Data-driven modelling of the flocculation process on mineral processing tailings treatment

Abstract The clarification of tailings slurry using polymer flocculants has been widely used in the mining industry to promote the cleaner production of mineral resources. In this paper, a data-driven prediction model was proposed using gradient boosting machine (GBM) for the non-linear relationship modelling and firefly algorithm (FA) for GBM hyper-parameters tuning. Two studies were performed, among which the main study omitted the influence of chemical characteristics of mineral processing tailings (MPT) while the supplementary study considered. For the main study, 27 types of MPT and 4 types of anionic flocculants were used to prepare the dataset. The flocculation performance was represented by the initial settling rate (ISR) and its influencing variables were selected to be the particle size distribution (PSD) of MPT, the solids content of tailings slurry, the flocculants type, and the flocculants dosage. For the supplementary study, the chemical characteristics of 7 types of MPT were also considered as influencing variables and its influence on the predictive performance of GBM was investigated. The main study shows that the optimum GBM model achieved a correlation coefficient of 0.841 between the predicted and experimental ISR values on the testing set, denoting it was robust in predicting the ISR of the flocculation. Compared with the solids content, the flocculants dosage and the flocculants type, the PSD of MPT was found to be the most significant influencing variable for the flocculation with an importance score of 0.420 out of 1. The supplementary study shows that the predictive performance of GBM could be improved considering chemical compositions of MPT, which were also important influencing variables for the flocculation process.

[1]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[2]  Hongjiang Wang,et al.  Control of waste rock-tailings paste backfill for active mining subsidence areas , 2018 .

[3]  Qingxia Liu,et al.  Effect of solution salinity on settling of mineral tailings by polymer flocculants , 2013 .

[4]  Xiaolin Tang,et al.  Slope stability prediction using integrated metaheuristic and machine learning approaches: A comparative study , 2018, Comput. Ind. Eng..

[5]  Emmanuel Manlapig,et al.  Designing mine tailings for better environmental, social and economic outcomes: a review of alternative approaches , 2014 .

[6]  Xiao-yan Li,et al.  Numerical simulation and experimental verification of particle coagulation dynamics for a pulsed input. , 2003, Journal of colloid and interface science.

[7]  Bayram Ercikdi,et al.  Predicting the uniaxial compressive strength of cemented paste backfill from ultrasonic pulse velocity test , 2016 .

[8]  Andy Fourie,et al.  Prediction of open stope hangingwall stability using random forests , 2018, Natural Hazards.

[9]  Chemical and physical variables in polymer-induced flocculation , 1993 .

[10]  R. Hogg,et al.  Flocculation and dewatering , 2000 .

[11]  Andy Fourie,et al.  Neural network and particle swarm optimization for predicting the unconfined compressive strength of cemented paste backfill , 2018 .

[12]  J. Soares,et al.  Using acrylamide/propylene oxide copolymers to dewater and densify mature fine tailings , 2016 .

[13]  B. Bussière.  Colloquium 2004: Hydrogeotechnical properties of hard rock tailings from metal mines and emerging geoenvironmental disposal approaches , 2007 .

[14]  Guowei Ma,et al.  Comparative Study of Hybrid Artificial Intelligence Approaches for Predicting Hangingwall Stability , 2018, J. Comput. Civ. Eng..

[15]  A. James,et al.  Effect of polyacrylamide polymers on floc size and rheological behaviour of kaolinite suspensions , 2007 .

[16]  Particle-size dependence on metal(loid) distributions in mine wastes: Implications for water contamination and human exposure , 2011 .

[17]  H. Lambers,et al.  Young calcareous soil chronosequences as a model for ecological restoration on alkaline mine tailings. , 2017, The Science of the total environment.

[18]  T. Jin,et al.  Quantitative modelling of electricity consumption using computational intelligence aided design , 2014 .

[19]  P. D. Fawell,et al.  The impact of achieving a higher aggregate density on polymer-bridging flocculation , 2013 .

[20]  Mohammad Reza Feylizadeh,et al.  Investigation of 2-nitrophenol solar degradation in the simultaneous presence of K2S2O8 and H2O2: Using experimental design and artificial neural network , 2018 .

[21]  P. Simms,et al.  Determination of the optimum polymer dose for dewatering of oil sands tailings using UV–vis spectrophotometry , 2016 .

[22]  A. Tropsha,et al.  Beware of q2! , 2002, Journal of molecular graphics & modelling.

[23]  J. Soares,et al.  Investigation on the flocculation of oil sands mature fine tailings with alkoxysilanes , 2017 .

[24]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[25]  Andy Fourie,et al.  Experimental investigation on the strength characteristics of cement paste backfill in a similar stope model and its mechanism , 2017 .

[26]  Won-Hwa Hong,et al.  New approach for forecasting demolition waste generation using chi-squared automatic interaction detection (CHAID) method , 2017 .

[27]  Zhang Xing-kai,et al.  The safety analysis of current situation and management countermeasure on tailing reservoir in China , 2009 .

