Froth Characteristics Research Articles

Working condition perception for froth flotation based on NSCT multiscale features

Visual features at the froth surface of a flotation cell are closely related to the process condition and performance. Accurate identification of flotation conditions is crucial. However, the multi-scale properties of froth images are not all extracted based on existing perception methods. Considering that multi-scale frequency domain analysis can obtain more informative statistical froth features, a new working condition recognition based on nonsubsampled contourlet transform (NSCT) multiscale features is proposed and successfully validated by industrial froth images taken under different process conditions. NSCT was used to enhance the froth image, including the decomposition and reconstruction, contrast-limited adaptive histogram equalization (CLAHE), and multi-scale features of the enhanced image are extracted and analyzed. The fuzzy binarization method is adopted for extracting the morphological feature. Texture feature parameters are extracted from other high-frequency images. The particle swarm optimization support vector machine is used to recognize the working condition. The results indicate that the proposed algorithms, in particular the multiscale features classification based on NSCT, have the highest classification accuracy (93.33 %), and can accurately and reliably identify the working condition in the actual froth images.

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.

Prediction of Sulfur Removal from Iron Concentrate Using Column Flotation Froth Features: Comparison of k-Means Clustering, Regression, Backpropagation Neural Network, and Convolutional Neural Network

Froth feature extraction plays a significant role in the monitoring and control of the flotation process. Image-based soft sensors have received a great deal of interest in the flotation process due to their low-cost and non-intrusive properties. This study proposes data-driven soft sensor models based on froth images to predict the key performance indicators of the flotation process. The ability of multiple linear regression (MLR), the backpropagation neural network (BPNN), the k-means clustering algorithm, and the convolutional neural network (CNN) to predict the amount of sulfur removal from iron ore concentrate in the column flotation process was examined. A total of 99 experimental results were used to develop the predictive models. Extracted froth features including color, bubble shape and size, texture, stability, and velocity were used to train the traditional predictive models, whereas in the CNN model the froth images were directly fed into the model. The results comparison indicated that the three-layered feedforward NN model (17-10-1 topology) and CNN model provided better predictions than the MLR and k-means algorithm. The BPNN model displayed a correlation coefficient of 0.97 and a root mean square error of 4.84% between the actual data and network output for both training and the testing datasets. The error percentages of the CNN, BPNN, MLR and k-means models were 10, 11, 15 and 18%, respectively. This study can become a key technical support for the application of intelligent models in the control of the operational variables for the flotation process used to desulfurize iron concentrate.

Spectroscopic-Based Prediction of Milk Foam Properties for Barista Applications

The important quality parameters of cow’s milk for barista applications are frothability and foam stability. In the past, quality assessment was very time-consuming and could only be carried out after milk treatment had been completed. Since spectroscopy is already established in dairies, it could be advantageous to develop a spectrometer-based measurement method for quality control for barista applications. By integrating online spectroscopy to the processing of UHT (ultra-high temperature processing) milk before filling, it can be checked whether the currently processed product is suitable for barista applications. To test this hypothesis, a feasibility study was conducted. For this purpose, seasonal UHT whole milk samples were measured every 2 months over a period of more than 1 year, resulting in a total of 269 milk samples that were foamed. Samples were frothed using a self-designed laboratory frother. Frothability at the beginning and foam loss after 15 min describe the frothing characteristics of the milk and are predicted from the spectra. Near-infrared, Raman, and fluorescence spectra were recorded from each milk sample. These spectra were preprocessed using 15 different mathematical methods. For each spectrometer, 85% of the resulting spectral dataset was analyzed using partial least squares (PLS) regression and nine different variable selection (VS) algorithms. Using the remaining 15% of the spectral dataset, a prediction error was determined for each model and used to compare the models. Using spectroscopy and PLS modeling, the best results show a prediction error for milk frothability of 3% and foam stability of 2%.

An unsupervised method for extracting semantic features of flotation froth images

• A new network structure maps the froth images data space to the latent semantic space. • The rich semantic knowledge of froth images can be automatically discovered. • The semantics can be visually interpreted by manipulating the froth image features. • The feature extraction method uses the unlabelled froth images effectively. • The extracted physical features perform well in flotation circuit monitoring. The froth feature extraction plays an important role in flotation circuit monitoring. Given the low efficiency of hand-crafted features and the poor interpretability of high-dimensional features extracted by convolutional neural networks, an unsupervised method for extracting human-understandable semantic features of flotation froth images is proposed in this paper. First, based on the combination of generative adversarial networks and autoencoder, we design a new network structure that maps the froth images data space to the latent semantic space. Then through network training with the historical froth image data, a matrix with rich latent semantics is constructed. Finally, the semantic features of froth images can be automatically extracted by decomposing the constructed matrix. As demonstrated in the industrial experiment, the extracted semantic features can not only be visually interpreted but also can be effectively used in flotation condition recognition and grade prediction. This is the first report that generative adversarial networks can be used to extract froth image features and improve the semantic interpretability of features.

