A froth velocity measurement method based on improved U-Net++semantic segmentation in flotation process

During flotation,the features of the froth image are highly correlated with the concentrate grade and the corresponding working conditions.The static features such as color and size of the bubbles and the dynamic features such as velocity have obvious differences between different working conditions.The extraction of these features is typically relied on the outcomes of image segmentation at the froth edge,making the segmentation of froth image the basis for studying its visual information.Meanwhile,the absence of scientifically reliable training data with label and the necessity to manually construct dataset and label make the study difficult in the mineral flotation.To solve this problem,this paper constructs a tungsten concentrate froth image dataset,and proposes a data augmentation network based on Conditional Generative Adversarial Nets(cGAN)and a U-Net++-based edge segmentation network.The performance of this algorithm is also evaluated and contrasted with other algorithms in this paper.On the results of semantic segmentation,a phase-correlationbased velocity extraction method is finally suggested.

浮选泡沫图像特征提取方法研究进展

机器视觉作为设备操作人员的工具,在泡沫浮选设备的监测中得到了广泛的应用。利用泡沫图像数据集建立预测识别模型,以初级泡沫特征参数为输入,以品位和回收率等浮选指标为输出。根据是否需要手动提取浮选泡沫图像特征,可以将特征提取算法划分为两大类别:一种是基于颜色、形态特征等的传统手动特征提取方法,另一种是基于深度神经网络的自动特征提取方法。本文总结并归纳了近年来浮选泡沫图像特征提取算法领域的研究进展,分析了各种方法的优势和不足,对当前难以人工识别泡沫状态及实现浮选自动化提升浮选效率,具有一定的指导价值。

硫化—胺法浮选菱锌矿体系中两相和三相泡沫的性能研究

硫化—胺法是氧化锌的主要选别方法之一,在工业生产中的指标较好,但存在浮选泡沫发黏、难消泡的问题。研究了硫化-胺法浮选菱锌矿体系中两相泡沫和三相泡沫的性能,考察了硫化钠用量、十二胺用量、矿物含量、矿物粒度、矿物种类等对泡沫稳定性的影响,并测试了不同矿物含量的矿浆黏度。结果表明,在采用硫化—胺法浮选菱锌矿时,加入硫化钠能够提高两相和三相泡沫的稳定性。不同粒度的矿物颗粒对泡沫稳定性影响不同,加入-74+37μm粒级的菱锌矿和石英颗粒均能够降低泡沫稳定性,而加入-37μm粒级的菱锌矿和石英颗粒均能够提高泡沫稳定性,-18μm的石英颗粒影响尤为明显。当十二胺与微细粒级石英共同存在时,浮选泡沫尤为稳定。加入石英颗粒后的三相泡沫半衰期均高于菱锌矿,这是由于石英矿浆的黏度高于菱锌矿,因而泡沫液膜的Marangoni效应增强,导致排液速率变慢,泡沫液膜变薄速率下降,泡沫稳定性更强。

基于浮选泡沫图像预测精矿品位的研究进展

随着人工智能技术在矿业生产的广泛应用,利用计算机视觉技术提高精矿品位预测的准确性和效率已成为必然趋势。在综述了传统图像处理算法和深度学习算法在精矿品位预测中的应用与发展历程基础上,并探讨了未来的发展趋势和挑战。传统图像处理技术通过提取泡沫图像的尺寸、颜色、纹理和流速等特征,结合分水岭分割、颜色矩、灰度共生矩阵和局部点特征匹配等算法进行特征提取。这些特征在计算资源有限的场景中具有一定的应用价值,但在应对精矿品位预测任务时精度较低。深度学习技术通过构建合适的模型架构并利用大量数据进行训练,能够提取高层语义特征,具有较高的预测精度,与图形处理单元(GPU)等高效运算设备配合使用,可实现高性能和高效率的统一。介绍了支持向量机(SVM)、极限学习机(ELM)等机器学习算法以及多层感知器(MLP)、全连接层和多尺度特征融合等深度学习算法在特征映射和品位预测中的应用,以及深度学习模型的发展历程。最后综述了工业界视觉检测系统的应用现状,并从数据驱动模型、多模态数据融合、算法实时性和数据集规模等方面分析了该领域所面临的挑战和未来发展趋势。

