Thanh Hung Vo  
701 1 |a Wood  |b D. A.  |g David 
701 1 |a Makarov  |b N. S.  |g Nikita Sergeevich  |f 1999-  |c specialist in the field of petroleum engineering  |c Engineer of Tomsk Polytechnic University  |9 88868 
701 1 |a Mehrad  |b M.  |g Mohammad 
701 1 |a Burnaev  |b E.  |g Evgeny 
801 0 |a RU  |b 63413507  |c 20260629 
850 |a 63413507 
856 4 0 |u https://doi.org/10.1016/j.matlet.2025.140037  |z https://doi.org/10.1016/j.matlet.2025.140037 
942 |c CF