In the coal mining industry,the gangue separation phase imposes a key challenge due to the high visual similaritybetween coal and gangue.Recently,separation methods have become more intelligent and efficient,using new...In the coal mining industry,the gangue separation phase imposes a key challenge due to the high visual similaritybetween coal and gangue.Recently,separation methods have become more intelligent and efficient,using newtechnologies and applying different features for recognition.One such method exploits the difference in substancedensity,leading to excellent coal/gangue recognition.Therefore,this study uses density differences to distinguishcoal from gangue by performing volume prediction on the samples.Our training samples maintain a record of3-side images as input,volume,and weight as the ground truth for the classification.The prediction process relieson a Convolutional neural network(CGVP-CNN)model that receives an input of a 3-side image and then extractsthe needed features to estimate an approximation for the volume.The classification was comparatively performedvia ten different classifiers,namely,K-Nearest Neighbors(KNN),Linear Support Vector Machines(Linear SVM),Radial Basis Function(RBF)SVM,Gaussian Process,Decision Tree,Random Forest,Multi-Layer Perceptron(MLP),Adaptive Boosting(AdaBosst),Naive Bayes,and Quadratic Discriminant Analysis(QDA).After severalexperiments on testing and training data,results yield a classification accuracy of 100%,92%,95%,96%,100%,100%,100%,96%,81%,and 92%,respectively.The test reveals the best timing with KNN,which maintained anaccuracy level of 100%.Assessing themodel generalization capability to newdata is essential to ensure the efficiencyof the model,so by applying a cross-validation experiment,the model generalization was measured.The useddataset was isolated based on the volume values to ensure the model generalization not only on new images of thesame volume but with a volume outside the trained range.Then,the predicted volume values were passed to theclassifiers group,where classification reported accuracy was found to be(100%,100%,100%,98%,88%,87%,100%,87%,97%,100%),respectively.Although obtaining a classification with high accuracy is the main motive,this workhas a remarkable reduction in the data preprocessing time compared to related works.The CGVP-CNN modelmanaged to reduce the data preprocessing time of previous works to 0.017 s while maintaining high classificationaccuracy using the estimated volume value.展开更多
Based on the separation and backfilling system of coal and gangue, the mineral material impact experiments were conducted utilizing the hardness difference between coal and gangue according to the uniaxial compression...Based on the separation and backfilling system of coal and gangue, the mineral material impact experiments were conducted utilizing the hardness difference between coal and gangue according to the uniaxial compression experiments. The broken coal and gangue particles were collected and screened by different size meshes. The particle size distributions of coal and gangue under different impact velocities were researched according to the Rosin-Rammler distribution. The relationships between separation indicators and impact velocities were discussed. It is found from experiments that there is a fully broken boundary of coal material. The experimental results indicate that the Rosin-Rammler distribution could accurately describe the particle size distribution of broken coal and gangue under different impact velocities, and there is a minimum overlap region when the impact velocity is 12.10 m/s which leads to the minimum mixed degree of coal and gangue, and consequently the benefit of coal and gangue separation.展开更多
Rutile separation from calcite, apatite and quartz by flotation was investigated. The results show that the rutile separation from calcium and silicon gangue minerals can be realized with alkyl-imino-bismethylene phos...Rutile separation from calcite, apatite and quartz by flotation was investigated. The results show that the rutile separation from calcium and silicon gangue minerals can be realized with alkyl-imino-bismethylene phosphoric acid (TF112) as a collector and sodium hexametaphosphate (SH) as a regulator.展开更多
Gangue from underground separation of coal can directly be used for filling mined out areas, saving transport capacity and reducing the amount of waste polluting the environment above the ground. We introduced a struc...Gangue from underground separation of coal can directly be used for filling mined out areas, saving transport capacity and reducing the amount of waste polluting the environment above the ground. We introduced a structure and operating principle of an underground direct-impact sieving device by which a separation experiment was carried out. By means of high speed conveyer belts, coal and gangue impacted the breaking board at high speeds ranging from 6 to 14 m/s. Given the differences of hardness between coal and gangue, after selective crushing, the gangue with the higher hardness was crushed less and coal with lower hardness crushed more, which could be separated by a 50 mm sieving plate. The material above the sieving plate was disposed of as gangue and the material below as coal. The results indicate that the crush ratio below the 50 mm sieving plate increases linearly with an increase in impact velocity and decays exponentially with an increase in hardness. Employing this equipment to separate coal and gangue, the hardness of coal f should be <2. This separation device provides relatively good effect in separating coal and gangue with a relatively wide difference of hardness.展开更多
Selective separation of silica from a siliceous-calcareous phosphate ore that had been sieved into different size fractions is investigated by a combination of chemical analysis,zeta potential measurement and FTIR and...Selective separation of silica from a siliceous-calcareous phosphate ore that had been sieved into different size fractions is investigated by a combination of chemical analysis,zeta potential measurement and FTIR and XPS techniques.Scrubbing is a better choice than flotation for removing silica from the coarse fractions.The P_2O_5 grade of the coarse fractions is increased to about 30%by scrubbing and the product yields are higher than those obtained by flotation.The silica in the fine fraction is separated by reverse flotation.An alkyl amine salt(DAH)is an effective collector and the P_2O_5 grade of the fine fraction can be increased by 7%to beyond 30%under acidic conditions.The higher zeta potential obtained using DAH suggests that it is more strongly absorbed onto the ore particles than the other cationic collectors. FTIR and XPS results confirm physical absorption of the cationic collector onto the ore surface.They also indicate that calcite is dissolved at low pH values,which increases the Si concentration on the ore surface.展开更多
基金the National Natural Science Foundation of China under Grant No.52274159 received by E.Hu,https://www.nsfc.gov.cn/Grant No.52374165 received by E.Hu,https://www.nsfc.gov.cn/the China National Coal Group Key Technology Project Grant No.(20221CY001)received by Z.Guan,and E.Hu,https://www.chinacoal.com/.
