o:5973 Relative prediction error of flotation indices by anfis models en Abstract: This paper describes performances of three different ANFIS models trough the important statistical parameters – relative prediction error, its standard deviation and its mean. Copper content in the ore feed, collector dosage and frother dosage were selected as input parameters to estimate the copper grade and recovery in the final concentrate, and the copper content in the final tailings of the flotation plant. For each output parameter one ANFIS model is developed. Evaluation of the proposed models were performed on the basis of real process data collected by the multiannual monitoring of industrial flotation plant operation in “Veliki Krivelj Mine”. The results showed that the proposed ANFIS methodology is the most suitable for prediction of copper recovery in the final concentrate, given that the smallest relative prediction errors with their smallest standard deviation (SDE = 0.11) were obtained in this case. Keywords: flotation modeling, relative prediction error, ANFIS. 91552100 138181897 1552100 978-86-6305-133-1 2024-11-02T21:58:03.186Z 44 no 46 Ivana Jovanović Institut za rudarstvo i metalurgiju Bor 79412745 0000-0002-7450-6632 2023 46 Vesna Conić Institut za rudarstvo i metalurgiju Bor 55525641 0000-0002-4268-3626 2023 46 Dragan Milanović Institut za rudarstvo i metalurgiju Bor 6197863 2023 46 Fardis Nakhaei School of Chemical and Minerals Engineering, North West University, South Africa 110635017 0000-0001-8840-9772 2023 46 Slađana Krstić Institut za rudarstvo i metalurgiju Bor 84771337 0000-0002-4342-3842 2023 application/pdf 1562004 https://unilib.phaidrabg.rs/o:5973 no yes 1 70 622.7 92000004 71A03 Proceedings International Mineral Processing and Recycling Conference (15 ; 2023 ; Belgrade) 387 390 2023