Feature selection and Gaussian process prediction of rougher copper recovery

Abstract The emergence of advanced computational techniques provides opportunity in better modelling complex, nonlinear relationship of industrial processes. In this work, the performance of Gaussian Process Regression (GPR) models in predicting rougher copper recovery, following development with and without model-selected, relevant rougher flotation variables has been investigated. Randomly selected training and validation data sets as well as an independent testing data set (later than the original training and validation sets) were used to demonstrate the model predictive behaviour. The results showed that exponential GPR covariance function, modelled with selected relevant rougher flotation variables (throughput, feed particle size, xanthate dosage, frother dosage and froth depth), was the best model yielding correlation coefficient ( r ), root mean square error (RMSE), normalised root mean square error (NRMSE), variance accounted for (VAF) and performance index (PI) values of 0.99, 0.10, 0.01%, 99.99% and 1.97, respectively for training set. In the same manner, the validation set yielded 0.95, 0.40, 0.06%, 91.0%, and 1.75 whilst the testing set gave 0.96, 0.39, 0.07%, 92.10% and 1.78, confirming that exponential GPR algorithm can make good rougher copper recovery prediction given a set of useful rougher flotation variables. In all cases, the Regularised Neighbourhood Component Analysis algorithm performed best better in selecting useful flotation variables for rougher copper recovery prediction. Sobol’s global sensitivity analysis indicated feed particle size as the most sensitive input variable recording first and total sobol indices values of ~63% and ~67%, respectively. Partial dependence plots revealed the functional relationship between the top two sensitive input variables (feed particle size and froth depth of tank cell 1) and predicted rougher copper recovery, suggesting their critical operating regime.

[1]  Theodore B. Trafalis,et al.  Support vector machine for regression and applications to financial forecasting , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[2]  M. Massinaei,et al.  Modeling of bubble surface area flux in an industrial rougher column using artificial neural network and statistical techniques , 2010 .

[3]  Luis E. Arias,et al.  Sensors and Process Control in Copper Smelters: A Review of Current Systems and Some Opportunities , 2020, Minerals.

[4]  Jie Yu,et al.  Online quality prediction of nonlinear and non-Gaussian chemical processes with shifting dynamics using finite mixture model based Gaussian process regression approach , 2012 .

[5]  Heiga Zen,et al.  On the Use of Kernel PCA for Feature Extraction in Speech Recognition , 2003, IEICE Trans. Inf. Syst..

[6]  Xiangguang Chen,et al.  Soft sensor development for online quality prediction of industrial batch rubber mixing process using ensemble just-in-time Gaussian process regression models , 2016 .

[7]  Juan Yianatos,et al.  The long way toward multivariate predictive control of flotation processes , 2011 .

[8]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[9]  E. Amini.  Influence of flotation cell hydrodynamics on the flotation kinetics and scale up of flotation recovery , 2012 .

[10]  Hiroshi Motoda,et al.  Feature Selection for Knowledge Discovery and Data Mining , 1998, The Springer International Series in Engineering and Computer Science.

[11]  E. Manlapig,et al.  The effect of breakage mechanism on the mineral liberation properties of sulphide ores , 2010 .

[12]  W. Skinner,et al.  Enhancing gold recovery from refractory bio-oxidised gold concentrates through high intensity milling , 2020, Mineral Processing and Extractive Metallurgy.

[13]  Amirhossein Mokhtari,et al.  Evaluation and recommendation of sensitivity analysis methods for application to Stochastic Human Exposure and Dose Simulation models , 2006, Journal of Exposure Science and Environmental Epidemiology.

[14]  Furong Gao,et al.  Review of Recent Research on Data-Based Process Monitoring , 2013 .

[15]  Krist V. Gernaey,et al.  Meta-modeling based efficient global sensitivity analysis for wastewater treatment plants - An application to the BSM2 model , 2019, Comput. Chem. Eng..

[16]  W. Skinner,et al.  Refractory gold ores and concentrates part 2: gold mineralisation and deportment in flotation concentrates and bio-oxidised products , 2019, Mineral Processing and Extractive Metallurgy.

[17]  Samsul Bahari Mohd Noor,et al.  Froth-based modeling and control of a batch flotation process , 2016 .

[18]  Ludmila I. Kuncheva,et al.  PCA Feature Extraction for Change Detection in Multidimensional Unlabeled Data , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Lars Imsland,et al.  Stochastic Nonlinear Model Predictive Control Using Gaussian Processes , 2018, 2018 European Control Conference (ECC).

[20]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

[21]  I. Sherrell.  Development of a Flotation Rate Equation from First Principles under Turbulent Flow Conditions , 2004 .

