Froth Velocity Research Articles

Predicting future velocity of mineral flotation froth using STMA-LSTM with sequence images

During the mineral flotation process, the surface froth image contains characteristic information that is closely related to the production index of the process. However, a delay often exists between the state of the flotation tank and the taste calculation results, which hinders real-time process regulation. To address this challenge, a video sequence prediction algorithm is proposed to forecast the future sequence of flotation froth, and a Spatiotemporal Motion-Attentive Long Short-Term Memory (STMA-LSTM) network model is introduced to estimate and predict the future image information of the froth by integrating spatiotemporal information. After obtaining the future froth image, an image velocity measurement algorithm is utilized to achieve the future velocity prediction of the flotation froth. To address the ambiguity of future froth images and the real-time demand of future velocity estimation, a Fast Froth Velocity Estimation (FFVE) algorithm is introduced. This algorithm is suitable for fast estimation of flotation froth velocity due to its low sensitivity to image blurring factors and fast feature matching. The proposed approach implements future motion velocity prediction of froth images, thereby addressing the delay in froth taste prediction and enhancing the overall efficiency of the process control in the flotation field.

An Adaptive Fuzzy Logic Control Method for Froth Velocity in the Flotation Process

In the flotation process, too high or too low froth velocity can lead to a reduction in the recovery of useful minerals. However, it is difficult to achieve stable control of froth velocity due to complex process characteristics and fluctuating working conditions. Uncertain feed conditions (feed flow rate, feed grade, and feed concentration) can cause large changes in the desired froth velocity and other uncertain conditions, which affect the accurate evaluation of the velocity state for feedback control. In this paper, an adaptive fuzzy logic control method for froth velocity (AFLC-FV) in the flotation process is proposed. In the method, an adaptive fuzzy quantization function with a dead zone is designed and used instead of the constant fuzzy quantization factor in the fuzzification procedure. Thus, the dynamic real domain of the velocity error can be mapped to a fixed standard fuzzy domain. Meanwhile, the width of the dead zone is adaptively adjusted according to froth mobility to improve steady-state performance. In addition, the velocity trend is extracted and used as an input variable to the controller together with the velocity error. The application results show that, compared with manual control, the AFLC-FV significantly enhances the control accuracy and stability under different ranges of velocity set-points, and effectively improves the mineral recovery by 0.18%.

Prediction of Clean Coal Ash Content in Coal Flotation through a Convergent Model Unifying Deep Learning and Likelihood Function, Incorporating Froth Velocity and Reagent Dosage Parameters

This study successfully achieved high-precision detection of the clean coal ash content in the coal froth flotation domain by integrating deep learning with the likelihood function. Methodologically, a novel data processing and prediction framework was established by combining a deep learning Keras neural network with the likelihood function from probability statistics. The SIFT algorithm was utilized to extract key feature points and descriptors from the images, and keypoint matching and mean-shift clustering algorithms were employed to accurately obtain information on foam motion trajectories and velocities. For parameter optimization, the maximum likelihood estimation was applied to find the optimal parameter estimates of the likelihood function, ensuring enhanced model accuracy. By incorporating the optimized likelihood function parameters into the Keras deep neural network, an efficient prediction model was constructed for the dosage of flotation reagents, froth velocity, and clean coal ash content. The model’s evaluation involved six performance metrics. The experimental results were highly significant, with R2 at 0.99997%, RMSE at 0.04458%, MAE at 0.00170%, MAPE at 0.02329%, RRSE at 0.00994%, and MAAPE at 0.00067%.

Froth velocity extraction method from froth image for flotation with large throughput based on composite deep learning network

Froth velocity is a crucial variable in froth flotation and its accurate detection is vital to process control. The velocity extraction is a challenging work under large throughput conditions due to the complex motion of the froth. Therefore, in this paper, a novel method called composite deep learning network (CDLN) is proposed, which is mainly composed by a cascade of pre-trained supervised network and an unsupervised network. The supervised network is pre-trained on a benchmark dataset and then is used to extract an initial flow field of the froth motion. The unsupervised network is trained on industrial froth videos with occlusion modeling to get a calibration flow field. The two flow fields are then fused to obtain the final flow field. The test results show that the proposed method can extract the froth velocity more accurately and faster than other popular methods through industrial froth videos under large throughput.

