Coal Sorting Research Articles

Rapid multispectral image identification of coal and gangue based on super-resolution reconstruction

Accurate coal and gangue separation is crucial for efficient coal utilization. Multispectral imaging (MSI) offers a promising approach but often suffers from limited resolution, hindering accurate identification. This study proposes, a novel method, to our knowledge, combining super-resolution (SR) reconstruction and machine learning to enhance coal and gangue identification in MSI. A spectral attention mechanism and an enhanced multi-scale residual network with GAN (SAM-EMSR-GAN) were developed and evaluated alongside four established SR methods: SRCNN, VDSR, ESRGAN, and DRMSFFN. MSI images of 300 coal and 300 gangue samples were reconstructed, using each method to compare their performance. SAM-EMSR-GAN achieved superior reconstruction, attaining the highest structural similarity index (SSIM) of 0.906 and peak signal-to-noise ratio (PSNR) of 32.97 at 4× magnification. The study further investigated the combination of the SR method with seven widely used classification models: CatBoost, random forest (RF), support vector machine (SVM), least squares support vector machines (LSSVMs), eXtreme gradient boosting (XGBoost), ResNet50, and ResNet101. CatBoost consistently delivered the highest classification accuracy across all SR methods, reaching 97.32% accuracy at 959.37 nm when paired with SAM-EMSR-GAN. Independent validation using a separate dataset confirmed the robustness of this approach, achieving a 92.49% accuracy. These findings demonstrate the potential of combining SAM-EMSR-GAN and CatBoost for accurate and efficient coal and gangue identification, paving the way for intelligent and automated coal sorting technologies.

Classification of coal gangue and identification of coal type based on first-derivative of mid-infrared spectrum

Efficiently sorting coal gangue and identifying coal types are vital operations in coal preparation, yet they are traditionally resource-consuming, labor-intensive, and potentially hazardous. This work puts forward an straightforward method employing mid-infrared spectroscopy with first derivative spectrum to address these issues. The proposed technique focuses on the delineation and enhancement of characteristic spectra to detect subtle differences among samples. The method utilizes just a few characteristic spectra of 3740–3700 cm−1, 1790–1750 cm−1, 1615–1583 cm−1, 1580–1540 cm−1, 1550–1440 cm−1, 1270–1210 cm−1 and 867–854 cm−1 to achieve 100 % high-accuracy classification of coal gangue and identification of coal types with total 250 spectra, such as bituminite, anthracite, lignite, roof sandstone and gangue, without the need for secondary sample processing or the assistance of machine learning algorithms, simplifying the process considerably. Such a strategy not only significantly improves the efficiency of coal sorting but also endorses real-time on-site detection. It offers a theoretical foundation for advanced coal separation technology and its implementation in real-world mining operations.

Numerical simulation and experiment of coal particles separation in flexible air chamber jig

Flexible air chamber jig is a new type of coal sorting and processing equipment with broad application prospects. The separation of coal particles in the jig mainly depended on the gas working cycle, liquid level height and particles looseness. This paper discusses the separation of clean coal and middling coal in this jig with simulation and experimental methods. Numerical simulation of jigger separation process was realized, and the effects of inlet, expansion and exhaust proportion on the water movement and particle separation were investigated based on the liquid level height, bed looseness and percentage of particles. It was verified by the water level detection experiments. The results showed that the model was accurate and the experimental results were consistent with the simulation. The maximum discrepancy between the water levels in the experiment and the simulation was less than 5%, confirming the accuracy of the VOF-DEM (Volume of Fluid-Discrete Element Method) model. The liquid level was significantly affected by the gas working cycles, while the bed looseness was mainly affected by the intake proportion. Appropriate intake and exhaust proportions increased the proportion of particles with different densities. A reasonable gas working period proportion for jigging separation: intake 24%, expansion 27%, and exhaust 24%. In this condition, the proportions of Zone 1′s clean coal and Zone 2′s medium coal is 81.16% and 94.18%, respectively.

A high accuracy detection method for coal and gangue with S3DD-YOLOv8

ABSTRACT In the process of coal sorting, the similarity in color and shape between coal and gangue makes the sorting process more difficult. This paper proposes a new method for detecting coal gangue based on an improved version of YOLOv8 (You Only Look Once). First, to enhance the recognition of different types, the input images are converted from Red-Green-Blue (RGB) channel to Hue-Saturation-Value (HSV) channel. Then, a Squeeze-and-Excitation (SE) attention module is added to the first layer to increase the robustness of the network. Next, a 3D dilated convolutional module is added after the SE attention module to improve feature detection. Furthermore, the SE attention mechanism module has been integrated with the existing C2f module. Finally, the last 2D convolution in the backbone is replaced with a deformable convolution (DCN). In this paper, we call new model S3DD-YOLOv8. The experiment on self-built coal and gangue data sets showed that the enhanced YOLOv8n has significant advantages in the detection. The Precision and Recall have been increased by 11.95% and 7.769%, and the mAP50 has been improved to 0.988. Our algorithm can effectively detect coal and gangue that are stacked together in various quantities and sizes under various lighting conditions, and demonstrates a certain level of robustness and practicality.

