Froth Image Research Articles

A Convolutional Neural Network for Classification of Froth Mobility in an Industrial Flotation Cell

ABSTRACT Froth flotation is widely used in the resource industry as a particle separation process. The performance of the flotation process is significantly affected by the mobility of the froth phase. Despite its importance, little work has been done to develop a simple and robust method for indicating froth mobility. In the present study, a simple method to monitor froth mobility was developed using a readily available web-camera to take images and a convolutional neural network (CNN) model classifying the images mainly based on the degree of motion blur. The CNN model was trained with a newly built froth image dataset, comprising froth images taken near the overflowing lip of an industrial flotation cell at a wide range of operating conditions using the web-camera. It was found that the trained model could correctly classify 98% of the froth images into one of three categories: low, medium, and high mobility. The froth mobility determined by the trained CNN model was in good agreement with the one analyzed with a commercial software. A potential application of the present method for indicating flotation performance was illustrated.

ASM-VoFDehaze: a real-time defogging method of zinc froth image

When the ambient temperature is low, a large amount of water mist and dust will inevitably appear around the zinc flotation cell, forming haze, which seriously affects the extraction of flotation froth image features. General defogging methods of natural image are difficult to obtain satisfactory results for such industrial haze image. Therefore, we propose a real-time defogging method based on ASM-VoFD (Atmospheric Scattering Model and the Variable-order Fractional Differential). First, the dark pixel ratio is used to detect fog in froth image, which solves the redundant calculation caused by unnecessary defogging operations. Second, the linear transformation of the atmospheric scattering model is used to calculate the initial transmission map, and the gaussian filter is used to optimize the initial transmittance, and the haze-free image is restored with atmospheric light estimation. Finally, a variable order fractional differential operator is used to enhance the edges and texture details of the restored froth image, which solves the problems of blurred edges and low contrast. The experiments show that the algorithm has a good defogging effect on the industrial images, enhance the edges of the image, and can be effectively implemented in O(N) time to meet the application requirements of real-time flotation monitoring.

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.

Spatial-temporal joint zinc flotation froth image denoising based on bubble dynamic features

The environment of the flotation plant is harsh, and the noise pollution of the collected froth images is severe. It is challenging to obtain real-time and high-quality froth images by common denoising methods. A spatial-temporal joint denoising method based on bubble dynamic features is proposed. This method first analyses the dynamic features of the bubble and detects the stability of each reference image sub-blocks; then selects the corresponding filtering to denoising according to the different states of the froth sub-blocks; and finally obtains a weighted average result of temporal filtering and spatial filtering. This method uses a modified and noise-robust cross-correlation method to estimate the sub-blocks' motion, which improves the denoising performance of time-domain filtering. The experiments show that the method can obtain a high signal-to-noise ratio and strong structural similarity result for non-static background images. It has also been well verified in the application of zinc flotation froth images.

Operating Condition Recognition in Zinc Flotation Using Statistic and Temporal Correlation Features

Accurate recognition of operating conditions helps to correctly control froth flotation. Most previous recognition methods mainly focus on the statistic feature but ignore the temporal information in the dynamic and changing flotation process. Actually, the temporal changing trend of froth appearance can reflect the change in flotation performance. Besides, the bubble size distribution (BSD) is a representative visual feature for characterizing froth appearance. Therefore, we propose to exploit the statistics and temporal correlation of BSD for condition recognition in this paper. First, to sufficiently characterize the statistics of bubble sizes about the initial state of the froth video, we sample multiple froth images from a short video clip at the beginning of the video, and then use a cumulative distribution function to describe the BSD in these sampled images, which is regarded as the cumulative distribution statistic (CDS). Meanwhile, to obtain the temporal change trend of BSDs from the initial to the last moment of the froth video, we sample multiple sequential froth images from the whole video and use the cumulative distribution function to describe the BSD of individual image, and then the BSD sequences are input into the bi-directional long short-term memory to extract their temporal correlation, which is regarded as the cumulative distribution temporal correlation (CDTC). Additionally, we integrate texture and velocity features with our constructed CDS and CDTC features via a joint learning network to recognize operating conditions. Extensive experiments demonstrate that the proposed model using CDS and CDTC is more effective than other models with BSD features. Besides, compared to the models using the single CDS and CDTC, the accuracy of the proposed model is increased by 8.39% and 2.61%, respectively.

