煤泥浮选泡沫图像分割算法研究

针对工业现场采集的泡沫图像噪声大、对比度低、气泡粘连等特点,提出了一种基于双边滤波与限制对比度自适应直方图均衡的分水岭分割模型。首先通过双边滤波对原始泡沫图像进行去噪处理;其次,针对泡沫图像对比度低的特点,采用限制对比度自适应直方图均衡(CLAHE)增强图像对比度以及防止噪声的放大,最后利用分水岭变换对预处理之后的图像进行分割处理。实验结果证明该模型的有效性,预处理之后分割的图像能够有效改善直接处理所带来的欠分割现象。     

利用阈值分割技术提取煤泥浮选泡沫图像的物理特征

探讨了煤泥浮选泡沫图像特征的提取方法，首先将RGB图像转化为灰度级图像，再采用直方图均衡化和局域中值滤波处理，以改善图像的对比度，利用阈值分割技术和二值化处理方法提取了气泡的个数，对亮点的面积，形状，周长进行了计算，求出了气泡的粒度分布，通过对51幅煤泥浮选泡沫图像的研究。发现该方法适用于亮点明显，气泡粒度大的图像，可以用来指导煤泥浮选的操作。     

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,无法精确的分割泡沫边缘。据此,本文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,本文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Fscore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。     

基于Contourlet变换的模糊聚类和膨胀重构相结合的浮选图像增强方法

针对用分水岭算法分割铅锌矿泡沫图像时标识点难以提取及气泡边界模糊问题,提出了模糊C均值聚类和二值开重构相结合的方法及基于Contourlet变换的泡沫图像增强方法。首先对图像进行聚类,提取出灰度值较大的一类点,对提取出获得的图像用不同的结构元素进行二值开重构操作除掉一些灰度值较大的边缘点和噪声,得到气泡内部高亮点作为标识点。然后对泡沫图像做Contourlet变换提取高频系数,构造自适应增强函数作用于高频系数,利用增强后的高频系数做Contourlet反变换以增强泡沫图像。最后在上面获得的标识图像和增强图像的基础上用分水岭变换对图像进行分割。试验结果表明,该方法能够对气泡边界模糊的铅锌矿图像实行有效分割。     

浮选颗粒-气泡脱附机理研究进展及展望

浮选颗粒-气泡矿化包括碰撞、黏附以及矿化气絮体升浮3个子过程,部分目的矿物会在矿化气絮体升浮过程中发生脱附,降低目的矿物浮选回收率,这也是粗颗粒浮选效率较低的根本原因。深入理解颗粒-气泡的脱附机理一直是浮选领域的研究热点与难点,更是实现粗颗粒浮选强化的前提条件。围绕矿浆相、泡沫相以及矿浆-泡沫相界面区3个脱附区域,综述了颗粒-气泡脱附机理最新的研究进展,以期为粗颗粒浮选强化提供理论指导。湍流与气泡兼并脱附分别是颗粒在矿浆相和泡沫相中发生脱附的主要机制,而矿浆-泡沫相界面区颗粒脱附机理尚存在争议,一种观点认为矿化气絮体撞击界面时动能的改变导致脱附,另一种观点认为界面处气泡兼并引起的气泡振荡才是脱附的主要原因,该区域的脱附机理尚需进一步探索。最后提出了未来颗粒-气泡脱附机理研究的发展方向,包括矿浆相多种脱附机制协同作用、宽粒级物料的原位脱附过程及其粒度匹配效应、矿化气泡在相界面处碰撞及兼并脱附过程的能量演化竞争机制。     

在浮选泡沫中颗粒—气泡附着的问题

在浮选过程中，由于气泡的结合、破裂及泡沫过载而使泡沫相中的疏水颗粒从气泡上脱落。当某些脱落的颗粒返回到矿浆中时，另有一部分颗粒可能会选择性地再附着于从泡沫中上升的气泡上。这样可能形成泡沫中品位变化的特性。虽然这过程未经详细研究，但定性的数据表明，这种现象出现在较深的、载荷小的泡沫中，正如浮选柱过程所出现的情况那样。已研究出一种描述上述过程的数学模型，这种模型考虑了气泡表面被可浮颗粒复盖的程度以及随     

泡沫分选机的研究

根据泡沫分选的特点,针对粗颗粒选别环境设计了新型的泡沫分选机试验系统,通过浮选动力学的清水对比试验研究,找到了最优的气泡发生器。同时在安徽铜陵冬瓜山铜矿选矿厂进行了矿浆试验,对于粗颗粒而言,泡沫分选装置系统的选别能力要优于JJF-130型浮选机。矿浆试验证明,泡沫分选机系统在粗颗粒矿物选别方面具有很好的发展前景,值得进一步研究。     

煤泥浮选泡沫图像分割与特征提取

针对在煤泥浮选泡沫图像中的煤泥气泡互相粘连、边界模糊的情况,根据分水岭变换模拟浸水原理,提出一种新的、有效的分割算法,同时应用数学形态学中的腐蚀和膨胀算法,解决了经典分水岭算法不能处理的过分割和欠分割问题,使得粘连的煤泥气泡得到了有效的分割.然后计算出各个煤泥气泡的横截面积、周长、形状等物理特征参数,这些参数是实现自动控制浮选过程的重要依据.     