基于质心−凸包−自适应聚类法的浮选泡沫动态特征提取

面对复杂的浮选现场环境及浮选泡沫自身相互粘连导致的边界不清等情况,现有泡沫动态特征(流动速度和崩塌率)提取方法往往无法准确划定属于每个泡沫的动态特征采样区域、不能全面匹配相邻帧间的特征点对且难以有效识别崩塌区域。针对上述问题,提出了一种基于质心−凸包−自适应聚类法的浮选泡沫动态特征提取方法。该方法采用集成Swin−Transformer多尺度特征提取能力的改进型Mask2Former,实现对泡沫质心的精准定位和崩塌区域的有效识别;通过最优凸包评价函数搜寻目标泡沫周围相邻一圈泡沫质心构建的凸包,拟合出接近实际泡沫轮廓的动态特征采样区域;运用基于Transformer的局部图像特征匹配(LoFTR)算法匹配相邻帧图像间的特征点对;针对动态特征采样区域内部的所有特征点对,通过基于OPTICS算法的主特征自适应聚类法提取每个泡沫的主要流动速度。实验结果表明,在普通泡沫质心定位和崩塌区域识别任务中,该方法分别取得了88.83%,97.92%的准确率及77.90%,96.52%的交并比;以2.69%的平均剔除率实现了99.93%的特征点对匹配正确率;在多种工况下均能有效划定与实际泡沫边界相近的特征采样区域,进而定量提取每个泡沫的动态特征。

萘磺酸钠对硫化铅锌矿中碳质物的选择性抑制

针对硫化铅锌矿中碳质物吸附浮选药剂、恶化浮选效果的问题,本文以隐晶质石墨为难浮碳质物,研究了抑制剂萘磺酸钠(2-NSS)对方铅矿、闪锌矿以及隐晶质石墨浮选行为的影响。结果表明:2-NSS对难浮碳质物石墨具有明显的抑制作用。加入2-NSS后,方铅矿品位从82.28%提高至85.93%,回收率从82.08%提高至97.06%;闪锌矿品位从61.19%提高至63.48%,回收率从89.31%提高至93.46%。接触角试验、红外光谱分析、吸附量测试、浮选泡沫分析等结果表明:2-NSS易吸附于石墨表面,难吸附于铅锌硫矿物表面,2-NSS吸附于石墨表面后,能减弱捕收剂异丁基黄原酸钠(SIX)在石墨表面的吸附,减少药剂消耗,浮选泡沫更稳定。DFT模拟分析结果表明:2-NSS主要通过π-π堆积作用吸附于石墨表面。

浮选图像中泡沫边缘分割

矿物浮选过程中泡沫的表面特征是浮选性能的重要指标,它可以实时、直观地反映浮选效果的变化,准确分割泡沫的边缘信息是浮选过程中一项重要的任务。近年来,研究人员提出了各种浮选泡沫图像分割算法,但浮选泡沫图像中存在泡沫数量多、泡沫间粘连严重以及边缘不清晰等问题,现存的方法由于其特征提取能力有限,无法精确地分割泡沫边缘。据此,利用深度学习提出了一种基于多尺度融合的浮选泡沫图像边缘分割算法,该算法通过引入一种深度高分辨率的编码结构以及一种基于注意力的分层融合方法来增强模型的特征提取能力,从而提高对于浮选泡沫边缘的分割效果。具体而言,深度高分辨率的编码结构可以在不同分辨率层级上同时维护特征信息,使我们的网络模型可以有效地捕捉不同尺度的信息,在提高图像语义理解能力的同时能够保持更多的细节信息,提高处理高分辨率以及密集任务图像的能力。除此之外,设计了一种基于注意力的分层融合方法来充分融合深层和浅层的特征图,使融合得到的特征图趋向于更重要的特征信息,从而提高识别浮选泡沫的边界和精确定位浮选泡沫的能力。该算法在泡沫边界分割数据集上凭借58.25的泡沫IoU以及73.62的泡沫F_(score)取得了最佳的性能,证明了我们提出的算法可以更加准确地分割浮选泡沫边缘。

