Machine Learning and Data Science in Chemical Engineering

Gao, Hanyu; Zhu, Liang; Luo, Zheng‐Hong; Fraga, Marco A.; Hsing, I‐Ming

doi:10.1021/acs.iecr.2c01788

Cited by 14 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other researchers have used a wide variety of machine learning approaches to predict and ascertain flow behavior, transport properties in multiphase flow systems. 24,25 Based on these successful instances of application of machine learning models to deal with complex non linearly correlated data, we ventured to use GBM, RF, and ANN for prediction of liquid holdup in trickle bed systems.…”

Section: Previous Studies On Data-driven Modelsmentioning

confidence: 99%

“…Their results indicate that reconstruction based on SVR produced the best performance for all data sets; RVR not only produced comparable results for larger data but also was computationally much faster. Other researchers have used a wide variety of machine learning approaches to predict and ascertain flow behavior, transport properties in multiphase flow systems. , Based on these successful instances of application of machine learning models to deal with complex non linearly correlated data, we ventured to use GBM, RF, and ANN for prediction of liquid holdup in trickle bed systems.…”

Section: Previous Studies On Data-driven Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Development of Gradient Boosting Machines for Estimation of Total and Dynamic Liquid Holdup in Trickle Bed Reactor

Bhosale

Pandya

Chatterjee

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Prediction of liquid holdup is of significance in designing and in evaluating the performance of trickle bed contactors. The present work focuses on the development of Gradient Boosting Machines (GBM) for the prediction of total and dynamic liquid holdup in trickle bed reactors. A comprehensive data set of 394 data points of total liquid holdup and 416 data points of dynamic liquid holdup curated from open literature is used in this study. We built GBM models with the input data sets containing 11 governing variables. GBM provided excellent predictions for both data sets. We have also compared the GBM predictions with that of the Random Forest (RF) and Artificial Neural Networks (ANN) predictions. As GBM provided the best performance, we further employed SHAP (SHapley Additive exPlanations) with GBM black box models to get local and global interpretability. Also, we have used SHAP to identify informative subsets of governing variables. The work shall pave the way for use of GBM in prediction of hydrodynamic parameters in multiphase systems.

show abstract

Section: Previous Studies On Data-driven Modelsmentioning

confidence: 99%

Section: Previous Studies On Data-driven Modelsmentioning

confidence: 99%

Development of Gradient Boosting Machines for Estimation of Total and Dynamic Liquid Holdup in Trickle Bed Reactor

Bhosale

Pandya

Chatterjee

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…For such a size, estimating the convex hull is possible within seconds only up to dimension 7 (and dimension 8 in some cases). From dimension 9 onwards the computation time would exceed two hours 1) . Moreover, the computation would require large amounts of memory.…”

Section: Convex Hullmentioning

confidence: 99%

“…From experiments to observational studies and numerical simulations, there are numerous ways to generate data sets. Input-output data sets (i.e., involving input variables and output values) are ubiquitous [1]. Without sufficient expertise either on the process itself or on how to handle data skillfully, a lot of information from laboratories, plants, and computer simulations could be wasted.…”

Section: Introductionmentioning

confidence: 99%

Real‐Time Interactive Navigation on Input‐Output Data Sets in Chemical Processes

Baldan

Ludl

Süss

et al. 2023

Chemie Ingenieur Technik

View full text Add to dashboard Cite

Input‐output data sets are ubiquitous in chemical process engineering. We introduce a real‐time interactive navigation framework that provides several capabilities to the decision maker (DM). Once a surrogate model is trained the DM can perform what‐if analyses in both input and output spaces by manipulating sliders. An approximated convex hull spanned in the input space supports both a reliable surrogate prediction and a navigation close to the data set. The framework has been tested on data sets obtained with a flowsheet simulator modeling a real steam methane reforming process.

show abstract

“…These models use algorithms to learn the underlying complex nonlinear patterns of the data and make faster and accurate predictions. The potential of AI/ML models has been explored for the prediction of various key parameters of the chemical process and engineering applications, which cannot be easily measured experimentally or calculated theoretically. − Several models were developed for accurate prediction of the progress of different chemical reactions using previously reported experimental data. For the case of water gas shift reaction (WGS) over noble metal catalysts, data mining tools such as decision trees, artificial neural networks (ANN), and support vector machines were trained with the data collected from published literature between 2002 and 2012 and they were used to predict the catalytic performance in terms of CO conversion .…”

Section: Introductionmentioning

confidence: 99%

Oxidative Dehydrogenation of Ethane with CO₂ over the Fe-Co/Al₂O₃ Catalyst: Experimental Data Assisted AI Models for Prediction of Ethylene Yield

Povari

Alam

Shylaja

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

In this work, Fe-Co-based mixed metal oxides supported on Al2O3 are proposed for ethylene production through oxidative dehydrogenation of ethane with CO2 (ODH-CO2). Thermodynamic feasibility analysis followed by a systematic experimental study is performed on catalyst synthesis and its composition optimization along with process condition optimization in a fixed bed reactor. The study revealed that 5% Fe loaded on 10% Co/Al2O3, 700 °C, and 1:1 are the optimal composition, temperature, and molar ratio of CO2 to ethane, respectively, achieving 29% ethane conversion and resulting in 16% ethylene yield. Further, the experimental data was used to develop different linear, nonlinear, and ensemble AI models for ethylene yield prediction through a systematic grid search and k-fold cross-validation procedure. Among all the models, the kernel ridge regression model is found to be the most accurate, exhibiting the highest R 2 value of 0.966 and lowest root mean-squared error (RMSE) of 0.032 on test data, successfully capturing the underlying nonlinear dynamics of ODH-CO2.

show abstract

Machine Learning and Data Science in Chemical Engineering

Cited by 14 publications

References 31 publications

Development of Gradient Boosting Machines for Estimation of Total and Dynamic Liquid Holdup in Trickle Bed Reactor

Development of Gradient Boosting Machines for Estimation of Total and Dynamic Liquid Holdup in Trickle Bed Reactor

Real‐Time Interactive Navigation on Input‐Output Data Sets in Chemical Processes

Oxidative Dehydrogenation of Ethane with CO₂ over the Fe-Co/Al₂O₃ Catalyst: Experimental Data Assisted AI Models for Prediction of Ethylene Yield

Contact Info

Product

Resources

About

Machine Learning and Data Science in Chemical Engineering

Cited by 14 publications

References 31 publications

Development of Gradient Boosting Machines for Estimation of Total and Dynamic Liquid Holdup in Trickle Bed Reactor

Development of Gradient Boosting Machines for Estimation of Total and Dynamic Liquid Holdup in Trickle Bed Reactor

Real‐Time Interactive Navigation on Input‐Output Data Sets in Chemical Processes

Oxidative Dehydrogenation of Ethane with CO2 over the Fe-Co/Al2O3 Catalyst: Experimental Data Assisted AI Models for Prediction of Ethylene Yield

Contact Info

Product

Resources

About

Oxidative Dehydrogenation of Ethane with CO₂ over the Fe-Co/Al₂O₃ Catalyst: Experimental Data Assisted AI Models for Prediction of Ethylene Yield