基于浮选泡沫图像特征参数的应用研究

基于泡沫图像分析仪在大山选厂的具体应用,研究浮选泡沫的物理意义以及获取的浮选泡沫图像具体特征参数,提取100个矿浆样以及相对应的泡沫图像样,建立两者的数学模型,用该模型对铜精矿品位进行实时预测,有效地指导了现场的实际生产操作。     

白云鄂博稀土矿浮选泡沫图像颜色特征与品位相关性研究

在稀土矿物实际浮选中,泡沫颜色特征与稀土品位关系密切。针对白云鄂博稀土矿浮选过程中浮选槽中含气率高、气泡重叠、变形,以及不断发生气泡兼并与破裂的情况,设计建立图像采集系统,并针对LED光源特点,设定照射光源最佳角度,进行图像采集。对采集图像进行进一步颜色特征提取,对泡沫图像颜色与品位之间的相关性进行分析研究。根据浮选过程中浮选泡沫表征颜色与品位的相关性,结合计算机图像处理技术,使用Matlab数学分析软件,对泡沫图像进行预处理并且进一步对泡沫图像进行边缘提取,对泡沫色彩进行色彩效果增强处理,将颜色分类量化,并进行色彩分类统计。通过对泡沫图像灰度直方图分析,计算并统计其整体亮度情况,作为泡沫图像亮度值定量依据。结果表明:通过分析浮选图像RGB颜色值分布、颜色分级分类量化提取图像颜色特征值以及灰度信息,对泡沫颜色特征有一定代表性,并且提高泡沫图像颜色提取精度。通过BP神经网络,输入泡沫图像特征值颜色与品位信息并建立黑箱模型,通过样本训练,得到稀土品位预测值。     

The effect of mothers on bubble size distributions in flotation pulp phases and surface froths

Froth dynamics, i.e. the stability and mobility of the froth, are crucial indicators of various important features of flotation systems. For example, it is desirable that the froth collapses as soon as possible after it is skimmed off the cell in order to curtail losses in throughput. On the other hand, if the froth is too prone to collapse, it will not be sufficiently stable to support its load prior to skimming. Likewise, the mobility of the froth gives similar information on the performance of the flotation cell. For example, a sharp contrast can be observed between dry viscous (immobile) froths and watery runny froths with high mobility. Several authors have recently shown that analysis of the structure of the froth in a flotation cell can be used to assess the performance of the cell. This implies that there is a close relationship between the bubble size distribution in the pulp and froth phases.Until very recently, it was not possible to verify this hypothesis direct, since reliable measurements of bubble size distributions in especially the froth phase could not be obtained. With recent improvements in the machine vision technology originally developed at the University of Stellenbosch, it is now possible to measure bubble size distributions and stability in froth structure with a high degree of accuracy. Unlike previous methods, these improved algorithms can provide a detailed map of flow patterns in the froths, which can give a significantly better idea of operating conditions in the flotation cell. Consequently, in this experimental study the bubble size distribution in the pulp phase of a laboratory flotation cell was measurement with a capillary tube system (UCT bubble size analyser), while the bubble size distribution in the froth phase was measured by use of digital image analysis. The relationship between these bubble size distributions in the pulp and froth phases is discussed.     

一种改进分水岭算法的浮选泡沫图像分割方法

为了解决煤泥浮选泡沫图像分割中传统分水岭算法的过分割问题,提出了一种基于自适应标记提取的改进分水岭算法。该方法首先对浮选泡沫图像进行高斯滤波,再运用基于形态学的扩展最大值技术从泡沫图像中自适应提取标记,利用标记对梯度图像进行修改,最后使用分水岭算法对修正后的梯度图像进行分割。试验结果表明,改进后的算法克服了标记提取需要先验知识、分割过程繁琐等问题,使参数选取更加合理,分割结果更加准确。     

浮选指标与浮选泡沫数字图像关系研究

在实验室采集了大量黄铜矿浮选的泡沫图像,并对浮选泡沫图像进行了预处理;采用数字图像分析技术分析了泡沫图像及其灰度直方图,提取了浮选泡沫图像灰度直方图的统计纹理特征参数;采用径向基神经网络建立了黄铜矿浮选指标与泡沫灰度直方图统计纹理特征参数的关系模型。仿真实验证明,所建立的模型有较高的精度。     

Selective transport of attached particles across the pulp–froth interface

A technique for determining the recovery of attached particles across the froth phase in flotation that relies on measuring the rate at which bubble–particle aggregates enter the froth is used to investigate the selectivity of attached particles across the froth phase. Combining these measurements with those of other techniques for determining the froth recovery of attached particles provides an insight into the different sub-processes of particle rejection in the froth phase. The results of experiments conducted in a 3 m³ Outokumpu tank cell show that the detachment of particles from aggregates in the froth phase occurs largely at the pulp–froth interface. In particular it is shown that the pulp–froth interface selectively detaches particles from aggregates according to their physical attributes.     