[22]  W. Skinner,et al.  Application of ToF-SIMS to predict contact angles of pyrite particles , 2020 .

[23]  Mehmet Polat,et al.  First-order flotation kinetics models and methods for estimation of the true distribution of flotation rate constants , 2000 .

[24]  Shiru Sharma,et al.  Feature selection using regularized neighbourhood component analysis to enhance the classification performance of motor imagery signals , 2019, Comput. Biol. Medicine.

[25]  W. Skinner,et al.  Pulp mineralogy and chemistry, leaching and rheological behaviour relationships of refractory gold ore dispersions , 2019, Chemical Engineering Research and Design.

[26]  H. Do.  Development of a turbulent flotation model from first principles , 2010 .

[27]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[28]  Lidia Auret,et al.  Machine learning applications in minerals processing: A review , 2019, Minerals Engineering.

[29]  Mohsen Karimi,et al.  A computational fluid dynamics model for the flotation rate constant, Part I: Model development , 2014 .

[30]  Verónica Bolón-Canedo,et al.  A review of microarray datasets and applied feature selection methods , 2014, Inf. Sci..

[31]  Li-Yeh Chuang,et al.  Improved binary PSO for feature selection using gene expression data , 2008, Comput. Biol. Chem..

[32]  Bogdan Gabrys,et al.  Data-driven Soft Sensors in the process industry , 2009, Comput. Chem. Eng..

[33]  Jan J. Cilliers,et al.  A review of froth flotation control , 2011 .

[34]  D. Hinkle,et al.  Applied statistics for the behavioral sciences , 1979 .

[35]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[36]  I. Sobola,et al.  Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates , 2001 .

[37]  Victor Amoako Temeng,et al.  A novel artificial intelligent model for predicting air overpressure using brain inspired emotional neural network , 2020 .

[38]  C. Rasmussen,et al.  Gaussian Process Priors with Uncertain Inputs - Application to Multiple-Step Ahead Time Series Forecasting , 2002, NIPS.

[39]  R. Asamoah.  Specific Refractory Gold Flotation and Bio-Oxidation Products: Research Overview , 2021, Minerals.

[40]  S. S. Matin,et al.  Prediction of froth flotation responses based on various conditioning parameters by Random Forest method , 2017 .

[41]  Tao Chen,et al.  Bagging for Gaussian process regression , 2009, Neurocomputing.

[42]  Badih Ghattas,et al.  A review of supervised machine learning algorithms and their applications to ecological data , 2012 .

[43]  Zhiyong Gao,et al.  Effect of grinding media on the surface property and flotation behavior of scheelite particles , 2017 .

[44]  Lei Pan,et al.  Development of a turbulent flotation model from first principles and its validation , 2016 .

[45]  Gavin M. Mudd,et al.  Modelling future copper ore grade decline based on a detailed assessment of copper resources and mining , 2014 .

[46]  Juha Reunanen,et al.  Overfitting in Making Comparisons Between Variable Selection Methods , 2003, J. Mach. Learn. Res..

[47]  M.-V. Durance,et al.  Flotation modelling: A wide range of solutions for solving industrial problems , 1995 .

[48]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[49]  W. Skinner,et al.  Refractory gold ores and concentrates part 1: mineralogical and physico-chemical characteristics , 2019, Mineral Processing and Extractive Metallurgy.

[50]  Stefano Panzeri,et al.  A unifying model of concurrent spatial and temporal modularity in muscle activity. , 2014, Journal of neurophysiology.

[51]  MN Trame,et al.  Sobol Sensitivity Analysis: A Tool to Guide the Development and Evaluation of Systems Pharmacology Models , 2015, CPT: pharmacometrics & systems pharmacology.

[52]  J Q Shi,et al.  Gaussian Process Functional Regression Modeling for Batch Data , 2007, Biometrics.

[53]  Mohammad Hamiruce Marhaban,et al.  Prediction of the metallurgical performances of a batch flotation system by image analysis and neural networks , 2014 .

[54]  Yanhui Yang,et al.  Response surface methodology using Gaussian processes: Towards optimizing the trans-stilbene epoxidation over Co2+-NaX catalysts , 2010 .

[55]  Zhiqiang Ge,et al.  Quality prediction for polypropylene production process based on CLGPR model , 2011 .

[56]  Wei Yang,et al.  Neighborhood Component Feature Selection for High-Dimensional Data , 2012, J. Comput..

[57]  Huan Liu,et al.  Advancing feature selection research , 2010 .

[58]  Christa Boer,et al.  Correlation Coefficients: Appropriate Use and Interpretation , 2018, Anesthesia and analgesia.