Capabilities of Machine Learning Methods in Prediction of Solubility of Substances in Supercritical Carbon Dioxide DOI
D. A. Lavrukhina,

А. Д. Павлов,

М. П. Шлеймович

и другие.

Russian Journal of Physical Chemistry B, Год журнала: 2024, Номер 18(8), С. 1815 - 1820

Опубликована: Дек. 1, 2024

Язык: Английский

Smart Analytical Chemistry: Integrating Green, Sustainable, White and AI-Driven Approaches in Modern Analysis DOI Creative Commons
Chaudhery Mustansar Hussain,

Ghazanfar Hussain,

Rüstem Keçili

и другие.

TrAC Trends in Analytical Chemistry, Год журнала: 2025, Номер unknown, С. 118295 - 118295

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
A deep-learning model for predicting spatiotemporal evolution in reactive fluidized bed reactor DOI
Chenshu Hu, Xiaolin Guo,

Yuyang Dai

и другие.

Renewable Energy, Год журнала: 2024, Номер 225, С. 120245 - 120245

Опубликована: Март 2, 2024

Язык: Английский

Процитировано

3
Predicting the solubility of solids in supercritical carbon dioxide using the Chrastil equation with parameters estimated from a group contribution method DOI Creative Commons

Clara García-Samino,

Eva M. Martín del Valle, Antonio Tabernero

и другие.

Journal of Molecular Liquids, Год журнала: 2024, Номер 403, С. 124890 - 124890

Опубликована: Май 1, 2024

Язык: Английский

Процитировано

3
Optimal transonic buffet aerodynamic noise PSD predictions with Random Forest: modeling methods and feature selection DOI
Qiao Zhang,

Dangguo Yang,

Weiwei Zhang

и другие.

Aerospace Science and Technology, Год журнала: 2024, Номер 150, С. 109245 - 109245

Опубликована: Май 24, 2024

Язык: Английский

Процитировано

3
Predicting the microalgae lipid profile obtained by supercritical fluid extraction using a machine learning model DOI Creative Commons
Juan J. Pinto, J. Luis Guerrero,

L. Niño de Rivera

и другие.

Frontiers in Chemistry, Год журнала: 2024, Номер 12

Опубликована: Окт. 25, 2024

In this study a Machine Learning model was employed to predict the lipid profile from supercritical fluid extraction (SFE) of microalgae

Язык: Английский

Процитировано

2
A Three-Pronged Computational Approach for Evaluating Density Based Semi Empirical Equations of Supercritical Extraction Process and Data DOI Creative Commons

FNU Srinidhi

Опубликована: Май 8, 2024

Software programs for parameter estimation, phase visualization and predictive modeling of supercritical extraction process data using algorithms is presented in this work. A contextually appropriate, iterative, ordinary least squares estimation selection method developed estimating model coefficients density based semi empirical equations associated with data. Visualization the behaviors projected by specific semiempirical equation(s) also performed iteratively plotting three-dimensional surfaces involving state variables solute solubility mole fraction. Predictive input has been implemented three supervised machine learning (Multilayer perceptron, K-nearest neighbors support vector machine). Hyperparameter optimization prior to prediction. Detailed analysis prediction conducted standard scoring metrics descriptive charts. Theoretical inference discrepancies regarding predicted window maximum solubility, efficiency, vapor liquid equilibrium have elucidated from program outputs. In summary, these are first its kind, accurate, reliable simple computational tools evaluating / designing

Язык: Английский

Процитировано

1
A Three-Pronged Computational Approach for Evaluating Density Based Semi Empirical Equations of Supercritical Extraction Process and Data DOI Creative Commons

FNU Srinidhi

Опубликована: Авг. 7, 2024

Software programs for parameter estimation, phase visualization and predictive modeling of supercritical extraction process data using algorithms is presented in this work. A contextually appropriate, iterative, ordinary least squares estimation selection method developed estimating model coefficients density based semi empirical equations associated with data. Visualization the behaviors projected by specific semiempirical equation(s) also performed iteratively plotting three-dimensional surfaces involving state variables solute solubility mole fraction. Predictive input has been implemented three supervised machine learning (Multilayer perceptron, K-nearest neighbors Support vector regression). Hyperparameter optimization prior to prediction. Detailed analysis prediction conducted standard scoring metrics descriptive charts. Theoretical inference discrepancies regarding predicted window maximum/optimal solubility, efficiency, vapor liquid equilibrium have elucidated from program outputs. In summary, these are unique, accurate, reliable simple computational tools evaluating/designing

Язык: Английский

Процитировано

1
A Three-Pronged Computational Approach for Evaluating Density Based Semi Empirical Equations of Supercritical Extraction Process and Data DOI Creative Commons

FNU Srinidhi

Опубликована: Авг. 8, 2024

Software programs for parameter estimation, phase visualization and predictive modeling of supercritical extraction process data using algorithms is presented in this work. A contextually appropriate, iterative, ordinary least squares estimation selection method developed estimating model coefficients density based semi empirical equations associated with data. Visualization the behaviors projected by specific semiempirical equation(s) also performed iteratively plotting three-dimensional surfaces involving state variables solute solubility mole fraction. Predictive input has been implemented three supervised machine learning (Multilayer perceptron, K-nearest neighbors Support vector regression). Hyperparameter optimization prior to prediction. Detailed analysis prediction conducted standard scoring metrics descriptive charts. Theoretical inference discrepancies regarding predicted window maximum/optimal solubility, efficiency, vapor liquid equilibrium have elucidated from program outputs. In summary, these are unique, accurate, reliable simple computational tools evaluating/designing

Язык: Английский

Процитировано

1
Artificial neural network aided vapor–liquid equilibrium model for multi-component high-pressure transcritical flows with phase change DOI
Navneeth Srinivasan, Suo Yang

Physics of Fluids, Год журнала: 2024, Номер 36(8)

Опубликована: Авг. 1, 2024

In this work, an artificial neural network (ANN) aided vapor–liquid equilibrium (VLE) model is developed and coupled with a fully compressible computational fluid dynamics (CFD) solver to simulate the transcritical processes occurring in high-pressure liquid-fueled propulsion systems. The ANN trained Python using TensorFlow, optimized for inference Open Neural Network Exchange Runtime, C++ based CFD solver. This plug-and-play model/methodology can be used convert any multi-component only open-source packages, without need of in-house VLE development. then study shock-droplet interaction both two- four-component systems turbulent temporal mixing layer (TML), where qualitative quantitative agreement (maximum relative error less than 5%) shown respect results on direct evaluation state-of-the-art situ adaptive tabulation (ISAT) method. method showed 6 times speed-up over 2.2-time ISAT two-component case. faster by 12 interaction. A 7 observed TML case compared while achieving data compression factor 2881. also shows intrinsic load balancing, unlike traditional solvers. strong parallel scalability number processors was all three test cases. Code repository 0D solvers, interface—https://github.com/UMN-CRFEL/ANN_VLE.git.

Язык: Английский

Процитировано

1
Conversion of soybean oil under subcritical water conditions into liquid biofuels with low oxygen contents DOI
Jong-Ho Choi,

JoYong Park,

Aye Aye Myint

и другие.

Fuel, Год журнала: 2024, Номер 378, С. 132772 - 132772

Опубликована: Авг. 23, 2024

Язык: Английский

Процитировано

1