[28]  Rolf T. Wigand,et al.  Community Detection in Complex Networks: Multi-objective Enhanced Firefly Algorithm , 2013, Knowl. Based Syst..

[29]  Andy Fourie,et al.  Pressure drop in pipe flow of cemented paste backfill: Experimental and modeling study , 2018, Powder Technology.

[30]  B. Roe,et al.  Boosted decision trees as an alternative to artificial neural networks for particle identification , 2004, physics/0408124.

[31]  M. Bagheri,et al.  Application of artificial intelligence for the management of landfill leachate penetration into groundwater, and assessment of its environmental impacts , 2017 .

[32]  Johan Six,et al.  Clay illuviation provides a long-term sink for C sequestration in subsoils , 2017, Scientific Reports.

[33]  Erol Yilmaz,et al.  Effect of curing under pressure on compressive strength development of cemented paste backfill , 2009 .

[34]  Ayhan Kesimal,et al.  Effect of properties of tailings and binder on the short-and long-term strength and stability of cemented paste backfill , 2005 .

[35]  J. Hunt.  Self-similar particle-size distributions during coagulation: theory and experimental verification , 1982, Journal of Fluid Mechanics.

[36]  O. Ozdemir,et al.  Dewatering of coal plant tailings: Flocculation followed by filtration , 2011 .

[37]  Andy Fourie,et al.  Recycling phosphogypsum and construction demolition waste for cemented paste backfill and its environmental impact , 2018, Journal of Cleaner Production.

[38]  Bo Zhang,et al.  Experimental investigation on the relationship between pore characteristics and unconfined compressive strength of cemented paste backfill , 2018, Construction and Building Materials.

[39]  G. Franks,et al.  Temperature responsive flocculation and solid-liquid separations with charged random copolymers of poly(N-isopropyl acrylamide). , 2011, Journal of colloid and interface science.

[40]  R. Maier,et al.  Treatment impacts on temporal microbial community dynamics during phytostabilization of acid-generating mine tailings in semiarid regions. , 2018, The Science of the total environment.

[41]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[42]  Keunje Yoo,et al.  Decision tree-based data mining and rule induction for identifying hydrogeological parameters that influence groundwater pollution sensitivity , 2016 .

[43]  Ir. R. Rutgers.  Relative viscosity and concentration , 1962 .

[44]  S. B. Kanungo.  Effect of some commercial flocculating agents on settling and filtration rates of low grade, fragile manganese ores of Andhra Pradesh , 2005 .

[45]  Xin-She Yang,et al.  Firefly Algorithm: Recent Advances and Applications , 2013, ArXiv.

[46]  Benjamin Hofner,et al.  Generalized additive models for location, scale and shape for high dimensional data—a flexible approach based on boosting , 2012 .

[47]  B. Jefferson,et al.  The impact of zeta potential on the physical properties of ferric--NOM flocs. , 2006, Environmental science & technology.

[48]  Indresan Govender,et al.  The effect of particle sizes and solids concentration on the rheology of silica sand based suspensions , 2008 .

[49]  Qian Du,et al.  Firefly-Algorithm-Inspired Framework With Band Selection and Extreme Learning Machine for Hyperspectral Image Classification , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[50]  Senjian An,et al.  Fast cross-validation algorithms for least squares support vector machine and kernel ridge regression , 2007, Pattern Recognit..

[51]  Xin-She Yang,et al.  Nature-Inspired Metaheuristic Algorithms , 2008 .

[52]  Chongchong Qi,et al.  A new procedure for recycling waste tailings as cemented paste backfill to underground stopes and open pits , 2018, Journal of Cleaner Production.

[53]  A. Townsend Peterson,et al.  Novel methods improve prediction of species' distributions from occurrence data , 2006 .

[54]  Y. Leong,et al.  Structural recovery behaviour of kaolin, bentonite and K-montmorillonite slurries , 2012 .

[55]  E. V. Hees,et al.  Environmentally Hazardous Boron in Gold Mine Tailings, Timmins, Ontario, Canada , 2015, Mine Water and the Environment.

[56]  A. Fourie,et al.  A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill , 2018 .

[57]  R. Smart,et al.  Kinetics of adsorption of high molecular weight anionic polyacrylamide onto kaolinite: the flocculation process. , 2002, Journal of colloid and interface science.

[58]  Yang Liu,et al.  A two-step flocculation process on oil sands tailings treatment using oppositely charged polymer flocculants. , 2016, The Science of the total environment.

[59]  Andy Fourie,et al.  An intelligent modelling framework for mechanical properties of cemented paste backfill , 2018, Minerals Engineering.

[60]  Wolfgang Durner,et al.  The integral suspension pressure method (ISP) for precise particle‐size analysis by gravitational sedimentation , 2017 .

[61]  Alfonso R. Gennaro,et al.  Remington:the science and practice of pharmacy , 1995 .

[62]  Dalibor Petković,et al.  A comparative study for estimation of wave height using traditional and hybrid soft-computing methods , 2016, Environmental Earth Sciences.