Measurement of bubble size and froth velocity using convolutional neural networks

Bubble size and froth velocity are the most important froth characteristics used for evaluating and controlling flotation systems. Bubble size is often measured using watershed and edge detection algorithms. These algorithms typically result in the over-segmentation of big bubbles or the under-segmentation of small ones. Froth velocity is usually determined by processing successive images using various techniques such as pixel tracing, block matching, and bubble tracking. Most of these algorithms perform well but are quite slow. Pre-trained convolutional neural networks are more accurate and simpler models for image classification and feature extraction. In this research, a new approach based on using a pre-trained convolutional neural network to measure bubble size and froth velocity from froth flotation images is proposed. The results demonstrate that pre-trained convolutional neural networks can serve as a more reliable and faster approach than classical image processing algorithms for analyzing froth images.

Operating condition recognition based on temporal cumulative distribution function and AdaBoost-extreme learning machine in zinc flotation process

Bubble size distribution (BSD) is a crucial indicator of operating conditions in froth flotation. However, current BSD-based recognition methods have some limitations in the BSD estimation and don't achieve satisfactory results. Therefore, an alternative operating condition recognition method is proposed. Firstly, the temporal cumulative distribution function (TCDF) is designed to represent the BSD on the froth video. Then, the piecewise basis function is established to fit the TCDF. Secondly, the TCDF-Minimum Redundancy Maximum Relevancy (MRMR) feature is generated by MRMR to increase the sensitivity of TCDF features to the operating conditions. Lastly, the proposed TCDF-MRMR feature together with froth velocity and texture features are fed into an AdaBoost-extreme learning machine (ELM) model to recognize the operating conditions. Experiments in a zinc flotation process demonstrate that the TCDF-MRMR feature is more effective than other BSD-based features, and the AdaBoost-ELM shows better performance than traditional single recognition models.

A dynamic flotation model for predictive control incorporating froth physics. Part II: Model calibration and validation

Modelling for flotation control purposes is the key stage of the implementation of model-based predicted controllers. In Part I of this paper, we introduced a dynamic model of the flotation process, suitable for control purposes, along with sensitivity analysis of the fitting parameters and simulations of important control variables. Our proposed model is the first of its kind as it includes key froth physics aspects. The importance of including froth physics is that it improves the estimation of the amount of material (valuables and entrained gangue) in the concentrate, which can be used in control strategies as a proxy to estimate grade and recovery.In Part II of this series, experimental data were used to estimate the fitting parameters and validate the model. The model calibration was performed to estimate a set of model parameters that provide a good description of the process behaviour. The model calibration was conducted by comparing model predictions with actual measurements of variables of interest. Model validation was then performed to ensure that the calibrated model properly evaluates all the variables and conditions that can affect model results. The validation also allowed further assessing the model’s predictive capabilities.For model calibration and validation purposes, experiments were carried out in an 87-litre laboratory scale flotation tank. The experiments were designed as a randomised 32 full factorial design, manipulating the superficial gas velocity and tailings valve position. All experiments were conducted in a 3-phase system (solid-liquid–gas) to ensure that the results obtained, as well as the behaviour of the flotation operation, are as similar as possible to those found in industrial flotation cells.In total, six fitting parameters from the model were calibrated: two terms from the equation for overflowing bubble size; three parameters from the bursting rate equation; and the number of pulp bubble size classes. After the model calibration, simulations were performed to validate the predictions of the model against experimental data. The validation results revealed good agreement between experimental data and model predictions of important flotation variables, such as pulp level, air recovery, and overflowing froth velocity. The high accuracy of the predictions suggests that the model can be successfully implemented in predictive control strategies.

Monitoring of Flotation Systems by Use of Multivariate Froth Image Analysis

Froth image analysis has been considered widely in the identification of operational regimes in flotation circuits, the characterisation of froths in terms of bubble size distributions, froth stability and local froth velocity patterns, or as a basis for the development of inferential online sensors for chemical species in the froth. Relatively few studies have considered flotation froth image analysis in unsupervised process monitoring applications. In this study, it is shown that froth image analysis can be combined with traditional multivariate statistical process monitoring methods for reliable monitoring of industrial platinum metal group flotation plants. This can be accomplished with well-established methods of multivariate image analysis, such as the Haralick feature set derived from grey level co-occurrence matrices and local binary patterns that were considered in this investigation.