文摘In the coal mining industry,the gangue separation phase imposes a key challenge due to the high visual similaritybetween coal and gangue.Recently,separation methods have become more intelligent and efficient,using newtechnologies and applying different features for recognition.One such method exploits the difference in substancedensity,leading to excellent coal/gangue recognition.Therefore,this study uses density differences to distinguishcoal from gangue by performing volume prediction on the samples.Our training samples maintain a record of3-side images as input,volume,and weight as the ground truth for the classification.The prediction process relieson a Convolutional neural network(CGVP-CNN)model that receives an input of a 3-side image and then extractsthe needed features to estimate an approximation for the volume.The classification was comparatively performedvia ten different classifiers,namely,K-Nearest Neighbors(KNN),Linear Support Vector Machines(Linear SVM),Radial Basis Function(RBF)SVM,Gaussian Process,Decision Tree,Random Forest,Multi-Layer Perceptron(MLP),Adaptive Boosting(AdaBosst),Naive Bayes,and Quadratic Discriminant Analysis(QDA).After severalexperiments on testing and training data,results yield a classification accuracy of 100%,92%,95%,96%,100%,100%,100%,96%,81%,and 92%,respectively.The test reveals the best timing with KNN,which maintained anaccuracy level of 100%.Assessing themodel generalization capability to newdata is essential to ensure the efficiencyof the model,so by applying a cross-validation experiment,the model generalization was measured.The useddataset was isolated based on the volume values to ensure the model generalization not only on new images of thesame volume but with a volume outside the trained range.Then,the predicted volume values were passed to theclassifiers group,where classification reported accuracy was found to be(100%,100%,100%,98%,88%,87%,100%,87%,97%,100%),respectively.Although obtaining a classification with high accuracy is the main motive,this workhas a remarkable reduction in the data preprocessing time compared to related works.The CGVP-CNN modelmanaged to reduce the data preprocessing time of previous works to 0.017 s while maintaining high classificationaccuracy using the estimated volume value.
基金Project(2012AA062102)supported by High-Tech Research and Development Program of ChinaProject(KYLX_1379)supported by the Innovation Training Project of Graduate Student in Jiangsu Province,ChinaProject supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions,China
文摘Based on the separation and backfilling system of coal and gangue, the mineral material impact experiments were conducted utilizing the hardness difference between coal and gangue according to the uniaxial compression experiments. The broken coal and gangue particles were collected and screened by different size meshes. The particle size distributions of coal and gangue under different impact velocities were researched according to the Rosin-Rammler distribution. The relationships between separation indicators and impact velocities were discussed. It is found from experiments that there is a fully broken boundary of coal material. The experimental results indicate that the Rosin-Rammler distribution could accurately describe the particle size distribution of broken coal and gangue under different impact velocities, and there is a minimum overlap region when the impact velocity is 12.10 m/s which leads to the minimum mixed degree of coal and gangue, and consequently the benefit of coal and gangue separation.
文摘Rutile separation from calcite, apatite and quartz by flotation was investigated. The results show that the rutile separation from calcium and silicon gangue minerals can be realized with alkyl-imino-bismethylene phosphoric acid (TF112) as a collector and sodium hexametaphosphate (SH) as a regulator.
基金the Natural Science Foundation of Jiangsu Province (No.BK2009098)
文摘Gangue from underground separation of coal can directly be used for filling mined out areas, saving transport capacity and reducing the amount of waste polluting the environment above the ground. We introduced a structure and operating principle of an underground direct-impact sieving device by which a separation experiment was carried out. By means of high speed conveyer belts, coal and gangue impacted the breaking board at high speeds ranging from 6 to 14 m/s. Given the differences of hardness between coal and gangue, after selective crushing, the gangue with the higher hardness was crushed less and coal with lower hardness crushed more, which could be separated by a 50 mm sieving plate. The material above the sieving plate was disposed of as gangue and the material below as coal. The results indicate that the crush ratio below the 50 mm sieving plate increases linearly with an increase in impact velocity and decays exponentially with an increase in hardness. Employing this equipment to separate coal and gangue, the hardness of coal f should be <2. This separation device provides relatively good effect in separating coal and gangue with a relatively wide difference of hardness.
基金the National Key Technology R&D Program of China forthe support of this work(No.2007BAE58B01).
文摘Selective separation of silica from a siliceous-calcareous phosphate ore that had been sieved into different size fractions is investigated by a combination of chemical analysis,zeta potential measurement and FTIR and XPS techniques.Scrubbing is a better choice than flotation for removing silica from the coarse fractions.The P_2O_5 grade of the coarse fractions is increased to about 30%by scrubbing and the product yields are higher than those obtained by flotation.The silica in the fine fraction is separated by reverse flotation.An alkyl amine salt(DAH)is an effective collector and the P_2O_5 grade of the fine fraction can be increased by 7%to beyond 30%under acidic conditions.The higher zeta potential obtained using DAH suggests that it is more strongly absorbed onto the ore particles than the other cationic collectors. FTIR and XPS results confirm physical absorption of the cationic collector onto the ore surface.They also indicate that calcite is dissolved at low pH values,which increases the Si concentration on the ore surface.