Сортировка угля на разрезе "Майкубен"

The main indicators of coal quality were considered and a more effective sorting method was proposed. The characteristics of coal and technologies developed in the field are presented. The efficiency of coal sorting by granulometric composition for obtaining high-quality coal is considered, methods of operational planning and optimization of daily coal production in the conditions of the Maikuben mine are developed, taking into account the requirements of quality, economic efficiency and technical capability. It is proposed to introduce a sorting plant at the transshipment point of the Maikuben mine. The entire path of coal from the deposit to the final consumer is described. In this work, the following goals were set: to investigate the sorting of coal in the conditions of the Maikuben mine and to determine a more efficient way of sorting. To achieve these results, the following were used: analysis of geological and scientific works on exploration, sorting and mining of coal.

Detection of Coal and Gangue Based on Improved YOLOv8.

To address the lightweight and real-time issues of coal sorting detection, an intelligent detection method for coal and gangue, Our-v8, was proposed based on improved YOLOv8. Images of coal and gangue with different densities under two diverse lighting environments were collected. Then the Laplacian image enhancement algorithm was proposed to improve the training data quality, sharpening contours and boosting feature extraction; the CBAM attention mechanism was introduced to prioritize crucial features, enhancing more accurate feature extraction ability; and the EIOU loss function was added to refine box regression, further improving detection accuracy. The experimental results showed that Our-v8 for detecting coal and gangue in a halogen lamp lighting environment achieved excellent performance with a mean average precision (mAP) of 99.5%, was lightweight with FLOPs of 29.7, Param of 12.8, and a size of only 22.1 MB. Additionally, Our-v8 can provide accurate location information for coal and gangue, making it ideal for real-time coal sorting applications.

Autonomous Multiple Tramp Materials Detection in Raw Coal Using Single-Shot Feature Fusion Detector

In the coal mining process, various types of tramp materials will be mixed into the raw coal, which will affect the quality of the coal and endanger the normal operation of the equipment. Automatic detection of tramp materials objects is an important process and basis for efficient coal sorting. However, previous research has focused on the detection of gangue, ignoring the detection of other types of tramp materials, especially small targets. Because the initial Single Shot MultiBox Detector (SSD) lacks the efficient use of feature maps, it is difficult to obtain stable results when detecting tramp materials objects. In this article, an object detection algorithm based on feature fusion and dense convolutional network is proposed, which is called tramp materials in raw coal single-shot detector (TMRC-SSD), to detect five types of tramp materials such as gangue, bolt, stick, iron sheet, and iron chain. In this algorithm, a modified DenseNet is first designed and a four-stage feature extractor is used to down-sample the feature map stably. After that, we use the dilation convolution and multi-branch structure to enrich the receptive field. Finally, in the feature fusion module, we designed cross-layer feature fusion and attention fusion modules to realize the semantic interaction of feature maps. The experiments show that the module we designed is effective. This method is better than the existing model. When the input image is 300 × 300 pixels, it can reach 96.12% MAP and 24FPS. Especially in the detection of small objects, the detection accuracy has increased by 4.1 to 95.57%. The experimental results show that this method can be applied to the actual detection of tramp materials objects in raw coal.

Design of speed control system for intelligent sorting conveyor belt of coal gangue

With the development of technology, the application of intelligent coal gangue sorting is more and more favored by coal mining enterprises. The coal gangue intelligent sorting system has higher requirements on the coal conveyor belt. The traditional transmission system has the problems of slow speed response, unstable operation, high energy consumption and jitter in the process of speed change. Using PLC, touch screen, frequency converter, RS-485, sensors and so on, the speed control and speed monitoring system of belt transport mechanism is constructed. By analyzing the error law of the system speed control and using Numpy system analysis and calculation, speed pre-compensation can be made. Then by controling speed precision through the PID and monitoring display through the time-speed curve, the real-time automation gives an alarm for abnormal speed situation. According to the speed requirement of the intelligent sorting system of coal gangue, the system can quickly reach the predetermined speed value, and effectively eliminate the shaking phenomenon in the process of changing speed. The system has strong universality, easy maintenance, and stable speed control, which is conducive to improving the reliability and efficiency of the intelligent sorting system for coal gangue and reduceing transmission mechanism wear caused by dithering.

