The application of machine learning models based on particles characteristics during coal slime flotation

Binglong Zhao, Shunxuan Hu, Xuemin Zhao, Baonan Zhou, Junguo Li, Wei Huang, Guohua Chen, Changning Wu*, Ke Liu*

*Corresponding author for this work

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

14 Citations (Scopus)

Abstract

In this study, four different machine learning (ML) models were used to simulate the migration behavior of minerals during coal slime flotation based on particle characteristics (shape, size, compositions, and types): random forest (RF), logistic regression (LR), AdaBoosting (Ada), and k-nearest neighbors (KNN). For ML model development, 70% of the total data was used for the training phase, and 30% was used for the testing phase. F-score and area under the curve (AUC) were used as the most vital indicators for evaluating the different ML models. Compared to the other ML models, the RF model had the best accuracy for simulating particle migration behavior during flotation. Furthermore, the RF model avoided the drawback of having to be retrained when the feed conditions changed. The results revealed that particle size and particle composition play the most significant role in coal slime flotation.
Original languageEnglish
Article number103363
JournalAdvanced Powder Technology
Volume33
Issue number1
Online published30 Nov 2021
DOIs
Publication statusPublished - Jan 2022
Externally publishedYes

Research Keywords

  • Flotation
  • Machine learning
  • Particle behavior
  • Particle characteristics
  • Random forest (RF)

Fingerprint

Dive into the research topics of 'The application of machine learning models based on particles characteristics during coal slime flotation'. Together they form a unique fingerprint.

Cite this