With the rise of artificial intelligence(AI)in mineral processing,predicting the flotation indexes has attracted significant research attention.Nevertheless,current prediction models suffer from low accuracy and high ...With the rise of artificial intelligence(AI)in mineral processing,predicting the flotation indexes has attracted significant research attention.Nevertheless,current prediction models suffer from low accuracy and high prediction errors.Therefore,this paper utilizes a two-step procedure.First,the outliers are pro-cessed using the box chart method and filtering algorithm.Then,the decision tree(DT),support vector regression(SVR),random forest(RF),and the bagging,boosting,and stacking integration algorithms are employed to construct a flotation recovery prediction model.Extensive experiments compared the prediction accuracy of six modeling methods on flotation recovery and delved into the impact of diverse base model combinations on the stacking model’s prediction accuracy.In addition,field data have veri-fied the model’s effectiveness.This study demonstrates that the stacking ensemble approaches,which uses ten variables to predict flotation recovery,yields a more favorable prediction effect than the bagging ensemble approach and single models,achieving MAE,RMSE,R2,and MRE scores of 0.929,1.370,0.843,and 1.229%,respectively.The hit rates,within an error range of±2%and±4%,are 82.4%and 94.6%.Consequently,the prediction effect is relatively precise and offers significant value in the context of actual production.展开更多
Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have...Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation,like color,shape,size and texture,always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case.In this work,a new integrated method based on convolution neural network(CNN)combined with transfer learning approach and support vector machine(SVM)is proposed to automatically recognize the flotation condition.To be more specific,CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection.As compared with the existed recognition methods,it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy.Hence,a CNN-SVM based,real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.展开更多
Aspiration spiral flow type centrifugal flotation machine takes full advantage of centrifugal force field and gravitational field, and strengthens flotation of coal slurry. As a new-type flotation machine of high effi...Aspiration spiral flow type centrifugal flotation machine takes full advantage of centrifugal force field and gravitational field, and strengthens flotation of coal slurry. As a new-type flotation machine of high efficiency, its key component is bubble generator. Which completes the process of ore pulp inflation and liberalization. The design, parameters and working principle of bubble generator provide the design of the same device in similar equipment with reference. The result of industrial operation shows that this machine is of such features as small occupational area, greater concentration ratio, high processing capacity, high efficiency and lower investment etc.展开更多
Aiming at the problems such as more repeatedly design and longer design cycle, in this paper, the similarity theory was introduced to the design process of the key structures of flotation machine. The impeller and U-s...Aiming at the problems such as more repeatedly design and longer design cycle, in this paper, the similarity theory was introduced to the design process of the key structures of flotation machine. The impeller and U-shaped tank of flotation machine system were analyzed as similarity unit. Meanwhile, the level of similarity of the units and the similarity of the system were calculated. Based on the analysis of the impeller and the size of U-shaped tank, the similarity criteria were derived. The derived conclusions are： （1） The relationship between the diameter of the impeller and the volume of the tank was power function and calculated as the similarity criteria of the impeller; （2） The relationship between the ratio between the U-shaped tank＇s cross-sectional area and impeller＇s diameter and the volume of the tank was power function and calculated as the similarity criterions of the U-shaped tank. Using the similarity criterion combined with computer technology and database technology to realize part and system serialization design. The results show that the research can efficiency. avoid repeatedly design, shorten design cycle, and raise the design展开更多
The mixing mechanism of flotation cells is studied, and the mathematics model for mixing power is established. The model can be used to calculate the power consumption of the whole mechanism, as well as the power comp...The mixing mechanism of flotation cells is studied, and the mathematics model for mixing power is established. The model can be used to calculate the power consumption of the whole mechanism, as well as the power composition of each individual part. The power magnitude and the ratio between the macroscopic convection diffusion and the turbuleut diffusion, which are closely related to the performance of a cell, are also analyzed.展开更多
针对浮选过程变量滞后、耦合特征及建模样本数量少所导致精矿品位难以准确预测的问题,提出了一种基于改进麻雀搜索算法(Improved Sparrow Search Algorithm,ISSA)优化混核最小二乘支持向量机(Hybrid Kernel Least Squares Support Vecto...针对浮选过程变量滞后、耦合特征及建模样本数量少所导致精矿品位难以准确预测的问题,提出了一种基于改进麻雀搜索算法(Improved Sparrow Search Algorithm,ISSA)优化混核最小二乘支持向量机(Hybrid Kernel Least Squares Support Vector Machine,HKLSSVM)的浮选过程精矿品位预测方法.首先采集浮选现场载流X荧光品位分析仪数据作为建模变量并进行预处理,建立基于最小二乘支持向量机(Least Squares Support Vector Machine,LSSVM)的预测模型,以此构建新型混合核函数,将输入空间映射至高维特征空间,再引入改进麻雀搜索算法对模型参数进行优化,提出基于ISSA-HKLSSVM方法实现精矿品位预测,最后开发基于LabVIEW的浮选精矿品位预测系统对本文提出方法实际验证.实验结果表明,本文提出方法对于浮选过程小样本建模具有良好拟合能力,相比现有方法提高了预测准确率,可实现精矿品位的准确在线预测,为浮选过程的智能调控提供实时可靠的精矿品位反馈信息.展开更多
基金supported by the National Key R&D Program of China(No.2023YFC2908200)National Natural Science Foundation of China(No.52174249)Key Research and Development Program of Jiangxi Province(No.20203BBGL73231).