Deep learning-based image classification for online multi-coal and multi-class sorting

Deep learning is an effective way to improve the classification accuracy of coal images for the machine vision-based coal sorting. However, the related research on deep learning-based mineral image classification has not systematically considered the models for multi-coal and multi-class sorting. Additionally, the universal CNNs model for multi-coal image classification has not been proposed. Given the above problems, combined with deep learning and transfer learning and based on VGG Net, Inception Net, and Res Net, this study builds four CNNs models with different depth and structure for multi-coal and multi-class image classification. Finally, we take anthracite, gas coal, coking coal as the research objects and propose a universal CNNs model suitable for multi-coal and multi-class sorting. Moreover, with the Channel Visualization map, Heatmap, Gard-CAM map, and Guided Backpropagation map, the operational processes of CNNs model in coal image recognition and classification are revealed, and the features that affect the classification weights are analyzed.

An Optimization Algorithm to Determine Apparent Power of Active Filter

The coal grading plants in Viet Nam extensively apply induction motors. Induction motors consume active and reactive power from the power supply systems. The reactive power flowing through the electrical network creates active power losses. The reactive power received from power utilities reduces the load power factor at the node where coal sorting plants are connected to the supply network. Frequency-controlled induction motors introduce distortions into the electrical network because they are electrical equipment with a nonlinear current-voltage characteristic. Non-sinusoidal current and voltage cause additional losses of active power in the electrical network and electrical equipment, thereby shortening its service life, reducing the reliability of operation, and causing economic damage. Active filters can solve these problems. The paper proposes an optimization algorithm for determining the apparent power of the active filter, which provides the load power factor and power quality indices corresponding to the regulatory documents. The algorithm is used to calculate the apparent power of the active filter for the coal grading plant owned by the Vietnamese company “Cua Ong-Vinacomin."

Assessment of coal sortability and washability using dual energy X-ray transmission system

ABSTRACT Sorting coal using x-ray transmission sensors has been explored since 1972 by Jenkinson et al. Coal sortability is assessed using washability derived from dual-energy X-Ray transmission (DE-XRT) system. Coal sorting is considered to be dry separation of coal that can be carried out before coal is send to the processing plant. It can act as deshaling/destoning process or it can also be used to selectively mine shallow coal seams to avoid overburden contamination hence dilution. There are a few commercial concepts in the coal industry which utilizes the XRT sensors to sort the coarse particle coal. In order to define final product quality in terms of ash as well the efficiency of any separation based on density such as yield, washability is used to determine the separation process parameter such as density of separation, e.g. specific gravity. Washability characteristics have been traditionally assessed using the float-sink (washability) tests. These analyses determine how much of coal can be separated from associated rock (mineral matter) in liquids of different densities. However, the test work requires a wet processing where organic liquids, referred to as heavy liquids are used. The test work is very time consuming as it requires significant amount of time to complete full washability for a wide spectrum of coal particles. To avoid using toxic chemicals and save time, the DE-XRT can easily become an alternative method to assess the washability of coarse coal before the coal is processed by sorting to establish separation parameters and obtain information about the yield of clean coal of desired quality in terms of ash content. In this project in order to assess effectiveness of DE-XRT for sorting and at the same time to derive the washability data for the coarse coal, the test work has been designed to test various lithotypes identified from coarse coal sample. As a result, the test work included classification of coal lithotypes (larger pieces of coal of certain petrographic composition), density measurement using both DE-XRT and float-sink tests and ash analysis. The results are compared to float-sink tests for coarse coal fractions obtained by proxy washability analysis derived from pycnometry. Similar to float-sink tests, the DE-XRT can estimate a relative density by measuring the attenuation of x-rays from two different energy levels. The paper explains the basics of the DE-XRT analysis and its data processing methods to determine the relative densities and how to derive washability curves and density of separation for coal sorting. The basic principle of dual-material decomposition is adopted from Dual-Energy CT in the medical industry where the sum of each vector provides a proportion of the two material.

A methodical approach and computer programs to determine the power of active harmonic filters

Poor power quality creates big problems. With the poor power quality, the service life of the equipment is reduced. In connection with the creation and development of intelligent electrical power systems and the digital economy, the requirements for the power quality are increasing. Active harmonic filters began to used to solve problem with the poor power quality. The paper presents a methodical approach and computer programs for determining the power of the active harmonic filter. The power supply system of the Vietnamese coal sorting plant is considered to develop the methodical approach. The results of measurements of the power quality indices and the results of calculating the parameters of the modes of the electrical network of the plant at the fundamental frequency were used. To process a large amount of measured information, the special computer program was developed. On the basis of the methodical approach, the results of measurements of the power quality indices and the computer complex “Stationary permissible optimal mode”, the algorithm and the computer program have been developed to calculate the power of the active harmonic filter. The power of the active harmonic filter for the coal sorting plant was determined with the help of this program.

