Dielectric and geometric feature extraction and recognition method of coal and gangue based on VMD-SVM

Research on Coal Gangue Recognition Based on Multi-source Time-Frequency Domain Feature Fusion

The over-exploitation of resources caused by the increasing coal demand has resulted in a sharp increase in solid waste emissions mainly gangue, which has made the burden on the environment, economy, resources, and society of our country heavier. In order to achieve a balance between energy consumption and solid waste emission in the process of top coal caving, this study carried out coal gangue recognition research based on multi-source time-frequency domain feature fusion (MS-TFDF-F). First, the process of coal gangue symbiosis and the harm of gangue in top coal caving are analyzed, and the fundamental method of comprehensive treatment of gangue is put forward, which is the accurate recognition of the coal gangue interface. Second, by building a top coal caving simulation test bed, the MS signals generated in the caving process of the coal gangue mixture with a gangue content of 0-100% are collected and the TFDFs are extracted. Third, the MS-TFDF-F-based coal gangue recognition model is established. Then, the recognition effect of the two TFDF-F sample sets was compared, and the results show that the time-frequency domain feature selection fusion method (TFDFS-FM) has higher accuracy. On this basis, this paper studies the variation law of the number of sensors on the coal gangue recognition accuracy of MS information fusion. Finally, the economic, social, environmental, and resource benefits of the model are qualitatively described. The final results show that the MS-TFDF-F-based coal gangue recognition model has the strongest recognition ability when fusing six sensor signals, and the recognition accuracy reaches 99% under the AdaBoost algorithm. The establishment of this model brings huge benefits to China's environment, economy, resources, and society, and it is helpful to realize the balance between loss reduction mining and solid waste emission reduction in the process of top coal caving.

Research on the Identification Mechanism of Coal Gangue Based on the Differences of Mineral Components

For coal and gangue, intelligent sorting processes for separation, the use of coal and gangue mineral components with different fundamental differences, and the study of different properties of minerals and coal with different scales and density regarding the gray value change law are presented. The results show that the gray value of single minerals and mixed minerals gradually decreases with the increase of their thickness and density. The greater the density of minerals, the smaller the gray value at the same thickness, and the same rule applies to different coal ranks. Via regression analysis methods, the values of the regression equation parameter a of pure minerals for graphite, quartz, kaolinite, and montmorillonite are 59.25, 65.69, 61.61, and 58.02 in the high-energy region, respectively. In the low-energy region, they are 174.95, 177.31, 186.95, and 161.81. For the regression equation parameter of mixed minerals in the form of two mixed minerals (graphite and quartz, kaolinite, or montmorillonite) and three kinds of mineral mixing (graphite-kaolinite and quartz; graphite-montmorillonite and quartz; graphite-kaolinite and montmorillonite), the gray values are 151.12, 156.00, 153.13,152.43, 152.98, and 151.98 in the high-energy region, respectively; in the low-energy region, they are 193.34, 201.34, 192.93, 191.26, 194.68, and 193.08. The phenomenon for the gray range of two kinds of single minerals locates in the range of mixed minerals that was formed from a single mineral observed after the regression equation of mixed mineral was verified by a single mineral, which agrees with the X-ray recognition pattern. In the end, as the density of coking coal, fat coal, and gas coal increases, the gray value decreases, which was in agreement with single- and mixed-mineral analyses.

Hybrid Compression Optimization Based Rapid Detection Method for Non-Coal Conveying Foreign Objects

The existence of conveyor foreign objects poses a serious threat to the service life of conveyor belts, which will cause abnormal damage or even tearing, so fast and effective detection of conveyor foreign objects is of great significance to ensure the safe and efficient operation of belt conveyors. Considering the need for the foreign object detection algorithm to operate in edge computing devices, this paper proposes a hybrid compression method that integrates network sparse, structured pruning, and knowledge distillation to compress the network parameters and calculations. Combined with a Yolov5 network for practice, three structured pruning strategies are specifically proposed, all of which are proven to have achieved a good compression effect. The experiment results show that under the pruning rate of 0.9, the proposed three pruning strategies can achieve more than 95% compression for network parameters, more than 90% compression for the computation, and more than 90% compression for the size of the network model, and the optimized network is able to accelerate inference on both Central Processing Unit (CPU) and Graphic Processing Unit (GPU) hardware platforms, with a maximum speedup of 70.3% on the GPU platform and 157.5% on the CPU platform, providing an excellent real-time performance but also causing a large accuracy loss. In contrast, the proposed method balances better real-time performance and detection accuracy (>88.2%) when the pruning rate is at 0.6~0.9. Further, to avoid the influence of motion blur, a method of introducing prior knowledge is proposed to improve the resistance of the network, thus strongly ensuring the detection effect. All the technical solutions proposed are of great significance in promoting the intelligent development of coal mine equipment, ensuring the safe and efficient operation of belt conveyors, and promoting sustainable development.

Analysis of the vibration characteristics of tail beam of the hydraulic support under random coal gangue particle slip conditions

To study the influence of the gangue content of coal gangue particles on the vibration signal of the tail beam under sliding condition, this paper combines three-dimensional(3D) laser scanning technology with the finite element method, establishes a finite element model of the real shape of coal gangue particles and the hydraulic support in top coal caving in LS-DYNA, analyzes the influence of gangue content on some characteristics of the acceleration signal on the tail beam in the time and frequency domains, and then studies the influence of the size and total mass of the rock, and the angle of the tail beam on the characteristics. The following conclusions are obtained: when the coal gangue particles slip on the tail beam, an increase in gangue content significantly improves the effective value of the acceleration signal of the tail beam in the time domain and the average power and average amplitude in the frequency domain. With different sizes, total masses, and tail beam angles, the increase in gangue content always causes an increase in acceleration signal characteristics. In terms of the influence of various factors on the same gangue content, at the same total mass, the larger the rock mass size is, the faster the characteristic value increases with the increase in gangue content. The greater the total mass, the greater the value of the acceleration signal characteristics. A smaller angle between the tail beam and the ground increases the value of each characteristic. The results of this study provide a reference for further research on coal gangue identification based on vibrations.

Vibration Response Analysis of Hydraulic Support Based on Real Shape Coal Gangue Particles

Top coal caving is an important way of thick coal seam mining. The current coal gangue identification technology is not mature, resulting in a low degree of automation of coal caving. The current numerical simulation pays little attention to the real shape of rocks. This paper aims to reveal the vibration response of the tail beam under the action of real shape coal gangue particles. First, the real shape rock and hydraulic support model are established, and the relationship between the Rock Mixed Ratio (RMR) and the vibration signal characteristics during the impact process are studied. The influence of falling velocity and coal strength on this relationship are analyzed. Finally, the influence of motion mode on this relationship is analyzed and discussed. The numerical results show that the increase of the RMR can significantly enhance the velocity and acceleration signals of the tail beam, and the signals caused by different RMR are still different under different velocities and strengths. The best recognition effect can be obtained when the coal gangue particles slip on the hydraulic support, and the effect is the the worst when the coal gangue particles impact upon and roll on the hydraulic support. The conclusion provides directions for further study of coal gangue identification based on vibration.