Comparison of online and offline pulp sensor metrics in an industrial setting

Pulp-phase dynamics strongly impact flotation performance, yet flotation control and monitoring are usually limited to surface level froth characteristics. An online pulp-phase sensor promises a better understanding of flotation process dynamics and performance. This utility needs to be demonstrated through field trials with structured experimental design and testing under representative conditions. A three-factor Box-Behnken design was implemented to test airflow, pulp level, and frother reagent addition on pulp-phase measurements. The correlation of online pulp-phase measurements to offline pulp sensor measurements is analysed and discussed.

A new froth image classification method based on the MRMR-SSGMM hybrid model for recognition of reagent dosage condition in the coal flotation process.

Intelligent separation is a core technology in the transformation, upgradation, and high-quality development of coal. Realising the intelligent recognition and accurate classification of coal flotation froth is a key technology of intelligent separation. At present, the coal flotation process relies on artificial recognition of froth features for adjusting the reagent dosage. However, owing to the low accuracy and subjectivity of artificial recognition, some problems arise, such as reagent wastage and unqualified product quality. Thus, this paper proposes a new froth image classification method based on the maximal-relevance-minimal-redundancy (MR MR)-semi-supervised Gaussian mixture model (SSGMM) hybrid model for recognition of reagent dosage condition in the coal flotation process. First, the features of morphology, colour, and texture are extracted, and the optimal froth image features are screened out using the maximal-relevance-minimal-redundancy (MRMR) feature selection algorithm based on class information. Second, the traditional GMM clusterer is improved, called SSGMM, by introducing a small number of marked samples, the traditional GMM’ problems of unclear training goals, invisible clustering results, and artificially judged clustering results are solved. Then a new hybrid classification model is proposed by combining the MRMR with the modified GMM (SSGMM) which can be named as (MRMR - SSGMM). The optimal froth image features are screened by MRMR to provide the SSGMM classifier. In the process of training and learning the feature samples, using the marked feature samples of froth images to guide the unmarked feature samples. The information of marked feature samples of froth images is mapped to the unmarked feature samples, the classification of the froth images were realised. Finally, the accuracy of the SSGMM classifier is used as the evaluation criterion for the screened features by MRMR. By automatically executing the entire learning process to find the best number of froth image features and the optimal image features, so that the classifier achieves the maximum classification accuracy. Experimental results show that the proposed classification method achieves the best results in accuracy and time, compared with other benchmark classification methods. Application results show that the method can provide reliable guidance for the adjustment of the reagent dosage, realize the accurate and timely control of the reagent dosage, reduce the consumption of the reagent and the incidence of production accidents, and stabilize the product quality in the coal flotation production process.

Froth image clustering with feature semi-supervision through selection and label information

Accurate classification and recognition of coal flotation froth is one of the key technologies for intelligent coal separation. At present, the coal flotation process relies on artificial recognition of froth features for adjusting the reagent dosage, which cannot realize the optimal control of the quality of the clean coal product and the cost of the reagents. Therefore, in this paper, it is proposed a method of froth image clustering with feature semi-supervision through selection and label information. It is mainly divided into two stages: offline clustering and online recognition. The offline stage is to preprocess the froth image under various reagent conditions, extract the morphology, colour and texture features, and select the multi-dimensional optimal froth image features. A small number of marked samples are introduced to optimize the Gaussian mixture model. The selected optimal features are integrated into the optimized Gaussian mixture model to construct a froth image clusterer with multi-dimensional optimal features and class labels. In the online stage, the real-time froth image features are input clusterer and compared with the cluster feature samples to identify the current reagents conditions, which is used as feedback information to guide the abnormal reagent conditions during the production process. The effect of the amount of supervision information and the quality of feature on clustering results is analyzed and compared through experiments. The application results show that this method can provide key technical support for the accurate control of the dosage of reagents and the quality of clean coal product in the coal flotation production process, reduce the cost of reagents and the number of production accidents, improve the economic benefits, and promote the development of coal flotation intelligence to a higher level.

