X-ray fluorescence(XRF)sensor-based ore sorting enables efficient beneficiation of heterogeneous ores,while intraparticle heterogeneity can cause significant grade detection errors,leading to misclassifications and hi...X-ray fluorescence(XRF)sensor-based ore sorting enables efficient beneficiation of heterogeneous ores,while intraparticle heterogeneity can cause significant grade detection errors,leading to misclassifications and hindering widespread technology adoption.Accurate classification models are crucial to determine if actual grade exceeds the sorting threshold using localized XRF signals.Previous studies mainly used linear regression(LR)algorithms including simple linear regression(SLR),multivariable linear regression(MLR),and multivariable linear regression with interaction(MLRI)but often fell short attaining satisfactory results.This study employed the particle swarm optimization support vector machine(PSO-SVM)algorithm for sorting porphyritic copper ore pebble.Lab-scale results showed PSO-SVM out-performed LR and raw data(RD)models and the significant interaction effects among input features was observed.Despite poor input data quality,PSO-SVM demonstrated exceptional capabilities.Lab-scale sorting achieved 93.0%accuracy,0.24%grade increase,84.94%recovery rate,57.02%discard rate,and a remarkable 39.62 yuan/t net smelter return(NSR)increase compared to no sorting.These improvements were achieved by the PSO-SVM model with optimized input combinations and highest data quality(T=10,T is XRF testing times).The unsuitability of LR methods for XRF sensor-based sorting of investigated sample is illustrated.Input element selection and mineral association analysis elucidate element importance and influence mechanisms.展开更多
In this work the performance of a screening analytical method for Energy Dispersive X-Ray Fluorescence (EDXRF) analysis in terms of accuracy and precision was evaluated through analysis of rock standard reference mate...In this work the performance of a screening analytical method for Energy Dispersive X-Ray Fluorescence (EDXRF) analysis in terms of accuracy and precision was evaluated through analysis of rock standard reference materials. The method allowed the division of elements into four groups taking into account the excitation energies and measurement conditions of the sample. Two standard reference materials were used and 15 sample replicates were prepared and analyzed, then statistics were applied to assess the precision and accuracy of analytical results. The obtained results show that major compounds or elements (SiO<sub>2</sub>, P<sub>2</sub>O<sub>5</sub>, K<sub>2</sub>O, CaO, Fe<sub>2</sub>O<sub>3</sub>, Ti) can be determined in fine powder sample with a deviation lower than 15%, and a relative standard deviation in the range (1 - 10)%. The deviation was found to be lower than 5% for major compounds such as K<sub>2</sub>O, and CaO, which suggest that the EDXRF is accurate in evaluating major elemental concentrations in rock samples. It was also found that the method seems to be more accurate and precise for major elements than for trace element investigation. This screening analytical method can be used for routine analysis with acceptable results, even though the method should be optimized to increase its precision and accuracy.展开更多
基金supported by State Key Laboratory of Mineral Processing (No.BGRIMM-KJSKL-2022-16)China Postdoctoral Science Foundation (No.2021M700387)+1 种基金National Natural Science Foundation of China (No.G2021105015L)Ministry of Science and Technology of the People’s Republic of China (No.2022YFC2904502)。
文摘X-ray fluorescence(XRF)sensor-based ore sorting enables efficient beneficiation of heterogeneous ores,while intraparticle heterogeneity can cause significant grade detection errors,leading to misclassifications and hindering widespread technology adoption.Accurate classification models are crucial to determine if actual grade exceeds the sorting threshold using localized XRF signals.Previous studies mainly used linear regression(LR)algorithms including simple linear regression(SLR),multivariable linear regression(MLR),and multivariable linear regression with interaction(MLRI)but often fell short attaining satisfactory results.This study employed the particle swarm optimization support vector machine(PSO-SVM)algorithm for sorting porphyritic copper ore pebble.Lab-scale results showed PSO-SVM out-performed LR and raw data(RD)models and the significant interaction effects among input features was observed.Despite poor input data quality,PSO-SVM demonstrated exceptional capabilities.Lab-scale sorting achieved 93.0%accuracy,0.24%grade increase,84.94%recovery rate,57.02%discard rate,and a remarkable 39.62 yuan/t net smelter return(NSR)increase compared to no sorting.These improvements were achieved by the PSO-SVM model with optimized input combinations and highest data quality(T=10,T is XRF testing times).The unsuitability of LR methods for XRF sensor-based sorting of investigated sample is illustrated.Input element selection and mineral association analysis elucidate element importance and influence mechanisms.
文摘In this work the performance of a screening analytical method for Energy Dispersive X-Ray Fluorescence (EDXRF) analysis in terms of accuracy and precision was evaluated through analysis of rock standard reference materials. The method allowed the division of elements into four groups taking into account the excitation energies and measurement conditions of the sample. Two standard reference materials were used and 15 sample replicates were prepared and analyzed, then statistics were applied to assess the precision and accuracy of analytical results. The obtained results show that major compounds or elements (SiO<sub>2</sub>, P<sub>2</sub>O<sub>5</sub>, K<sub>2</sub>O, CaO, Fe<sub>2</sub>O<sub>3</sub>, Ti) can be determined in fine powder sample with a deviation lower than 15%, and a relative standard deviation in the range (1 - 10)%. The deviation was found to be lower than 5% for major compounds such as K<sub>2</sub>O, and CaO, which suggest that the EDXRF is accurate in evaluating major elemental concentrations in rock samples. It was also found that the method seems to be more accurate and precise for major elements than for trace element investigation. This screening analytical method can be used for routine analysis with acceptable results, even though the method should be optimized to increase its precision and accuracy.