煤泥浮选泡沫图像灰度直方图及其统计纹理特征研究

针对煤泥浮选泡沫图像灰度直方图特征问题，进行了实验室浮选柱试验，采集了50组煤泥浮选泡沫图像，分析了泡沫图像及其直方图的类别及形态，提取了浮选泡沫图像直方图统计纹理特征参数，研究了泡沫直方图统计纹理特征参数随浮选时间的变化关系。研究表明，统计纹理特征参数-方差能够表征浮选泡沫图像直方图特征，并与特定的泡沫状态相关，可为煤泥浮选视觉监控系统提供泡沫状态信息。     

Froth transport characterization in a two-dimensional flotation cell

A study of the froth bubble transport in a two-dimensional (2D) flotation cell was performed. Experiments were developed as a 2 × 2 factorial design, in which the effect of superficial air rate (1.2–1.8 cm/s) and froth depth (2–4 cm) on the froth transport for a two phase (air–water) system was characterized.Using image analysis techniques, bubble residence times, air recovery, bubble path and bubble size increase through the froth were obtained. This information was complemented by froth surface velocity measurements using the Visiofroth system.It was found that bubbles transported from the pulp–froth interface up to the overflow, showed a minimum residence time for bubbles entering the froth near the lip wall. Also, the air-recovery significantly changes in a range of 7–20% at different operating conditions.Higher residence times promoted bubble size increase by coalescence for bubbles transported from the interface. Conversely, for lower residence times, a smaller increase in bubble size was observed.     

Effect of ultrasound on separation selectivity and efficiency of flotation

The effect of the use of ultrasound in the froth phase on the flotation performance has been investigated in relation to the flotation rate of a complex sulphide ore. A series of kinetic flotation tests with and without ultrasound were conducted in a flotation machine with a 2-L cell, in which an ultrasonic probe is located in the froth zone. The results indicate that there is a considerable effect of ultrasound on separation selectivity and efficiency in the flotation of a complex sulphide ore at intermediate and high level airflow rates whereas, no significant differences in the separation performance were obtained from the flotation with and without ultrasound at low airflow rates. In addition, the results of the size-by-size analysis show that a much better cleaning action in the froth was promoted for coarse particles rather than fine particles as a result of the use of ultrasound. As a result of increase in the bubble coalescence, it was found that the use of ultrasound in the froth is more effective at shallow froths. Therefore, either effective pulp volume can be increased with a negligible loss of flotation performance or the pulp density can be decreased to obtain better product quality with the use of ultrasound in shallow froths.     

CFD modelling of bubble–particle attachments in flotation cells

In recent years, computational fluid dynamic (CFD) modelling of mechanically stirred flotation cells has been used to study the complexity of the flow within the cells. In CFD modelling, the flotation cell is discretized into individual finite volumes where local values of flow properties are calculated. The flotation effect is studied as three sub-processes including collision, attachment and detachment. In the present work, these sub-processes are modelled in a laboratory flotation cell. The flotation kinetics involving a population balance for particles in a semi-batch process has been developed.From turbulent collision models, the local rates of bubble–particle encounters have been estimated from the local turbulent velocities. The probabilities of collision, adhesion and stabilization have been calculated at each location in the flotation cell. The net rate of attachment, after accounting for detachments, has been used in the kinetic model involving transient CFD simulations with removal of bubble–particle aggregates to the froth layer.Comparison of the predicted fraction of particles remaining in the cell and the fraction of free particles to the total number of particles remaining in the cell indicates that the particle recovery rate to the pulp–froth interface is much slower than the net attachment rates. For the case studied, the results indicate that the bubbles are loaded with particles quite quickly, and that the bubble surface area flux is the limiting factor in the recovery rate at the froth interface. This explains why the relationship between flotation rate and bubble surface area flux is generally used as a criterion for designing flotation cells. The predicted flotation rate constants also indicate that fine and large particles do not float as well as intermediate sized particles of 120–240 μm range. This is consistent with the flotation recovery generally observed in flotation practice. The magnitude of the flotation rate constants obtained by CFD modelling indicates that transport rates of the bubble–particle aggregates to the froth layer contribute quite significantly to the overall flotation rate and this is likely to be the case especially in plant-scale equipment.