RPI-SURF: A Feature Descriptor for Bubble Velocity Measurement in Froth Flotation With Relative Position Information

The local feature-based method is the most popular choice for froth velocity measurement. However, due to similar patterns or objects in the froth image pair, current local feature-based methods only consider local intensity character (LIC) and cannot extract the matches well. Therefore, we propose a new feature descriptor named relative position information (RPI)-SURF that integrates the LIC and the RPI from the nearest reference point. First, we use the SURF descriptor with a distance constraint to extract the LIC. Next, we calculate the RPI by the direction and distance to the nearest reference point pair. After that, we integrate the LIC and RPI to demonstrate the new feature descriptor. Extensive experiments verify the effectiveness of the proposed feature descriptor. Compared with the SURF descriptor, the recall and $F_{1}$ -score of the proposed RPI-SURF descriptor have been obviously increased, and the number of detected accurate matches on real froth image pairs by the RPI-SURF descriptor has been increased by at least nearly 60%.

Machine vision based monitoring and analysis of a coal column flotation circuit

Flotation columns are being routinely used for recovery of fine coal particles in the coal preparation plants. Because of high sensitivity of the flotation columns to variations in the process conditions, their continuous control is of vital importance. Machine vision is an economically viable, uncomplicated and reliable technique for monitoring and control of flotation circuits. In this study, a machine vision system is successfully developed and implemented in a coal column flotation circuit. Industrial flotation experiments are conducted at various operating conditions (air flow rate, slurry solids%, froth depth, frother and collector dosage) and the froth visual (bubble size, froth velocity, froth color) and textural (energy, entropy, contrast, homogeneity and correlation) features along with the metallurgical performances (combustible recovery, concentrate ash content) are recorded simultaneously. The relationships between the froth characteristics with the process as well as the performance parameters are analyzed. The promising results indicate that the developed system can be successfully used for diagnosing the process conditions as well as predicting the process performance at different operating conditions.

Evaluation of column flotation froth behavior by image analysis: effects of operational factors in desulfurization of iron ore concentrate

ABSTRACTFlotation performance is expected to be affected by froth characteristics due to the changes in the operating conditions. However, very little study has been undertaken to investigate how froth behavior responds to the flotation variables. This study presents an experimental program performed to investigate the effects of flotation variables including gas flow rate, froth depth, slurry solids percent, frother/collector dosage, and pH on the froth features such as bubble size, froth velocity, froth color and froth stability during desulfurization of an iron ore. These parameters were varied using a central composite design (CCD). Image analysis methods have been developed and employed successfully to characterize the froth features. Results of the CCD experiments showed that the flotation variables have different effects on the froth features. The effect of pH and its interaction with collector dosage have a significant impact on all froth features. Process condition can be accurately deduced from the froth surface appearance which provides a convenient way to quantify the parameters as the process control function.

Fuzzy Association Rule Based Froth Surface Behavior Control in Zinc Froth Flotation

Froth flotation is a vital mineral concentration process. Froth surface behavior is the knowledge about flotation working condition. However, in computer vision aided froth surface behavior control, there are still two challenges that need to be tackled seriously. Against the difficulty in the froth surface behavior representation, this paper proposes to combine the bubble size distribution (BSD) and froth velocity distribution. As far as we know, this is the first time that the froth velocity distribution is presented. Against the difficulty in the adaptive generation of the optimal froth surface behavior feature (optimal setpoint), this paper introduces the fuzzy apriori to mine the association rule between the current working condition and the optimal setpoint. Then, a fuzzy inference module is constructed to generate optimal setpoint for current working condition adaptively. Many validation experiments and comparison experiments demonstrate the superiority and robustness of the proposed methods.

