Home > Research > Publications & Outputs > Modeling industrial hydrocyclone operational va...

Links

Text available via DOI:

View graph of relations

Modeling industrial hydrocyclone operational variables by SHAP-CatBoost - A “conscious lab” approach

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Modeling industrial hydrocyclone operational variables by SHAP-CatBoost - A “conscious lab” approach. / Chehreh Chelgani, S.; Nasiri, H.; Tohry, A. et al.
In: Powder Technology, Vol. 420, 118416, 15.04.2023.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Chehreh Chelgani S, Nasiri H, Tohry A, Heidari HR. Modeling industrial hydrocyclone operational variables by SHAP-CatBoost - A “conscious lab” approach. Powder Technology. 2023 Apr 15;420:118416. Epub 2023 Mar 10. doi: 10.1016/j.powtec.2023.118416

Author

Chehreh Chelgani, S. ; Nasiri, H. ; Tohry, A. et al. / Modeling industrial hydrocyclone operational variables by SHAP-CatBoost - A “conscious lab” approach. In: Powder Technology. 2023 ; Vol. 420.

Bibtex

@article{3b3a978eeb7d49b9a85f493b74bf39ef,
title = "Modeling industrial hydrocyclone operational variables by SHAP-CatBoost - A “conscious lab” approach",
abstract = "Undoubtedly hydrocyclones play a critical role in powder technology, which can considerably affect the plants' process efficiency. However, hydrocyclones were rarely modeled on an industrial scale, where a model can be used to train operators and minimize potential scale-up errors and lab costs. The novel approach for filling such a gap would be using conscious lab “CL” as a new concept that builds based on an industrial dataset and explainable artificial intelligence (XAI). As a novel approach, this study developed a CL and explored the interactions between hydrocyclone variables by the most recent XAI method called “SHapley Additive exPlanations (SHAP)”, and a novel machine-learning model, “CatBoost”. The hydrocyclone output and the particle size of the plant magnetic separator were modeled by SHAP-CatBoost. SHAP could successfully model all the relationships, and CatBoost could predict the O80 and K80 where outcomes had a higher accuracy (R2 ∼ 0.90) than other conventional AIs.",
keywords = "Hydrocyclone, Random forest, Support vector regression, Ultrafine particles, XGBoost",
author = "{Chehreh Chelgani}, S. and H. Nasiri and A. Tohry and Heidari, {H. R.}",
note = "Publisher Copyright: {\textcopyright} 2023 The Authors",
year = "2023",
month = apr,
day = "15",
doi = "10.1016/j.powtec.2023.118416",
language = "English",
volume = "420",
journal = "Powder Technology",
issn = "0032-5910",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Modeling industrial hydrocyclone operational variables by SHAP-CatBoost - A “conscious lab” approach

AU - Chehreh Chelgani, S.

AU - Nasiri, H.

AU - Tohry, A.

AU - Heidari, H. R.

N1 - Publisher Copyright: © 2023 The Authors

PY - 2023/4/15

Y1 - 2023/4/15

N2 - Undoubtedly hydrocyclones play a critical role in powder technology, which can considerably affect the plants' process efficiency. However, hydrocyclones were rarely modeled on an industrial scale, where a model can be used to train operators and minimize potential scale-up errors and lab costs. The novel approach for filling such a gap would be using conscious lab “CL” as a new concept that builds based on an industrial dataset and explainable artificial intelligence (XAI). As a novel approach, this study developed a CL and explored the interactions between hydrocyclone variables by the most recent XAI method called “SHapley Additive exPlanations (SHAP)”, and a novel machine-learning model, “CatBoost”. The hydrocyclone output and the particle size of the plant magnetic separator were modeled by SHAP-CatBoost. SHAP could successfully model all the relationships, and CatBoost could predict the O80 and K80 where outcomes had a higher accuracy (R2 ∼ 0.90) than other conventional AIs.

AB - Undoubtedly hydrocyclones play a critical role in powder technology, which can considerably affect the plants' process efficiency. However, hydrocyclones were rarely modeled on an industrial scale, where a model can be used to train operators and minimize potential scale-up errors and lab costs. The novel approach for filling such a gap would be using conscious lab “CL” as a new concept that builds based on an industrial dataset and explainable artificial intelligence (XAI). As a novel approach, this study developed a CL and explored the interactions between hydrocyclone variables by the most recent XAI method called “SHapley Additive exPlanations (SHAP)”, and a novel machine-learning model, “CatBoost”. The hydrocyclone output and the particle size of the plant magnetic separator were modeled by SHAP-CatBoost. SHAP could successfully model all the relationships, and CatBoost could predict the O80 and K80 where outcomes had a higher accuracy (R2 ∼ 0.90) than other conventional AIs.

KW - Hydrocyclone

KW - Random forest

KW - Support vector regression

KW - Ultrafine particles

KW - XGBoost

U2 - 10.1016/j.powtec.2023.118416

DO - 10.1016/j.powtec.2023.118416

M3 - Journal article

AN - SCOPUS:85149831670

VL - 420

JO - Powder Technology

JF - Powder Technology

SN - 0032-5910

M1 - 118416

ER -