A novel explainable modeling method for cleaned coal quality evaluation in jigged fluidized bed

ABSTRACT

Rapid monitoring of cleaned coal quality with soft sensors is essential for efficient production and control of the jigged fluidized bed. In this study, a new explainable modeling method for refined coal quality prediction in coal-jigged fluidization is proposed. The models were developed based on the 47 process variables of air pressure, buoy height, belt weight, water flow, gate opening, bucket level, hydraulic, and feed frequency. By comparing the performance of the two ensemble learning models, the results show that XGBoost predicts lower MAE (1.16%) and RMSE (1.72%) for cleaned coal quality. In addition, the SHapley Additive explanation (SHAP) is employed to interpret the contributions and analyze the importance of each process variable. The SHAP results indicate that nine important variables (Maximum buoy height of the 3- and 4-bed area, amplitude of gate opening of the 3- and 4-bed area, Gangue belt weight, Gangue bucket level, hydraulic of the 3- and 4-bed area and Feed frequency) contributed the most to ash content prediction of cleaned coal, which Gini coefficient higher than 0.2. Then, the XGBoost predictor is optimized again based on the 9 variables selected based on SHAP contributions. The results show that the MAE and RMSE of the XGBoost model are reduced by 0.24% and 0.40%, respectively. In contrast, the method in this paper effectively addresses the prediction of cleaned coal quality in the jigged fluidized bed, where the contribution of variables obtained by SHAP can be used as a theoretical basis for developing optimal control for jigged fluidized bed.

KEYWORDS:

• Process control
• Coal jigged fluidized bed
• Shapley additive explanations
• Machine learning
• Ash content

Supplementary material

Supplemental data for this article can be accessed online at https://doi.org/10.1080/15567036.2023.2208543.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by China Natural Science Foundation (No. 51974309)

Notes on contributors

Zhiping Wen

Mr. Zhiping Wen is a Ph.D candidate of Department of Resource and Environmental Engineering at China University of Mining and Technology in China. He has long been engaged in academics and research in flotation process modeling and system control. He has participate in all the work of full research. Focusing on conceptualization, methodology, machine learning method, writing-original draft, data processing.

Yali Kuang

Dr. Yali Kuang is working as a professor of Department of Process Control and Equipment at China University of Mining and Technology in China. She has done Ph.D degree in minerals processing and technology engineering from CUMT. She has more than a decade of experience in academics and research in the field of coal process modeling and control. He has participate in writing-reviewing and editing, supervision, funding acquisition of the paper.

Hongyue Zi

Hongyue Zi is a master of Department of Process Control and Equipment at China University of Mining and Technology in China. He has participate in all the work of full research. Focusing on methodology, models training, writing-Reviewing and editing, validation.

Changchun Zhou

Changchun Zhou is working as a Professor of Department of Resource and Environmental Engineering at China University of Mining and Technology in China. He has done Ph.D degree in minerals processing and technology engineering from CUMT. He was one of the main supervisors of this paper.

Guanghui Wang

Guanghui Wang is working as an Associate Professor of Department of Process Control and Equipment at China University of Mining and Technology in China. He has participate in writing-reviewing and editing, supervision, funding acquisition of the paper.