两性表面活性剂封堵性能研究

针对耐温耐盐两性表面活性剂的起泡性能和稳泡性能进行研究。通过起泡实验,筛选出了耐温耐盐的起泡剂(TTB、XXB、DSB)和稳泡剂(AEO);然后,对3种起泡剂和稳泡剂的复配体系进行研究,得到了起泡体积较大、稳定性较好的配方;最后,通过泡沫稳定性实验研究了温度以及Na Cl、Ca Cl_(2)在不同矿化度下对泡沫性能的影响。在各实验温度下(20℃、60℃、80℃、90℃),TTB、XXB与AEO系列非离子表面活性剂复配后,起泡体积均有一定程度的下降,随着EO系列表面活性剂浓度的增加,其泡沫稳定性则明显增加。此外,随着EO数的增加,其起泡体积增加,稳定性下降。随着温度的增加泡沫体积增加,稳定性逐渐降低。随Na^(+)、Ca^(2+)浓度的增大,泡沫体积逐渐减小,稳定性增加,但是Ca^(2+)比Na^(+)的效果更加明显。

浮选生产过程泡沫状态与药剂控制关系研究

针对泡沫状态与浮选药剂用量的对应关系,采用泡沫图像分析仪与液位计等在线检测设备对浮选生产过程中的泡沫状态进行量化处理,建立泡沫状态与浮选药剂控制之间的对应关系。基于量化后的泡沫特征变量,对浮选药剂用量给出了指导意见,并为后续开展浮选药剂智能控制提供了基础。经过长时间现场观察和大量数据分析,验证了理论研究的合理性,对于提高浮选生产过程的效率和稳定性具有重要意义。

基于机器视觉的浮选泡沫灰分在线检测研究

通过实验室搭建的煤泥浮选泡沫采集系统对不同浮选阶段的泡沫图像进行采集和预处理,分析了不同阶段的泡沫图像的特征。分别基于图像灰度直方图和灰度共生矩阵方法提取泡沫纹理特征参数,针对泡沫分割过程中的过分割和欠分割问题,建立基于自适应标记提取的改进分水岭算法实现泡沫图像的有效分割,基于此提取了泡沫面积和承载量两个特征参数。综合泡沫纹理特征参数、尺寸特征参数及泡沫稳定性构建了图像多维特征向量,使特征敏感度得到一定程度的增强,在此基础上,构建了预测精煤灰分的BP神经网络拓扑结构。精煤灰分预测结果表明:当BP神经网络模型的隐含层节点数为10时,灰分在线检测的绝对误差可以控制在±1%之内。

基于显著性检测的全变差去高光研究

选矿浮选过程中浮选槽中的泡沫图像,受到工业摄像角度和光照点位置影响,导致泡沫图像颜色特征以及纹理特征的提取达不到预期效果。为解决上述问题,提出一种基于显著性检测的自适应全变差去高光算法。将处于RGB颜色空间的图像转换到处于YUV颜色空间中,根据显著值的大小,判定某个像素点是否为高光像素点,并修复图像高光区域。构建改进的全变差修复模型,并对图像修复模型完成求解。实验结果可知,所提算法对图像高光区域的识别以及细微处的处理具有一定的提高,且均方误差值与峰值信噪比在一定程度上得到了改善,可以有效的提取泡沫图像存在的亮点区域且修复。