文摘With the rise of artificial intelligence(AI)in mineral processing,predicting the flotation indexes has attracted significant research attention.Nevertheless,current prediction models suffer from low accuracy and high prediction errors.Therefore,this paper utilizes a two-step procedure.First,the outliers are pro-cessed using the box chart method and filtering algorithm.Then,the decision tree(DT),support vector regression(SVR),random forest(RF),and the bagging,boosting,and stacking integration algorithms are employed to construct a flotation recovery prediction model.Extensive experiments compared the prediction accuracy of six modeling methods on flotation recovery and delved into the impact of diverse base model combinations on the stacking model’s prediction accuracy.In addition,field data have veri-fied the model’s effectiveness.This study demonstrates that the stacking ensemble approaches,which uses ten variables to predict flotation recovery,yields a more favorable prediction effect than the bagging ensemble approach and single models,achieving MAE,RMSE,R2,and MRE scores of 0.929,1.370,0.843,and 1.229%,respectively.The hit rates,within an error range of±2%and±4%,are 82.4%and 94.6%.Consequently,the prediction effect is relatively precise and offers significant value in the context of actual production.
基金Projects(61621062,61563015)supported by the National Natural Science Foundation of ChinaProject(2016zzts056)supported by the Central South University Graduate Independent Exploration Innovation Program,China
文摘Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation,like color,shape,size and texture,always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case.In this work,a new integrated method based on convolution neural network(CNN)combined with transfer learning approach and support vector machine(SVM)is proposed to automatically recognize the flotation condition.To be more specific,CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection.As compared with the existed recognition methods,it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy.Hence,a CNN-SVM based,real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.
文摘Aspiration spiral flow type centrifugal flotation machine takes full advantage of centrifugal force field and gravitational field, and strengthens flotation of coal slurry. As a new-type flotation machine of high efficiency, its key component is bubble generator. Which completes the process of ore pulp inflation and liberalization. The design, parameters and working principle of bubble generator provide the design of the same device in similar equipment with reference. The result of industrial operation shows that this machine is of such features as small occupational area, greater concentration ratio, high processing capacity, high efficiency and lower investment etc.
基金Supported by National Natural Science Foundation of China (Grant No.51275145)
文摘Aiming at the problems such as more repeatedly design and longer design cycle, in this paper, the similarity theory was introduced to the design process of the key structures of flotation machine. The impeller and U-shaped tank of flotation machine system were analyzed as similarity unit. Meanwhile, the level of similarity of the units and the similarity of the system were calculated. Based on the analysis of the impeller and the size of U-shaped tank, the similarity criteria were derived. The derived conclusions are： （1） The relationship between the diameter of the impeller and the volume of the tank was power function and calculated as the similarity criteria of the impeller; （2） The relationship between the ratio between the U-shaped tank＇s cross-sectional area and impeller＇s diameter and the volume of the tank was power function and calculated as the similarity criterions of the U-shaped tank. Using the similarity criterion combined with computer technology and database technology to realize part and system serialization design. The results show that the research can efficiency. avoid repeatedly design, shorten design cycle, and raise the design
文摘The mixing mechanism of flotation cells is studied, and the mathematics model for mixing power is established. The model can be used to calculate the power consumption of the whole mechanism, as well as the power composition of each individual part. The power magnitude and the ratio between the macroscopic convection diffusion and the turbuleut diffusion, which are closely related to the performance of a cell, are also analyzed.
文摘针对浮选过程变量滞后、耦合特征及建模样本数量少所导致精矿品位难以准确预测的问题,提出了一种基于改进麻雀搜索算法(Improved Sparrow Search Algorithm,ISSA)优化混核最小二乘支持向量机(Hybrid Kernel Least Squares Support Vector Machine,HKLSSVM)的浮选过程精矿品位预测方法.首先采集浮选现场载流X荧光品位分析仪数据作为建模变量并进行预处理,建立基于最小二乘支持向量机(Least Squares Support Vector Machine,LSSVM)的预测模型,以此构建新型混合核函数,将输入空间映射至高维特征空间,再引入改进麻雀搜索算法对模型参数进行优化,提出基于ISSA-HKLSSVM方法实现精矿品位预测,最后开发基于LabVIEW的浮选精矿品位预测系统对本文提出方法实际验证.实验结果表明,本文提出方法对于浮选过程小样本建模具有良好拟合能力,相比现有方法提高了预测准确率,可实现精矿品位的准确在线预测,为浮选过程的智能调控提供实时可靠的精矿品位反馈信息.