Analysis of the influence of non-sinusoidal and unbalanced network modes on induction motors

The parameters of electrical network modes do not correspond the requirements GOST 32144-2013 of Russian and the National technical regulation of Vietnam. In real operating conditions in electrical networks in non-sinusoidal and unbalanced modes there are harmonic components of voltages and currents as well as voltages and currents of negative sequence. They cause additional losses of active power, which leads to additional heating and causes premature aging of the insulation, and as the result, the reduction in the service life of induction motors. Currently, we see that the process of formation of intelligent electrical power systems is underway. Systems for continuous monitoring of power quality indices and parameters of electrical systems modes are being developed. These systems can be supplemented with programs for calculating characteristics that issue the warning when the unfavorable influence of the parameters of non-sinusoidal and unbalanced modes is detected on various electrical equipment of both electrical power systems and consumers of electrical energy. The paper provides an overview of the characteristics used to analyze, assess and predict the influence of poor power quality associated with non-sinusoidal and unbalanced of currents and voltages on induction motors. A computer program was developed to calculate these characteristics. The program was used to study the influence of non-sinusoidal and unbalanced modes on the induction motors of the coal sorting plant of the Vietnamese company “Cua Ong-Vinacomin”.

Facultative-anaerobic microbial digestion of coal preparation waste and use of effluent solids to enhance plant growth in a sandy soil

Coal preparation solid waste, which is a major environmental issue for coal-producing areas in China, may be microbiologically digested and transformed into a product suitable as a soil amendment to increase soil organic matter content and prevent and enhance plant/crop growth. Coal preparation waste collected from a coal sorting plant in Inner Mongolia, China was digested in bioreactors inoculated with microbial enrichments prepared from activated sludge and cow manure. The effluent solids from the coal preparation waste bioreactors were analyzed for their suitability as organic soil amendments, which complied with China standards. Plant growth tests were conducted in sandy soil from a semi-arid region in Colorado, which was amended with the effluent solids. Kentucky bluegrass (Poa pratensis L.) and chives (Allium schoenoprasum) were used as the representative plants for the growth tests, where results indicated substantially higher yields of Kentucky bluegrass and chives for the sandy soils amended with the effluent solids when compared to a commercial organic fertilizer. The number and average length of Kentucky bluegrass shoots were 10 and 5.1 times higher, respectively, in soils amended with the effluent solids. Similarly, the number and average length of chives shoots were 10 and 1.7 times higher, respectively, in soils amended with the effluent solids. Overall, the microbial digestion of coal preparation waste for application as an organic soil amendment is a viable alternative and beneficial use of coal preparation solid waste.

Steeply Inclined Vibrational Screen in Coal Preparation at Coke Plants

A steeply inclined vibrational screen may be used to sort coal batch (moisture content 11.2%) with a high content of the ≤3 mm class (70.7%). The influence of the screen’s structural and dynamic parameters on its performance is investigated. On the basis of experiment design, industrial research is undertaken, and the results are statistically analyzed. The efficiency of screening, the clogging of the screening surface, and the enlargement of the target product are determined as a function of the inclination of the screening surface, its type, and the acceleration of the drum vibrations. The optimal design is a steeply inclined screen with a freely supported screening surface (50° inclination), when the acceleration of the drum vibrations is 33 m/s2. In that case, the efficiency of coal sorting is 78%, with clogging of the screening surface and up to 1% enlargement of the target product.

Innovations in Coal Preparation and Coke Sorting

Abstract—New approaches permit the optimization of coal preparation and coke sorting. They may be used in construction and reconstruction projects at coke plants.