A k-Shot Learning Approach to Recognition of Flotation Froth Conditions with Convolutional Neural Networks

In this paper it is shown that operational regimes in flotation plants can be identified by machine learning models, based on the availability of just a few tens of froth images of each regime. This is accomplished through the generation of synthetic images that can be used to train machine learning models used in froth pattern identification. The study was based on a small set of images from a platinum group metals plant. Synthetic images were generated with two convolutional neural networks. Features extracted from synthetic and real images with local binary patterns and AlexNet were indistinguishable from each other. In addition, features from a small set of 30 synthetic images that were used as predictors in a random forest model performed similarly to the same features extracted from real images, even from considerably larger data set. This suggests that the use of synthetic froth images generated by deep learning models can serve as the basis for few shot learning models.

Deep learning-based ash content prediction of coal flotation concentrate using convolutional neural network

Convolutional neural networks, as the current state-of-the-art in image classification, are regarded as a promising way for flotation soft sensors based on froth images. This paper proposes a flotation soft sensor solution that predicts the concentrate ash content of coal flotation by using froth images and convolutional neural network architecture. A froth image dataset from the coal flotation site was divided into seven interval classes based on concentrate ash content, and data augmentation was used for this dataset. Then, several state-of-the-art convolutional neural networks (AlexNet, VGG_16, VGG_19, ResNet_18, ResNet_34, ResNet_50, ResNet_101) are trained to classifying the froth images with different concentrate ash content interval (integer ± 0.5). The classification performance of each model, the relationship between model performance and hyperparameters, and the abstract pixel feature of the best model are examined and visualized. The highest classification accuracy (97.1%) is obtained by the ResNet_101 network after fine-tuning. CNN extracts the features into a multi-channel set of abstract pixel features (7 × 7) before entered into the fully-connected layer. The results show that the abstract pixel feature significantly outperformed the manually engineered features. Finally, it takes only 0.31 s for the model to classify a froth image, which indicates that the convolutional neural network has a good industrial performance.

An integrated multi-mode model of froth flotation cell based on fusion of flotation kinetics and froth image features

Froth flotation is the most commonly used technology in minerals separation and beneficiation. A comprehensive and precise flotation model is the foundation for optimizing the recovery rate and grade of valuable minerals. In this paper, a phenomenological model is built to describe the underlying physicochemical principles of the flotation process. To account for the influence factors not explicitly included in the phenomenological model, a data-driven model based on Long Short-Term Memory (LSTM) is proposed for error compensation by learning from the sequentially collected froth images. Considering the time-varying nature of flotation dynamics, a multi-mode modeling framework is established in the context of comprehensive state space (CSS) description system. In the framework, the dynamics of the flotation cell is described using a twofold integration. For each working condition, the phenomenological model and the compensation model are integrated to describe the process dynamics. The process dynamics is formulated as an integration of the sub-models of each working condition. In order to follow the evolution of working condition, the weights of the sub-models vary with the location of the working point in the CSS, which are calculated using a SAE(Stacked Auto Encoder)-KD(K-dimensional tree)-TAN(Tree Augmented Naive Bayes) approach. The proposed approach utilizes both kinetics knowledge and froth image features, and can be adapted to the variation of working conditions. A case study illustrates the stability and accuracy of the proposed approach.

Statement of Retraction

This article refers to:RETRACTION ARTICLE: Correlation between Average Gray Value (AGV) of coal froth image with its ash and vitrinite content

Froth image feature engineering-based prediction method for concentrate ash content of coal flotation

Machine vision and machine learning have been researched widely in froth flotation and the technology continues to benefit from advances in computer technology. The feature engineering leads to a predicted resistance in the machine learning pipelines, especially in coal flotation. This study sought to examine the performance of feature engineering of coal flotation froth image on ash content prediction with an industrial dataset. In order to evaluate the practical use in industry, the morphoscopic (3 features), statistical (gray levels histogram (5 features), gray level co-occurrence matrix (24 features), statistical modeling (48 features)) and color spaces (18 features) are used to prepare feature engineering. Correlation matrix are used to investigate the relationship between features and ash content. The support vector regression is used to predict ash content. The evaluation of the model performance shows that the principal component analysis can effectively improve the accuracy. When the feature dimension is reduced to 14 by the principal component analysis, the optimal RMSE is 0.6331, the R2 value is 0.78. The feature engineering of coal flotation froth image in this paper can make a good prediction of the coal flotation concentrate ash content. Furthermore, the results can be used as the theoretical basis for the intelligent construction of flotation.

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.

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.

