Estimation of concentrate grade in platinum flotation based on froth image analysis

[摘要] ENGLISH ABSTRACT: Flotation is an important processing step in the mineral processing industry wherein valuable mineralsare extracted. Flotation is a difficult process to control due to its complexity, meaning that the reversal ofseries of changes will not necessarily bring the process back to its original state. Expert knowledge isincorporated in flotation control through operator experience and intervention, which is subject to manychallenges, creating the need for improvement in control. The performance of a flotation cell is oftendetermined by evaluating froth appearance. The application of image analysis to capture, evaluate andmonitor froth appearance poses multiple benefits such as consistent and reliable froth appearanceevaluation.The objective for this study was to conduct a laboratory study for the collection of froth images with thepurpose of evaluating the feasibility of using image information to predict platinum froth grade.Laboratory test work was performed according to a fractional factorial experimental design. Six variableswere considered: air flowrate, pulp level and collector, activator, frother and depressant dosages. Thelaboratory study results were quantified by assay analysis. Analysis of variance only revealed thesignificant effect of pulp height and collector addition on flotation performance. Data pre-processingrevealed information regarding feature correlations and variance contributions. Data analysis fromcaptured images achieved reliable froth grade predictions using random forest classification and artificialneural network (ANN) regression techniques. Random forest classification accuracies of 86.8% and 75.5%were achieved for the following respective datasets: image data of each individual experiment (average ofall experiments) and all image data. The applied ANN models achieved R2 values 0.943 and 0.828 for thesame 2 datasets. An industrial case study was done wherein a series of step changes in air flowrate wasmade on a specific flotation cell. The limited industrial case study results supported laboratory studyresults. Multiple linear regression performed very well, reaching Rª values up to 0.964. Neural networksachieved slightly better with R2 values of up to 0.997.Based on the findings, the following main conclusions were drawn from this study:- Reliable predictions using classification and regression models on image data were provedpossible in concept by the laboratory study, and supported by results from an industrial casestudy on a narrow system.The following main recommendations were made for further investigation:- Research over a larger range of operating conditions is needed to find a more comprehensivesolution.- Investigations should be conducted to determine hardware requirements and specifications interms of minimum resolution, lighting requirements, sampling frequency and data storage.Software requirements, specifications and maintenance challenges should also be investigated forimplementation purposes once a more comprehensive solution has been found.- Strategies in terms of camera placement and model building will need to follow, giving specialattention to a strategy to handle ore composition change.

[发布机构] Stellenbosch University