Dewatering in mineral processing industries is of paramount importance as most wet beneficiation of minerals needs removal of water. For this purpose, we have evaluated a 50.8 mm diameter hydrocyclone in order to assess whether it can be used as a partial replacement for a thickener. A multi-layer perceptron based artificial neural network (ANN) model was developed to characterise the dewatering performance of a hydrocyclone using experimentally generated data for silica and magnetite. Parametric sensitivity analysis was undertaken by studying the influence of vortex finder diameter, spigot diameter and inlet pressure on dewatering performance. The ANN model predictions showed that solid recovery to underflow increases and water recovery to overflow decreases with increasing spigot diameter whereas solid recovery to underflow decreases and water recovery to overflow increases with increased vortex finder diameter. Both increase monotonically with increase in inlet pressure. The neural model prediction was successfully validated with the experimental data.
AslanN, CifciF, YanD.2008. Optimization of process parameters for producing graphite concentrates using response surface methodology. Sep Purif Technol. 59:9–16. doi: 10.1016/j.seppur.2007.05.022
2.
BicalhoIC, MognonJL, JulianaS, AtaídeCH, DuarteCR.2012. Separation of yeast from alcoholic fermentation in small hydrocyclones. Sep Purif Technol. 87:62–70. doi: 10.1016/j.seppur.2011.11.023
3.
ByrdRH, LuP, NocedalJ, ZhuC.1995. A limited memory algorithm for bound constrained optimization. SIAM J Sci Comput. 16:1190–1208. doi: 10.1137/0916069
4.
CallanR.1998. The essence of neural networks. Upper Saddle River, USA: Prentice Hall.
5.
CilliersJJ, Diaz-AnadonL, WeeFS.2004. Temperature, classification and dewatering in 10 mm hydrocyclones. Minerals Engg. 17:591–597. doi: 10.1016/j.mineng.2003.11.022
6.
CilliersJJ, HarrisonSTL.1997. The application of mini-hydrocyclones in the concentration of yeast suspensions. Chem. Eng. J. 65:21–26. doi: 10.1016/S1385-8947(96)03100-2
7.
DasSK.2013. Neural network modelling of flow stress and mechanical properties for hot strip rolling of TRIP steel using efficient learning algorithm. Ironmaking Steelmaking. 40:298–304. doi: 10.1179/1743281212Y.0000000047
8.
DasSK, MandalD, SahooKL.2015. Neural modeling and experimental investigation of the erosion characteristics of boiler grade steels impacted by fly ash. J. of Materials Engg. and Performance. 24:3513–3526. doi: 10.1007/s11665-015-1609-8
9.
ElsayedK, LacorC.2012. Modeling and pareto optimization of gas cyclone separator performance using RBF type artificial neural networks and genetic algorithms. Powder Technol. 2170:84–99. doi: 10.1016/j.powtec.2011.10.015
10.
ErenH, FungCC, WongKW.1996. Back propagation neural network in determination of parameter d50/sub c/ of hydrocyclones. In IEEE TENCON – Digital Signal Processing Applications WA: 26–29.
11.
FirthB.2003. Hydrocyclones in dewatering circuits. Minerals Engg. 16:115–120. doi: 10.1016/S0892-6875(02)00209-1
12.
FlintoffBC, PlittLR, TurakAA.1987. Cyclone modeling: a review of present technology. CIM Bull. 80:39–50.
13.
GarmsiriMR, HajiASH.2014. The Effect of Grain Size on Flocculant Preparation. Minerals Engg. 65:51–53.
14.
GhoshI, DasK S, ChakrabortyN.2014. An artificial neural network model to characterize porosity defects during solidification of A356 aluminum alloy. Neural Computing and Applications. 25:653–662. doi: 10.1007/s00521-013-1532-6
15.
KarimiM, DehghaniA, NezamalhosseiniA, TalebiS.2010. Prediction of hydrocyclone performance using artificial neural networks. Journal- South African Institute of Mining and Metallurgy. 110:207–212.
16.
KumariA, DasSK, SrivastavaPK.2017. Data-driven modeling of fireside corrosion rate. Anti-corrosion Methods and Materials. 64:397–404. doi: 10.1108/ACMM-11-2016-1732
17.
LoggenbergSV, SchoorGV, UrenKR, MerweAFV.2016. Hydrocyclone cut-size estimation using artificial neural networks. IFAC-Papers On Line. 49:996–1001. doi: 10.1016/j.ifacol.2016.07.332
18.
LynchAJ, RaoTC.1975. Modeling and scale-up of hydrocyclone classifiers. Proc. 11th Int. mineral processing Congress; Cagliari:246–269.
19.
NiL, JinyiT, TaoS, YongsonJ, JianingZ.2018. Optimizing geometric parameters in hydrocyclones for enhanced separations: a review and prospective. Separation and Purification Reviews. 48:1–22.
20.
OoyenV, NienhuisB.1992. Improving the convergence of the back-propagation algorithm. Neural Netw. 5:465–471. doi: 10.1016/0893-6080(92)90008-7
21.
PasquierS, CilliersJJ.2000. Sub-micron particle dewatering using hydrocyclones. Chem. Eng. J. 80:283–288. doi: 10.1016/S1383-5866(00)00103-9
22.
PlittLR.1976. A mathematical model of the hydrocyclone classifier. CIM Bulletin Mineral Processing. 69:114–123.
23.
RizkSA, MageedAA, Abu-AliMH.2010. Dewatering the sludge from waste treatment plants with two hydrocyclones in series. J. Eng. Sci. 38:797–806.
24.
ShahM, DasSK.2018. An artificial neural network model to predict the bainite plate thickness of nanostructured bainitic steels using an efficient network-learning algorithm. J Mater Eng Perform. 27:5845–5855. doi: 10.1007/s11665-018-3696-9
25.
Shiao-HungC., DexinHe, FengY.2003. Liquid-solid separation. In: YangWen-Ching, editor. Handbook of fluidization and fluid-particle systems. Pittsburgh, Pennsylvania, U.S.A: CRC Press.
26.
SinghRK, DasA.2013. Analysis of separation response of Kelsey centrifugal jig in processing fine coal. Fuel Process Technol. 115:71–78. doi: 10.1016/j.fuproc.2013.04.005