Grouped Time Series Networks for Grade Monitoring of Zinc Tailings With Multisource Features

Accurate grade monitoring is an important task in froth flotation. Current grade monitoring methods focus on the visual froth features from an individual flotation cell. As the froth flotation is a long process industry, the multisource features from different flotation cells can further improve the accuracy of grade monitoring. However, the multisource features are from different measurement sources and locations, and they have varied dynamic characteristics for grade monitoring. Therefore, we propose a grouped time series network (GTSN) with multisource features for grade monitoring of zinc tailings in this article. First, we group the multisource features by their additional measurement properties with self-clustering algorithm. Next, we send the grouped features into different time series subnetworks with varied dynamic characteristics and extract the feature vector for each grouped feature. After that, we integrate these feature vectors to represent the tailings grade. Especially, to minimize the grade prediction errors by each individual grouped feature and the integrated feature, we consider multitask learning in the model training. Finally, we implement a case study in a real zinc froth flotation process. Compared with the recurrent neural network (RNN)-based models using the multisource features, the averages of mean absolute percentage error (MAPE) and root-mean-squared error (RMSE) of the proposed GTSN-based models decrease by about 2.93% and 6.21%, respectively, and the average of R-squared (R2) increases by about 4.73%.

Hyperspectral Characteristics of Oil Sand, Part 1: Prediction of Processability and Froth Quality from Measurements of Ore

This study is the first of two companion papers using hyperspectral data to generate predictive models of oil sand ore and froth characteristics as a potential new means for process control. In Alberta, Canada, shallow oil sands deposits are accessed by surface mining and crushed ore is transported to a processing plant for extraction of bitumen using flotation processes. The ore displays considerable variability in clay, bitumen, and fines which affects their behavior in flotation units. Using oil sand ore spanning a range of bitumen and fines characteristics, flotation experiments were performed to generate froth in a batch extractor to determine ore processability (e.g., separation performance) and froth characteristics (color, bitumen, solids). From hyperspectral observations of ore, models can predict the %bitumen content and %fines (particle passing at 44 and 3.9 µm) of ore but the models with highest r2 (>0.96) predict the solids/bitumen of froth and the processability of ore. Spectral observations collected on ore upstream of the separation vessels could therefore offer a first order assessment of froth quality for an ore blend before the ore enters the plant. These models could also potentially be used to monitor and control the performance of the blending process as another means to control the performance of the flotation process.

Hyperspectral Characteristics of Oil Sand, Part 2: Prediction of Froth Characteristics from Measurements of Froth

This is the second part of a study of predictive models of oil sand ore and froth characteristics using infrared hyperspectral data as a potential new means for process control. In Alberta, Canada, bitumen in shallow oil sands deposits is accessed by surface mining and then extracted from ore using flotation processes. The ore displays variability in the clay, bitumen, and fines content and this variability affects the separability and product quality in flotation units. Flotation experiments were performed on a set of ore samples of different types to generate froth and determine the ore processability (e.g., separation performance) and froth characteristics (bitumen and solids content, fines distribution). We show that point spectra and spectral imagery of good quality can be acquired rapidly (<1 s and <15 s, respectively) and these capture spectral features diagnostic of bitumen and solids. Ensuing models can predict the solids/bitumen (r2 = 0.88) and the %fines and ultrafines (particle passing at 3.9 and 0.5 µm) content of froth (r2 = 0.8 and 0.9, respectively). The latter model could be used to reject froth with a high solids content. Alternately, the strength of the illite-smectite absorption observed in froth could be used to retain all the samples above a pre-defined processability. Given that point spectrometers can currently be acquired for less than half the cost of an imaging system, we recommend the use of the former for future trials in operating environments.

R-K algorithm: A novel Dynamic Feature Matching Method of flotation froth

Froth flotation is a common process used for extracting a desired mineral from its ore. The dynamic characteristics extraction towards froth flotation can better identify the collapse and fragmentation. According to the characteristics of continuous movement of flotation froth, a new flotation froth feature matching method is proposed, which based on Kalman filtering and RANSAC algorithm, called R-K matching algorithm. And then, combining the R-K matching algorithm and SURF (fast robust scale invariant feature extraction algorithm) to extract the dynamic characteristics of flotation froth. Finally, the velocity and the entropy of the flotation froth are calculated to confirm the effectiveness and the practicability. The simulation results from the industrial experimental data show that the method can extract more feature matching pairs than the existing methods. So, it can obtain more accurate dynamic information on flotation froth in the changed state.

