Prediction of flotation efficiency of metal sulfides using an original hybrid machine learning model. Issue 6 (8th June 2020)

• Record Type: Journal Article
• Authors: Cook, Rachel; Monyake, Keitumetse Cathrine; Hayat, Muhammad Badar; Kumar, Aditya; Alagha, Lana
• Is Part Of: Engineering reports. Volume 2:Issue 6(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-06-08
• Subjects: complex sulfide ore -- firefly algorithm -- froth flotation -- machine learning -- random forests; Engineering -- Periodicals; Computer science -- Periodicals; 620.005
• DOI: 10.1002/eng2.12167
• Languages: English
• ISSNs: 2577-8196

Abstract

Abstract: Froth flotation process is extensively used for selective separation of base metal sulfides from uneconomic mineral resources. Reliable prediction of process outcomes (metal recovery and grade) is vital to ensure peak performance. This work employs an innovative hybrid machine learning (ML) model—constructed by combining the random forest model and the firefly algorithm—to predict froth flotation efficiency of galena and chalcopyrite in relation to various experimental process parameters. The hybrid model's prediction performance was rigorously evaluated, and compared against four different standalone ML models. The outcomes of this study illustrate that the hybrid ML model has the prediction ability to process outcomes with high‐fidelity, while consistently outperforming the standalone ML models. Abstract : An original hybrid machine learning (ML) model (RF‐FFA) is presented in this article. The model—developed by uniting the random forests (RF) model with the firefly algorithm (FFA)—is used to predict froth flotation efficiency of galena and chalcopyrite (the main economic sources of lead and copper metals) in relation to various experimental process parameters. High‐fidelity predictions produced by the RF‐FFA model suggests that the model could be used as a tool for the optimization of froth flotation processes at plant scale.