Effects of characteristics of bed structure on separation of 6-0 mm high-sulfur fine coal in a compound dry separator

ABSTRACT Large amounts of fine coal are produced during coal mining as a result of the extensive deployment of the mechanized mining technology and should be cleaned with the consideration of energy source conversation and environment protection, Urgent need for fine coal (especially high sulfur content fine coal) sorting desulfurization technology. On the basis of an analysis of raw coal, the use of a compound dry separator is proposed in this paper to separate high-sulfur coal across the full-size range of 6–0 mm. The relationship between the change of bed structure and the distribution of bed sulfur content and the force law of the particles is analyzed emphatically. The effect of the change of the backboard angle and the change of the clapboard length and height on the migration trajectories and vibration energy distribution of the material during the sorting process was studied systematically. The results showed that when the backboard angle was 45°, the clapboard length and height were 250 mm and 55–60 mm, respectively. The materials are sufficiently stratified, the sulfur content distribution regularity significantly. The law of vibration energy distribution is significant, and the maximum values of the particles force in the clean coal and gangue are 12.3 mN and 14.1 mN, the vibration acceleration of the clean section and the gangue section are 33.5m/s2, 20.6m/s2, the high sulfur content materials are mainly concentrated in the gangue section. The yields of the clean coal and gangue were 71.45% and 28.55%, respectively, with corresponding sulfur contents of 0.93% and 25.24%. The probable error (E) was 0.14g/cm3.

A Feasibility Study Evaluating the Efficiency of Fine Coal Washing Using Gravity Separation Methods

Coal mining and washing activities in South Africa often lead to the generation of fine and ultra-fine coal which is in most cases discarded due to high handling and transportation costs. Studies conducted revealed that a large quantity of these fines have market acceptable calorific values and lower ash contents. In order to reduce fines discarded, processes have been developed to re-mine and process the fine coal discards with the aim of improving the calorific value, adding them to coarse washed coal to increase the yield as well as pelletizing the fines so as to meet the market specifications in terms of size. The goal of this study was to evaluate the efficiency of fine coal washing using gravity separation methods and comparing the products thereof to the market specifications with regards to the calorific value and the ash content. Coal fines from the No.4 lower seam of the Witbank coalfield in South Africa resulting from a dry coal sorting plant were subjected to a double-stage spiral test work, heavy liquid separation and reflux classifier test work respectively. The reflux classifier achieved products with low ash content and an increased calorific value, at high mass yields. At higher fluidization water flowrate, the reflux classifier performance was superior to that of the spirals with products of lower ash content and higher calorific value. At low cut point densities, heavy liquid separation yielded the cleanest products with very low ash content but at much lower mass yields. As the density increased, the mass yields increased with the ash content while the calorific value decreased. Most of the products from the different processes met most of the local industries’ specifications but none of them met the export market as well as the gold and uranium industry specifications due to the high ash content.

Analyzing the potential for using active filters to reduce voltage nonsinusoidality in the electric power supply system of a coal open-cut in Vietnam

Coal mining is one of the important economic sectors in Vietnam. Power supply systems of coal mines and open-cuts are complex. They have multiple levels of voltages and different types of loads. New electrical equipment usually works alongside with the equipment that is obsolete and worn-out. Power supply systems of industrial areas of Vietnam where coal is mined are characterized by the low power quality. In Vietnam the indices which characterize the distortion of both voltage and current waveforms have standard values. The article presents the findings upon the analysis of a power supply system of a coal open-cut in Vietnam and the electrical equipment of the coal sorting plant along with the results of the experimental studies of power quality indices and the non-sinusoidal mode parameters. The measurement analysis has shown that the indices of the 5-th and 7-th harmonics of voltage were over the limits. There are interharmonics in voltages and currents. The article analyzes the characteristics of active filters. It is possible to improve the power quality by using an active filter which generates both reactive power to increase the load power factor and harmonic and interharmonic currents to reduce the degree of voltage and current waveform distortion.

Development of technology of pulverized coal injection in Ukraine’s blast furnaces in variable liquid and gas dynamic conditions

The aim of the work is to study the features of the use of pulverized coal (PCI) in the conditions of the blast furnace (BF) No. 5 of Metinvest Holding Ltd (Ukraine). The complex for the preparation and use of pulverized coal includes: a coal unloading and storage area; coal mixing section; coal sampling unit; plot of coal sorting and preparation; installation of drying and grinding coal raw materials, installation for the injection of pulverized coal into the BF. It is shown that the use of rational modes of loading and forming portions of the charge, the choice of rational slag mode allowed to increase the annual consumption of pulverized coal on average up to 130 kg / t of pig iron even in the conditions of variable load of BF and when working on coke of reduced quality. During the research, an operational monitoring of the condition of the lining of the BF shaft was carried out using the indications of the thermocouple of the lining and the body of the refrigerators. The determination of the thermal loads of the cooling system made it possible to develop measures to adjust the distribution of the charge components along the radius and circumference of the furnace. The temperature of the peripheral gas flow along the entire height of the furnace is reduced by an average of 13%, the irregularity of the peripheral temperature is reduced by 11%. The stability of the cooling system and the smooth operation of the blast furnaces.