Flotation froth feature analysis using computer vision technology

The possibility of machine vision application in the field of flotation efficiency evaluation was studied. Algorithm for froth image analysis was developed with aim of obtaining bubble’s size distribution. Algorithm consists of two parts: image processing and object detection. Algorithm’s work was verified on the sulfide flotation froth. As result, mathematical correlations for air flow rate, mean bubble diameter and surface area bubble flux were established.

Fault detection in flotation processes based on deep learning and support vector machine

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.

Shape-weighted bubble size distribution based reagent predictive control for the antimony flotation process

Antimony flotation is a complicated industrial process with an unknown system structure. Manual manipulation is still widely used by observing the froth appearance, which relies on operators’ experience. Therefore, this paper proposes a reagent predictive control strategy for the antimony flotation process based on machine vision, which is an optional replacement of manual control. Froth image is a good indicator to reflect the working conditions of the process. A shape-weighted bubble size distribution (SWBSD) is developed to characterize the froth image feature. The SWBSD combines the bubble size and bubble shape, which differs from the separate use of froth features. Since lots of the froth images can be obtained, a random selection of an image from a froth video as the indicator of the working conditions is not advisable. A typical froth image selection method is proposed to choose the froth image which can best characterize the current working conditions. Due to the unknown system model, multi-output least square support vector regressor (LS-SVR) is used to predict the future image feature according to the current image feature and reagent dosages. Based on the above methods, predictive control technique is employed to calculate the optimal control inputs of the reagents. Simulations using the real-world production data verify the effectiveness of the proposed control strategy. In further, industrial experiments in the antimony flotation plant of China demonstrate that our control strategy improved the tracking performance and decreased the tailing grade, compared with the manual manipulation.

On-Line Froth Depth Estimation for Sulphur Flotation Process With Multiple Working Conditions

This paper proposed a non-contact froth depth estimation approach based on machine vision. Firstly, the froth images collected from sulphur flotation process under different working conditions are processed to obtain froth features. Secondly, the working condition recognition model based on froth features of flotation process is built to recognize working conditions. Moreover, the key froth features are selected by correlation analysis for various operating modes, which are the inputs of the estimation models for froth depth. Finally, the estimation models of froth depth for different working conditions are established based on the low dimensional process features, which are composed of the deep froth image features under current working condition, and crucial process operating parameters, e.g., flow rates of air, tailing and feeding. Experimental results demonstrate that the proposed method can significantly improve the measuring accuracy, compared with traditional measuring method using physical liquid level meter.

Froth properties and entrainment in lab-scale flotation: A case of carbonaceous sedimentary phosphate ore

In flotation, the froth characteristics strongly influence the separation process as they are linked to water recovery, bubble size, entrainment of gangue particles, flotation rate constants and finally grade and recovery. In the case of a high-grade apatite ore with a high mass pull in lab-scale flotation, significant changes in pulp and froth properties occur, such that the froth stability decreases with increasing flotation time. These changes can be related to different particle and reagent concentrations. We describe the change of entrainment in a rich apatite ore batch flotation with time more precisely by measuring froth properties using a Dynamic Froth Analyzer (DFA). It is concluded that the degree of entrainment is not only dependent on particle size but also the pulp density due to its effect on particle settling and also froth properties in varying resistance to drainage. Through a combination of time-resolved dynamic froth analysis and automated mineralogy, we identify the dynamic effects governing in the froth and compare the entrainment results with existing models. Furthermore, our analyses offer novel support for the extension of the common understanding of the entrainment phenomena.

The effect of pulp bubble size on the dynamic froth stability measurement

The measurement of dynamic and static froth stability has found widespread application in the characterisation of froth performance. However, little attention has been given to scale parameters in the performance of these measurements. This study focussed on the effect of pulp bubble size on froth stability. Different pulp bubble sizes were generated in a non-overflowing column and time-dependent froth characteristics such as froth height, side-of-froth and top-of-froth bubble size were measured. An inverse relationship was found between apparent, measured froth stability and pulp bubble size. It was also shown that top-of-froth bubble size is independent of pulp bubble size. A normalised froth height parameter is used to generate a bubble growth curve which is independent of pulp bubble size. It is proposed that this type of analysis may present an avenue into a truly scale-independent analysis of froth stability.

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.