The effect of different flotation operating parameters on the froth properties and their relation to clean coal ash content

ABSTRACTFroth properties and their relation to the concentrate grade play an important role in monitoring flotation running conditions and predicting flotation concentrate quality. In this paper, the correlation between the froth properties and clean coal ash content was investigated under complicated conditions where the frother dosage, gas velocity, and froth height were changed together. For the froth properties under study, their degree of correlation with clean coal ash content decreased in the order of homogeneity, water recovery, gray value, and froth velocity. The coefficient of determination (R2) of the fitting relationship between homogeneity and clean coal ash content was as high as 0.9028, because homogeneity has a close correlation with the foam structure and foam destabilization behaviors.

Sulfur Flotation Performance Recognition Based on Hierarchical Classification of Local Dynamic and Static Froth Features

This paper proposes a flotation performance recognition system based on a hierarchical classification of froth images using both local dynamic and static features, which includes a series of functions in image extraction, processing, and classification. Within the integrated system, to identify the abnormal working condition with poor flotation performance (NB it could be significantly different with the dynamic features of the froth in abnormal working condition), it is functioned first with building up local dynamic features of froth image from the information including froth velocity, disorder degree, and burst rate. To enhance the dynamic feature extraction and matching, this system introduces a scale-invariant feature transform method to cope with froth motion and the noise induced by dust and illumination. For the performance subdividing under normal working conditions, bag-of-words (BoW) description is utilized to fill the semantic gap in performance recognition when images are directly described by global image features. Accordingly typical froth status words are extracted to form a froth status glossary so that the froth status words of each patch form the BoW description of an image. A Bayesian probabilistic model is built to establish a froth image classification reference with the BoW description of images as the input. An expectation-maximization algorithm is used for training the model parameters. Data obtained from a real plant are selected to verify the proposed approach. It is noted that the proposed system can reduce the negative effects of image noise, and has high accuracy in flotation performance recognition.

Effect of gas superficial velocity (Jg) and frother/collector (MIBC/X-343) reagent dosage on froth horizontal displacement and galena drainage

This paper attends the study of froth behaviour for the design of future launder, crowder and scraper configurations. The effect of gas superficial velocity (Jg) and Methyl Isobutyl Carbinol/Sodium Isopropyl Xanthate (MIBC/X-343) reagent dosage on froth horizontal displacement, bubble size of the froth surface, froth velocity, froth carrying capacity, grade and particle size of the concentrate obtained, was studied. A novel experimental apparatus was constructed to promote the free transport of froth in its horizontal displacement using three output sections each 200mm long to extend the overflow lip to 200, 400 and 600mm from the flotation cell. The aim of this new experimental apparatus was to magnify the phenomena that occur in the froths. Attending this consideration, the present apparatus cannot be compared with industrial flotation cells but was particularly useful for describing phenomena on froth transport. The results show that the froth horizontal displacement was promoted at high levels of Jg, while high levels of frother/collector reagent dosage promote high froth carrying capacity and longer media half-life inhibiting bubble collapse as an effect of the mineral layer and the hydrated layer on the bubble. An adequate selection of both study variables generates a well loaded and fluid froth, which can survive for longer distances toward the overflow lip. On the other hand, the galena concentration increased or decreased across the horizontal displacement as a function of both Jg and frother/collector reagent dosage.

Machine vision based monitoring of an industrial flotation cell in an iron flotation plant

Froth flotation is the most commonly used technique for the separation of valuable from gangue minerals. Unforeseeable changes in the ore characteristics and operating conditions have necessitated continuous control of the flotation circuits. Experienced operators usually control the process performance through the froth visual features. Machine vision technology now offers a viable means of monitoring and control of the flotation circuits. In the current communication, a machine vision system was installed on a flotation cell in the rougher circuit of an iron flotation plant to monitor the process at different conditions. Bubble size distribution, number of bubbles, froth velocity and stability were the main visual features extracted from the froth images. The results indicate that the developed system is capable of accurately monitoring the process behavior at different conditions.

Prediction of the metallurgical performances of a batch flotation system by image analysis and neural networks

It is now generally accepted that froth appearance is a good indicative of the flotation performance. In this paper, the relationship between the process conditions and the froth features as well as the process performance in the batch flotation of a copper sulfide ore is discussed and modeled. Flotation experiments were conducted at a wide range of operating conditions (i.e. gas flow rate, slurry solids%, frother/collector dosage and pH) and the froth features (i.e. bubble size, froth velocity, froth color and froth stability) along with the metallurgical performances (i.e. copper/mass/water recoveries and concentrate grade) were determined for each run. The relationships between the froth characteristics and performance parameters were successfully modeled using the neural networks. The performance of the developed models was evaluated by the correlation coefficient (R) and the root mean square error (RMSE). The results indicated that the copper recovery (RMSE=2.9; R=0.9), concentrate grade (RMSE=1.07; R=0.92), mass recovery (RMSE=1.94; R=0.94) and water recovery (RMSE=3.07; R=0.95) can be accurately predicted from the extracted surface froth features, which is of central importance for control purposes.