锂云母、钛铁矿及黄铜矿浮选泡沫特性研究

泡沫区是浮选动力学中的一个重要分区,是实现有用矿物与脉石矿物最终分离的一个重要分区,控制着产品的产率、精矿品位及最终的回收率。选取三种典型矿物进行泡沫特性的分析研究,通过径向泡沫取样测试、泡沫流动性测试、泡沫载荷核算和药剂制度分析,剖析了锂云母、钛铁矿及黄铜矿的泡沫特性,提出了差异化泡沫强制回收的思路,为浮选泡沫产品的及时高效回收提供了指导。

非离子型捕收剂作用下的铝电解渣浮选脱碳试验研究

由于铝电解过程中的碳阳极表面发生选择性氧化和不等燃烧,碳颗粒会脱落并形成碳残留物,被称为阳极炭渣。炭渣中含有表面被氧化的石墨碳、有毒杂质、氟化钙(CaF2)、刚玉(α-)和冰晶石(Na)等。对采自贵州某铝业生产过程中产生的铝电解阳极炭渣作为原样进行处理分析,结果表明:经X射线衍射仪(XPS)分析,原样炭渣中碳颗表面存在的主要含氧基团为O1sC=O,含量为45.54%。经激光粒度分析,样品中含有大量的无机矿物质细泥,在浮选过程中这些细颗粒会覆盖在碳颗粒表面,从而进一步降低碳颗粒表面疏水性。据相关研究表明,添加传统捕收剂煤油很难取得理想的碳颗粒回收率,故本研究选择了非离子型表面活性剂油酸、亚油酸甲酯和蓖麻酸作为浮选捕收剂,并与用煤油作为捕收剂结果相比较。浮选结果表明,煤油和蓖麻酸浮选脱碳的最佳用量为1500 g/t,而油酸和亚油酸甲酯的最佳用量为500 g/t,同时,亚油酸甲酯的用量在500 g/t时,浮选效果最佳,精矿回收率和可燃体回收率最大分别为25.70%和73.12%。此外,结合PABI测试表明,亚油酸甲酯能更好地改善铝电解渣中碳颗粒表面疏水性,并与浮选结果相一致。

Nanobubble generation and its applications in froth flotation(part Ⅱ):fundamental study and theoretical analysis

Froth flotation is a commonly employed technology to improve the quality of raw coal and minerals.Coal and minerals particle size and surface hydrophobicity are two main parameters that affect three key steps in froth flotation process:particle-bubble collision,adhesion,and detachment.This paper fundamentally investigated the effects of nanobubble on coal and phosphate flotation.It has been found that the presence of nanobubble in flotation pulp could widen the coal and phosphate flotation particle size range,increase the particle surface hydrophobicity,and thus improve the coal and phosphate froth flotation recovery.

Nanobubble generation and its application in froth flotation (part I): nanobubble generation and its effects on properties of microbubble and millimeter scale bubble solutions

A special nanobubble generation system has been developed for evaluating the effect of nanobubble on froth flotation. In this study, an eight-factor five-level Central Composite Experimental Design was conducted for investigating eight important parameters governing the median size and the volume of nanobubbles. These process parameters included surfactant concentration, dissolved oxygen (O2) content, dissolved carbon dioxide gas (CO2) content, pressure drop in cavitation tube nozzle, <50 nm hydrophobic particle concentration, <50 nm hydrophilic particle concentration, slurry temperature and the time interval after nanobubble generation. The properties, stability and uniformity of nanobubbles were investigated. The study of the produced nanobubble’s effects on the characteristics of microbubble solutions and millimeter scale bubble solutions was performed in a 50.8 mm column.

