Coupling of XGBoost ensemble methods and discrete element modelling in predicting autogenous grinding mill throughput

Tao Ou, Jie Liu*, Fei Liu, Wei Chen*, Jiangyi Qin

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Autogenous Grinding (AG) is one the most important mineral processing assets in the comminution circuit, and its production performance directly impacts on the circuit throughput. Understanding the key parameters impacting the AG mill throughput is critical to reducing the operational variability and to improve throughput predictions. This study aims to develop a coupled discrete element modelling and machine learning ensemble method for AG mill throughput predictions. Discrete Element Modelling (DEM) was coupled to an extreme gradient boosting (XGBoost) decision tree method to construct an accurate mill throughput prediction model. Hyperparameter optimizations and model pruning were conducted to improve the generalized model prediction capability. A suite of operational data as well as DEM modelling results from a 32FT AG mill were used to train and validate the developed model. Results indicated that the coupled method showed good agreement with the validation dataset. The impact from each mill operational parameter on the mill throughput was also evaluated and ranked, from which the improvement strategy on mill operation can then be devised.
Original languageEnglish
JournalPowder Technology
Volume422
Issue number118480
Publication statusPublished - 28 Mar 2023

Keywords

  • AG mill
  • Throughput prediction
  • Discrete element modelling
  • Decision tree
  • XGBoost
  • Feature importance

Fingerprint

Dive into the research topics of 'Coupling of XGBoost ensemble methods and discrete element modelling in predicting autogenous grinding mill throughput'. Together they form a unique fingerprint.

Cite this