Modeling the Relationship between Froth Bubble Size and Flotation Performance Using Image Analysis and Neural Networks

Machine vision technology now offers a viable means of monitoring and control of froth flotation systems. In this study the relationship between process conditions and the surface bubble size as well as the process performance in the batch flotation of a copper sulfide ore is discussed and modeled by neural networks. Flotation experiments are conducted at a wide range of process conditions (i.e., gas flow rate, slurry solids %, frother/collector dosage, and pH) and the froth mean bubble size along with the metallurgical parameters are determined for each run. An adaptive marker based watershed algorithm is successfully developed for segmentation of the froth images and measurement of the bubble size at different conditions. The results show that there is a strong correlation between process conditions and the froth mean bubble size, which is of great importance for control purposes. Even though the metallurgical parameters can be estimated from the froth mean bubble size alone, other froth features (i.e., froth velocity, color, and stability) are required to be measured in order to achieve more accurate predictions of the process performance.

Mechanism study of the impact of water-borne bacteria on flotation

Bacteria-containing water is being increasingly accessed by the minerals industry as an alternative water source to improve water efficiency. Water-borne bacteria have been shown to negatively affect the efficiency of froth flotation when using a representative system consisting of E. coli as the model bacterium and chalcopyrite as the model mineral. It is essential to understand the underlying mechanisms that could explain the observed effect, to provide guidance on the subsequent solutions to deal with it. This study conducted a systematic investigation into the mechanism by which bacteria affect flotation efficiency using fluorescence microscopy, bubble attachment time measurements, and froth phase characteristics. E. coli bacterial cells in solution were found to attach to chalcopyrite surfaces. In turn, the surface hydrophobicity of chalcopyrite particles decreased as the number of the attached bacterial cells increased. Reduction in surface hydrophobicity resulted in less mineral particles attaching to bubbles, leading to decreased froth stability, bubble coalescence rate and froth velocity. Slurry pH and Eh were also affected by the presence of the bacterial cells. These changes were correlated with reductions in flotation recoveries. These experimental results contribute to an understanding of how biotic water constituents impact the operation of flotation plants that choose to use alternative water sources, and provide knowledge towards possible solutions to the negative effect of water-borne bacteria.

Flow velocity measurement and analysis based on froth image SIFT features and Kalman filter for froth flotation

The flow velocity of flotation froth involves important information about the concentrate grade and the mineral recovery. It is significant to maintain the flow velocity of the froth at proper levels to achieve a good production performance in the machine vision-based process monitoring and control. However, the accurate velocity field measurement for the heavily deformed and seriously fragile froth bubbles is still a great challenge. Scale-invariant feature transform (SIFT) feature-based image matching provides an effective registration method for deformed objects, but most of the processing time would be wasted on the feature extraction and matching in irrelevant regions of the image pairs, which is unsuitable for online process monitoring. The Kalman filter is an effective tool to predict the next positions of the subblocks in the froth image sequences. Taking advantage of the merits of the SIFT and the Kalman filtering, an online froth velocity field measurement method based on the SIFT features and an improved Kalman filtering is presented in this paper. This method can obtain the accurate velocity field of various kinds of froth bubbles flowing to the scraper in the flotation cells, even including the bubbles with serious collapse and heavy deformation. The accuracy of the subblock registration is evaluated by a deformation model. After a long period of observation in a bauxite flotation plant, the relationship between the froth flow velocity and the production performance indices is analyzed and discussed. Finally, a kind of conclusive operation advice based on the relationship between the froth velocity and the flotation performance is established. The velocity measurement and the operation guidelines for the flotation operation and automatic control lay a foundation for the establishment of a flotation optimal control system based on machine vision monitoring.