Prediction of results of floatation process using artificial neural networks

Trumić, Maja; Balanović, Katarina; Gavrilović, Tamara

doi:10.5937/IMPRC25659T

Conference Object Open access M33

Trumic et al. - IMPRC 2025.pdf (10.21MB)

2025

Trumić, Maja
Balanović, Katarina
Gavrilović, Tamara

University of Belgrade, Technical Faculty in Bor

Proceedings - XVI International Mineral Processing and Recycling Conference, IMPRC, 28 – 30 May 2025, Belgrade, Serbia

659

664

English

M33 - Conference paper at an international conference, printed in full

In this paper, the use of artificial neural networks in the flotation process is presented and analyzed. Apart from utilization of flotation in the mineral processing, deinking flotation is used for separation of ink particles from the cellulose fibers. The time of deinking flotation, pH value, reagents such as oleic acid, oleic acid with CaCl2, oleic acid with AlCl2 as well as concentration of reagents were used as input for the network. The recovery of toner particles in froth was used as output data for the network. The neural network demonstrated high correlation coefficients during training (0.97), validation (0.96), and testing (0.94), and subsequent accuracy testing confirmed these results.

Artificial neural networks, Machine learning, Flotation, Deinking

DOI

10.5937/IMPRC25659T

ISBN

978-86-6305-158-4

URI

https://repozitorijum.tfbor.bg.ac.rs/handle/...

Scopus

OpenCitations

dc.rights.license	CC-BY-NC-ND
dc.identifier.doi	10.5937/IMPRC25659T
dc.identifier.uri	https://repozitorijum.tfbor.bg.ac.rs/handle/123456789/6054
dc.description.abstract	In this paper, the use of artificial neural networks in the flotation process is presented and analyzed. Apart from utilization of flotation in the mineral processing, deinking flotation is used for separation of ink particles from the cellulose fibers. The time of deinking flotation, pH value, reagents such as oleic acid, oleic acid with CaCl2, oleic acid with AlCl2 as well as concentration of reagents were used as input for the network. The recovery of toner particles in froth was used as output data for the network. The neural network demonstrated high correlation coefficients during training (0.97), validation (0.96), and testing (0.94), and subsequent accuracy testing confirmed these results.
dc.language.iso	en
dc.publisher	University of Belgrade, Technical Faculty in Bor
dc.source	Proceedings - XVI International Mineral Processing and Recycling Conference, IMPRC, 28 – 30 May 2025, Belgrade, Serbia
dc.subject	Artificial neural networks
dc.subject	Machine learning
dc.subject	Flotation
dc.subject	Deinking
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.title	Prediction of results of floatation process using artificial neural networks
dc.type	conferenceObject
dc.type.version	publishedVersion
dc.citation.spage	659
dc.citation.epage	664
dc.citation.rank	M33
dc.creator	Trumić, Maja
dc.creator	Balanović, Katarina
dc.creator	Gavrilović, Tamara
dc.date.accessioned	2025-12-12T12:29:07Z
dc.date.available	2025-12-12T12:29:07Z
dc.date.issued	2025
dc.identifier.isbn	978-86-6305-158-4


Prediction of results of floatation process using artificial neural networks	2


Trumic et al. - IMPRC 2025.pdf	0