A dynamic flotation model to infer process characteristics from online measurements

A dynamic flotation model incorporating fundamental and phenomenological relationships, information from froth images and steady-state models is described. Model outputs correspond with online measurements commonly available on flotation circuits, and the model parameters are estimated from industrial data. Simulation results are presented, highlighting important non-linearities that need to be taken into account for optimal flotation operation. Observability and controllability analyses are performed, proving that key flotation parameters can theoretically be estimated from online process measurements, and that the set of modelled inputs can control all the model outputs. This model can be used in advanced model-based control and optimisation applications. The ability to estimate key flotation parameters opens up opportunities for improved optimisation of operating variables such as aeration rates, froth depth and the reagent recipe.

Soft sensor of flotation froth grade classification based on hybrid deep neural network

ABSTRACT In recent years, the technology of deep learning has made great achievements in the field of machine learning. In this study, with the help of the transfer learning method, a kind of soft sensor is designed for the classification of iron ore tailings grade. Firstly, a sample database of froth images of flotation tailings was established. Secondly, the three most reliable models are determined after comparing the accuracy of 13 deep neural network models applied in the flotation froth image. A more accurate hybrid deep neural network model is established, with an accuracy of 97%. Finally, a software system is designed and developed, which can operate stably in the flotation plant. The experimental results show the effectiveness of the proposed hybrid deep neural network in the field of iron ore froth flotation.

Illumination-Invariant Flotation Froth Color Measuring via Wasserstein Distance-Based CycleGAN With Structure-Preserving Constraint.

Froth color can be referred to as a direct and instant indicator to the key flotation production index, for example, concentrate grade. However, it is intractable to measure the froth color robustly due to the adverse interference of time-varying and uncontrollable multisource illuminations in the flotation process monitoring. In this article, we proposed an illumination-invariant froth color measuring method by solving a structure-preserved image-to-image color translation task via an introduced Wasserstein distance-based structure-preserving CycleGAN, called WDSPCGAN. WDSPCGAN is comprised of two generative adversarial networks (GANs), which have their own discriminators but share two generators, using an improved U-net-like full convolution network to conduct the spatial structure-preserved color translation. By an adversarial game training of the two GANs, WDSPCGAN can map the color domain of froth images under any illumination to that of the referencing illumination, while maintaining the structure and texture invariance. The proposed method is validated on two public benchmark color constancy datasets and applied to an industrial bauxite flotation process. The experimental results show that WDSPCGAN can achieve illumination-invariant color features of froth images under various unknown lighting conditions while keeping their structures and textures unchanged. In addition, WDSPCGAN can be updated online to ensure its adaptability to any operational conditions. Hence, it has the potential for being popularized to the online monitoring of the flotation concentrate grade.

LTGH: A Dynamic Texture Feature for Working Condition Recognition in the Froth Flotation

Texture feature of the froth image is widely used in the working condition recognition of froth flotation. However, due to the complexity of the froth image, the current texture features vary greatly and are difficult to identify the work condition accurately. Therefore, we propose a dynamic texture feature named LBP on the TOP and GLCM Histograms (LTGH) which integrates the local binary patterns (LBPs) and gray-level co-occurrence matrix (GLCM) histograms on the three orthogonal planes (TOP). First, we use the rotation invariant LBPs to enhance rotation invariance and illumination robustness. Then, we implement the TOP on the enhanced texture feature map to generate the multiple dimensional enhanced feature maps. After that, we calculate the GLCM and supplementary features (SFs) on the multiple dimensional enhanced feature map. Finally, we integrate the histogram of the GLCM and SFs to discriminate the texture feature. The LTGH feature considers the froth structures both in the macrolevel and microlevel and captures the temporal information between the froth images. Experiments have demonstrated the effectiveness and stability of the proposed texture feature for work condition recognition in froth flotation. Compared with other traditional texture features, the accuracy of the LTGH feature has been increased by at least 7.76%.

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%.

Spatial-temporal joint zinc flotation froth image denoising based on bubble dynamic features

Spatial-temporal joint zinc flotation froth image denoising based on bubble dynamic features

Visual perception-based fault diagnosis in froth flotation using statistical approaches

Froth flotation is an important mineral concentration technique. Faulty conditions in flotation processes may cause the huge waste of mineral resources and reagents, and consequently, may lead to deterioration in terms of benefits of flotation plants. In this paper, we propose a computer vision-aided fault detection and diagnosis approach for froth flotation. Specifically, a joint Gabor texture feature based on the Copula model is designed to describe froth images; a rejection sampling technique is developed to generate training sets from the quality distribution of real flotation products, and then an isolation forest-based fault detector is learned; and a fault diagnosis model based on spline regression is developed for root cause identification. Simulation experiments conducted on the historical industry data show that the proposed strategy has better performance than the alternative methods. Thereafter, the entire framework has been tested on a lead-zinc flotation plant in China. Experimental results have demonstrated the effectiveness of the proposed method.