Interpretable modeling of metallurgical responses for an industrial coal column flotation circuit by XGBoost and SHAP-A “conscious-lab” development

Computing and Communications

Text available via DOI:

https://doi.org/10.1016/j.ijmst.2021.10.006
Final published version
Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Keywords

Coal flotation, Explainable AI, Separation efficiency, SHAP, XGBoost

View graph of relations

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Interpretable modeling of metallurgical responses for an industrial coal column flotation circuit by XGBoost and SHAP-A “conscious-lab” development. / Chehreh Chelgani, S.; Nasiri, H.; Alidokht, M.
In: International Journal of Mining Science and Technology, Vol. 31, No. 6, 30.11.2021, p. 1135-1144.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Bibtex

@article{7b9083682e9845cea640156664b6ad65,

title = "Interpretable modeling of metallurgical responses for an industrial coal column flotation circuit by XGBoost and SHAP-A “conscious-lab” development",

abstract = "Surprisingly, no investigation has been explored relationships between operating variables and metallurgical responses of coal column flotation (CF) circuits based on industrial databases for under operation plants. As a novel approach, this study implemented a conscious-lab “CL” for filling this gap. In this approach, for developing the CL dedicated to an industrial CF circuit, SHapley Additive exPlanations (SHAP) and extreme gradient boosting (XGBoost) were powerful unique machine learning systems for the first time considered. These explainable artificial intelligence models could effectively convert the dataset to a basis that improves human capabilities for better understanding, reasoning, and planning the unit. SHAP could provide precise multivariable correlation assessments between the CF dataset by using the Tabas Parvadeh coal plant (Kerman, Iran), and showed the importance of solid percentage and washing water on the metallurgical responses of the coal CF circuit. XGBoost could predict metallurgical responses (R-square > 0.88) based on operating variables that showed quite higher accuracy than typical modeling methods (Random Forest and support vector regression).",

keywords = "Coal flotation, Explainable AI, Separation efficiency, SHAP, XGBoost",

author = "{Chehreh Chelgani}, S. and H. Nasiri and M. Alidokht",

note = "Publisher Copyright: {\textcopyright} 2021",

year = "2021",

month = nov,

day = "30",

doi = "10.1016/j.ijmst.2021.10.006",

language = "English",

volume = "31",

pages = "1135--1144",

journal = "International Journal of Mining Science and Technology",

issn = "2095-2686",

publisher = "China University of Mining and Technology",

number = "6",

}

RIS

TY - JOUR

T1 - Interpretable modeling of metallurgical responses for an industrial coal column flotation circuit by XGBoost and SHAP-A “conscious-lab” development

AU - Chehreh Chelgani, S.

AU - Nasiri, H.

AU - Alidokht, M.

PY - 2021/11/30

Y1 - 2021/11/30

N2 - Surprisingly, no investigation has been explored relationships between operating variables and metallurgical responses of coal column flotation (CF) circuits based on industrial databases for under operation plants. As a novel approach, this study implemented a conscious-lab “CL” for filling this gap. In this approach, for developing the CL dedicated to an industrial CF circuit, SHapley Additive exPlanations (SHAP) and extreme gradient boosting (XGBoost) were powerful unique machine learning systems for the first time considered. These explainable artificial intelligence models could effectively convert the dataset to a basis that improves human capabilities for better understanding, reasoning, and planning the unit. SHAP could provide precise multivariable correlation assessments between the CF dataset by using the Tabas Parvadeh coal plant (Kerman, Iran), and showed the importance of solid percentage and washing water on the metallurgical responses of the coal CF circuit. XGBoost could predict metallurgical responses (R-square > 0.88) based on operating variables that showed quite higher accuracy than typical modeling methods (Random Forest and support vector regression).

AB - Surprisingly, no investigation has been explored relationships between operating variables and metallurgical responses of coal column flotation (CF) circuits based on industrial databases for under operation plants. As a novel approach, this study implemented a conscious-lab “CL” for filling this gap. In this approach, for developing the CL dedicated to an industrial CF circuit, SHapley Additive exPlanations (SHAP) and extreme gradient boosting (XGBoost) were powerful unique machine learning systems for the first time considered. These explainable artificial intelligence models could effectively convert the dataset to a basis that improves human capabilities for better understanding, reasoning, and planning the unit. SHAP could provide precise multivariable correlation assessments between the CF dataset by using the Tabas Parvadeh coal plant (Kerman, Iran), and showed the importance of solid percentage and washing water on the metallurgical responses of the coal CF circuit. XGBoost could predict metallurgical responses (R-square > 0.88) based on operating variables that showed quite higher accuracy than typical modeling methods (Random Forest and support vector regression).

KW - Coal flotation

KW - Explainable AI

KW - Separation efficiency

KW - SHAP

KW - XGBoost

U2 - 10.1016/j.ijmst.2021.10.006

DO - 10.1016/j.ijmst.2021.10.006

M3 - Journal article

AN - SCOPUS:85117760402

VL - 31

SP - 1135

EP - 1144

JO - International Journal of Mining Science and Technology

JF - International Journal of Mining Science and Technology

SN - 2095-2686

IS - 6

ER -

Research

Links

Text available via DOI:

Keywords