Nanobubble generation and its applications in froth flotation(part IV):mechanical cells and specially designed column flotation of coal

Coal is the world's most abundant fossil fuel.Coal froth flotation is a widely used cleaning process to separate coal from mineral impurities.Flotation of coarse coal particles,ultrafine coal particles and oxidized coal particles is well known to be difficult and complex.In this paper,the nanobubbles' effects on the flotation of the varying particle size,particle density and floatability coal samples were evaluated using a bank of pilot scale flotation cells,a laboratory scale and a pilot scale specially designed flotation column.The parameters evaluated during this study include the flow rate ratio between the nanobubble generator and the conventional size bubble generator,the superficial air velocity,collector dosage,frother concentration,flotation feed rate,feed solids concentration,feed particle size,and the superficial wash water flow rate,etc.The results show that the use of nanobubbles in a bank of mechanical cells flotation and column flotation increased the flotation recovery by 8%～27% at a given product grade.Nanobubbles increased the flotation rate constants of 600～355,355～180,180～75,and 75～0 microns size coal particles by 98.0%,98.4%,50.0% and 41.6%,respectively.The separation selectivity index was increased by up to 34%,depending on the flotation feed characteristics and the flotation conditions.

Froth flotation of scheelite – A review

Froth flotation of scheelite has regained new focus since the 2010s and research regarding floatability and reagents has made great progress over the years. The main objective was and remains the selective flotation of scheelite from other calcium-bearing minerals, in particular calcite, fluorite and apatite. Due to similar properties, most attempts have limited success or only specific application(linked to a type of ore or a location). This article aims at reviewing all general physical-chemical information on froth flotation of scheelite, including electrokinetic properties, influence of p H and already existing reagents as well as ones still under examination. It appears that chelating or mixed collectors and modified versions of sodium silicate and quebracho hold great promise for scheelite flotation, while the use of said depressants and/or promoters seems inevitable.

Nanobubble generation and its applications in froth flotation(partⅢ):specially designed laboratory scale column flotation of phosphate

Froth flotation is used widely for upgrading raw phosphate.The flotation recovery of coarse phosphate(-1.18+0.425 mm) is much lower than that achieved on the-0.425+0.15 mm size fraction.Enhanced recovery of coarse phosphate particles is of great economic and environmental importance for phosphate industry.In this investigation,four different phosphate samples were aquired,characterized and tested in a specially designed laboratory-scale flotation column.Significant recovery improvement of coarse phosphate flotation was achieved using cavitation-generated nanobubble though its effects differ among the four testing phosphate samples.The laboratory-scale flotation column test results indicate that nanobubble increased P_2O_5 recovery by up to 10%～30%for a given Acid Insoluble(A.I.) rejection,depending on the characteristic of phosphate samples.The improvement effect of nanobubble on the hard-to-float particles was more significant than that on easy-to-float particles,especially at lower collector dosages.Nanobubbles reduced the collector dosage by 1/3 to 1/2.Nanobubbles almost doubled the coarse phosphate flotation rate constant and increased the flotation selectivity index by up to 25%.

Froth flotation of refuse coal fines and process optimization using 2D surface plots

Refuse coal fines of size <500 μm was collected from a metallurgical coal preparation plant located in the eastern coalfield region of India. The coal was beneficiated using froth flotation technique to recover clean coal with ash content of about 20% with the highest possible yield. Diesel oil as collector and pine oil as frother were used. Box-Behnken statistical design was followed for analyzing the performance at varying pulp density, collector and frother dosage. Results were discussed using 2D surface plots. Response function predictions determined by the regression analysis show coefficient of correlation(R^2) for yield and the ash content as 0.72 and 0.86, respectively. The highest yield of 45.79% is obtained at pulp density 10%, collector dose 2 kg/t and frother dose 1.5 kg/t. The lowest ash content of 18.9% is obtained at pulp density 10%, collector dose 1 kg/t and frother dose 1 kg/t.

Experimental Study and Analysis on Performance and Dedusting Efficiency of Frothing Generator

By simulating test and study in laboratory, the structure and performance offrothing generator were determined. The relative curves between the frothing volume and gas velocityof foaming net, supplying liquid volume and the content of foaming agent were obtainedrespectively. There were an optimum gas-velocity of foaming net, an optimum supplying liquid volumeand an optimum content of foaming agent under the condition of the given material quality and shapeof foaming net and spraying form. The spraying froth is of a great assistance in collectingrespirable dust.