This study introduces a multilayer perceptron artificial neural network model to predict water split, cut size and sharpness of separation in hydrocyclone classifiers. The model is developed based on experimental data from 75, 100, 150 and 250 mm diameter hydrocyclones under different operating conditions and design parameters. The Levenberg–Marquardt training algorithm is found to be optimal based on the correlation coefficient and mean square error values. Pearson's correlation coefficient is used to assess the strength and direction between variables. The importance of input variables is estimated using the out-of-bag permuted predictor method. The ANN model employs 10, 10 and 8 hidden neurons achieving regression coefficients of R ∼ 0.92, R ∼ .99, R ∼ 0.90 and MSE values of 21.98, 38.915, 0.34 for water split, cut size and sharpness of separation, respectively. Comparative analysis indicates that the ANN model shows superior performance than empirical and semi empirical models.
JiLPaulPShanbhagBK, et al.Emerging application of hydrocyclone in biotechnology and food processing. Sep Purif Technol2023; 309: 122992.
2.
PadhiMVakamallaTRMangadoddyN. Iron ore slimes beneficiation using optimised hydrocyclone operation. Chemosphere2022; 301: 134513.
3.
PotgieterMPauckWJJohakimuJ, et al.Using hydrocyclone fractionation to improve chemical pulp quality. S Afr J Chem Eng2021; 36: 74–79.
4.
SripriyaRKaulaskarMDChakrabortyS, et al.Studies on the performance of a hydrocyclone and modeling for flow characterization in presence and absence of air core. Chem Eng Sci2007; 62: 6391–6402.
5.
WeiALiJShanM, et al.Removal of chlorine, microparticles and water from high-viscosity liquids by a sand filter coupling hydrocyclone. Process Saf Environ Prot2023; 170: 636–646.
6.
VakamallaTRMangadoddyN. The dynamic behaviour of a large-scale 250-mm hydrocyclone: a CFD study. Asia-Pac J Chem Eng2019; 14: e2287.
7.
ChuL-YChenW-MLeeX-Z. Effect of structural modification on hydrocyclone performance. Sep Purif Technol2000; 21: 71–86.
8.
ArterburnRA. The sizing and selection of hydrocyclones. In: Design and installation of comminution circuits. Madison: Society of Mining Engineers of AIME, 1982, pp.597–607.
9.
BohnetMHarmsG. Theoretical and experimental investigation on separation of two immiscible liquids using hydrocyclones. Report Number: CONF-960730-, United States, 31 December 1996. American Institute of Chemical Engineers, New York, NY (United States), https://www.osti.gov/biblio/430454 (1996).
10.
BradleyD. The hydrocyclone: international series of monographs in chemical engineering. Oxford: Elsevier, 1965.
11.
AsomahAKNapier-MunnTJ. An empirical model of hydrocyclones incorporating angle of cyclone inclination. Miner Eng1997; 10: 339–347.
12.
CoelhoMAZMedronhoRA. An evaluation of the Plitt And Lynch & Rao models for the hydrocyclones. In: SvarovskyLThewMT (eds) Hydrocyclones: analysis and applications. Dordrecht: Springer Netherlands, 1992, pp.63–72. DOI: https://doi.org/10.1007/978-94-015-7981-0_5.
13.
NageswararaoK. Further developments in the modelling and scale up of industrial hydrocyclones. PhD Thesis, University of Queensland, 1979.
14.
FirthB. Hydrocyclones in dewatering circuits. Sol-Liq Sep2003; 16: 115–120.
15.
NarasimhaMMainzaANHolthamPN, et al.A semi-mechanistic model of hydrocyclones — developed from industrial data and inputs from CFD. Int J Miner Process2014; 133: 1–12.
16.
JiLChenJKuangS, et al.Prediction of separation performance of hydrocyclones by a PC-based model. Sep Purif Technol2019; 211: 141–150.
17.
WalczakSCerpaN. Artificial neural networks. In: Encyclopedia of physical science and technology, Academic Press, Cambridge, MA, USA. 2003, pp.631–645.
18.
DasPJPreussCMazumderB, et al.Chapter 13 - artificial neural network as helping tool for drug formulation and drug administration strategies. In: PuriMPathakYSutariyaVK (eds) Artificial neural network for drug design, delivery and disposition. Boston: Academic Press, 2016, pp.263–276. https://www.sciencedirect.com/science/article/pii/B9780128015599000132.
19.
LesnikKLLiuH. Predicting microbial fuel cell biofilm communities and bioreactor performance using artificial neural networks. Environ Sci Technol2017; 51: 10881–10892.
20.
