Semi-autogenous mill power prediction by a hybrid neural genetic algorithm

Abstract

There are few methods of semi-autogenous (SAG) mill power prediction in the full-scale without using long experiments. In this work, the effects of different operating parameters such as feed moisture, mass flowrate, mill load cell mass, SAG mill solid percentage, inlet and outlet water to the SAG mill and work index are studied. A total number of 185 full-scale SAG mill works are utilized to develop the artificial neural network (ANN) and the hybrid of ANN and genetic algorithm (GANN) models with relations of input and output data in the full-scale. The results show that the GANN model is more efficient than the ANN model in predicting SAG mill power. The sensitivity analysis was also performed to determine the most effective input parameters on SAG mill power. The sensitivity analysis of the GANN model shows that the work index, inlet water to the SAG mill, mill load cell weight, SAG mill solid percentage, mass flowrate and feed moisture have a direct relationship with mill power, while outlet water to the SAG mill has an inverse relationship with mill power. The results show that the GANN model could be useful to evaluate a good output to changes in input operation parameters.

Keywords

semi-autogenous mill / mill power / prediction / sensitivity analysis / artificial neural network / genetic algorithm

References

[1] SalazarJ, MagneL, AcunaG, CubillosF. Dynamic modelling and simulation of semi-autogenous mills [J]. Minerals Engineering, 2009, 22(1): 70-77

[2] MorrellS. A method for predicting the specific energy requirement of comminution circuits and assessing their energy utilisation efficiency [J]. Minerals Engineering, 2008, 21(3): 224-233

[3] MorrellS. A new autogenous and semi-autogenous mill model for scale-up, design and optimisation [J]. Minerals Engineering, 2004, 17(3): 437-345

[4] VAN NieropM, MoysM. The effect of overloading and premature centrifuging on the power of an autogenous mill [J]. Journal of the South African Institute of Mining and Metallurgy, 1997, 97(7): 313-317

[5] HerbstJ, PateW. Object components for comminution system softsensor design [J]. Powder Technology, 1999, 105(1): 424-429

[6] Napier-MunnT J, MorrellS, MorrisonR D, KojovicTMineral comminution circuits: Their operation and optimisation [M], 1996, Brisbare, Julius Kruttschnitt Mineral Research Centre, University of Queensland: 413

[7] ValeryW, MorrellS. The development of a dynamic model for autogenous and semi-autogenous grinding [J]. Minerals Engineering, 1995, 8(11): 1285-1297

[8] ApeltT, AspreyS, ThornhillN. Inferential measurement of SAG mill parameters [J]. Minerals Engineering, 2001, 14(6): 575-591

[9] ChelganiS C, ShahbaziB, RezaiB. Estimation of froth flotation recovery and collision probability based on operational parameters using an artificial neural network [J]. International Journal of Minerals, Metallurgy, and Materials, 2010, 17(5): 526-534

[10] AmniehH B, SiamakiA, SoltaniS. Design of blasting pattern in proportion to the peak particle velocity (PPV): Artificial neural networks approach [J]. Safety Science, 2012, 50(9): 1913-1916

[11] KhandelwalM, SinghT. Prediction of blast-induced ground vibration using artificial neural network [J]. International Journal of Rock Mechanics and Mining Sciences, 2009, 46(7): 1214-1222

[12] PattersonD WArtificial neural networks: Theory and applications [M], 1998477

[13] EberhartR CNeural network PC tools: A practical guide [M], 2014440

[14] VoseM DThe simple genetic algorithm: Foundations and theory [M], 1999251

[15] ShopovaE G, Vaklieva-BanchevaN G. BASIC—A genetic algorithm for engineering problems solution [J]. Computers & Chemical Engineering, 2006, 30(8): 1293-1309

[16] YasinY, AhmadF B H, Ghaffari-MoghaddamM, KhajehM. Application of a hybrid artificial neural network–genetic algorithm approach to optimize the lead ions removal from aqueous solutions using intercalated tartrate-Mg–Al layered double hydroxides [J]. Environmental Nanotechnology, Monitoring & Management, 2014, 1: 2-7

[17] GuptaJ N, SextonR S. Comparing backpropagation with a genetic algorithm for neural network training [J]. Omega, 1999, 27(6): 679-684

[18] LiC Q, YangZ X, YanH Y, WangTThe application and research of the ga-bp neural network algorithm in the mbr membrane fouling [J], 2014

[19] Martínez-MoralesJ D, Palacios-HernándezE R, Velázquez-CarrilloG A. Artificial neural network based on genetic algorithm for emissions prediction of a SI gasoline engine [J]. Journal of Mechanical Science and Technology, 2014, 28(6): 2417-2427