VargheseMMAiswariaPVakamallaTR, et al.Measurement of solids holdup in a gas–solid fluidized bed: an experimental, statistical and ANN approach. Braz J Chem Eng2023; 40: 493–510.
21.
ZhangJLiCYinY, et al.Applications of artificial neural networks in microorganism image analysis: a comprehensive review from conventional multilayer perceptron to popular convolutional neural network and potential visual transformer. Artif Intell Rev2023; 56: 1013–1070.
22.
ZhaoBSuY. Artificial neural network-based modeling of pressure drop coefficient for cyclone separators. Chem Eng Res Des2010; 88: 606–613.
23.
YeQDuanPKuangS, et al.Multi-objective optimization of hydrocyclone by combining mechanistic and data-driven models. Powder Technol2022; 407: 117674.
24.
ErenHFungCCGuptaA. Application of artificial neural network in estimation of hydrocyclone parameters. In: AusIMM 1996 annual conference, 1996.
25.
AntonioJGnecchiGPinedaEM. Evaluation of methods for on-line image analysis of electrical impedance tomography images. In: Electronics, robotics and automotive mechanics conference (CERMA 2007), 25 September 2007, pp.283–288.
26.
KarimiMDehghaniANezamalhosseiniA. Prediction of hydrocyclone performance using artificial neural networks. J South Afr Inst Min Metall2010; 110: 207–212.
27.
van LoggenbergSvan SchoorGUrenKR, et al.Hydrocyclone cut-size estimation using artificial neural networks. 11th IFAC Symp Dyn Control Process SystemsInc Biosyst DYCOPS-CAB 20162016; 49: 996–1001.
28.
MohantySDasSKMajumderAK. Artificial neural network modeling and experimental investigation to characterize the dewatering performance of a hydrocyclone. Miner Process Extr Metall2021; 130: 396–408.
29.
ReddyV. Developing a comprehensive CFD model for dense slurry flow in industrial cyclones. PhD Thesis, Indian Institute of Technology Hyderabad, 2016.
30.
MangadoddyN. Improved computational and empirical models of hydrocyclones. PhD Thesis, University of Queensland, 2009.
31.
FanGEl-ShafayASEftekhariSA, et al.A well-trained artificial neural network (ANN) using the TRAINLM algorithm for predicting the rheological behavior of water – ethylene glycol/WO3 – MWCNTs nanofluid. Int Commun Heat Mass Transf2022; 131: 105857.
32.
BealeMHHaganMTDemuthHB. Deep learning toolbox, 2018.
33.
BawaVSKumarV. Linearized sigmoidal activation: a novel activation function with tractable non-linear characteristics to boost representation capability. Expert Syst Appl2019; 120: 346–356.
34.
HeatonJ. Introduction to neural networks for Java. 2nd ed. Chesterfield, MO: Heaton Research, Inc, 2008.
35.
AriaMCuccurulloCGnassoA. A comparison among interpretative proposals for random forests. Mach Learn Appl2021; 6: 100094.
36.
AuretLAldrichC. Interpretation of nonlinear relationships between process variables by use of random forests. Miner Eng2012; 35: 27–42.
37.
LegenhausenK. Particle classification. Von K. Heiskanen Chapman & Hall, London 1993. 321 S. Mit zahlr. Abb. und Tab., geb., £ 40,00. Chem Ing Tech1994; 66: 1094–1094.
38.
VakamallaTRMangadoddyN. Comprehensive dense slurry CFD model for performance evaluation of industrial hydrocyclones. Ind Eng Chem Res2021; 60: 12403–12418.
39.
VieiraLGMBarrozoMAS. Effect of vortex finder diameter on the performance of a novel hydrocyclone separator. Miner Eng2014; 57: 50–56.
40.
SuTZhangY. Effect of the vortex finder and feed parameters on the short-circuit flow and separation performance of a hydrocyclone. Processes2022; 10: 771.
41.
BhaskarKUMurthyYRRajuMR, et al.CFD Simulation and experimental validation studies on hydrocyclone. Miner Eng2007; 20: 60–71.
42.
ElsayedKLacorC. The effect of vortex finder diameter on cyclone separator performance and flow field. In: Proceedings of the 5th European conference on computational fluid dynamics (ECCOMAS CFD 2010), 1 January 2010.
43.
GhodratMKuangSBYuAB, et al.Computational study of the multiphase flow and performance of hydrocyclones: effects of cyclone size and spigot diameter. Ind Eng Chem Res2013; 52: 16019–16031.
44.
MukherjeeAKSripriyaRRaoPVT, et al.Effect of increase in feed inlet pressure on feed rate of dense media cyclone. Int J Miner Process2003; 69: 259–274.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
