Review
Materials Science, Multidisciplinary
Xianping Luo, Kunzhong He, Yan Zhang, Pengyu He, Yongbing Zhang
Summary: In the context of scarce global ore resources and intense market competition, the development of the mining industry is greatly restricted. Intelligent ore sorting equipment plays a crucial role in improving ore utilization and enhancing economic benefits for enterprises by increasing ore grade, reducing grinding costs, and minimizing tailings production. Factors that affect sorting efficiency in long-term research on intelligent ore sorting equipment include ore information identification technology, equipment sorting actuator, and information processing algorithm. These factors, with high precision, strong anti-interference capabilities, and high speed, ensure the separation efficiency of intelligent ore sorting equipment. Color ore sorters, X-ray ore transmission sorters, dual-energy X-ray transmission ore sorters, X-ray fluorescence ore sorters, and near-infrared ore sorters have been successfully developed to match the different characteristics of minerals while maintaining accurate sorting and improving sorting efficiency. With the continuous improvement of mine automation level, the future trend of equipment development will involve the application of high-speed, high-precision online element rapid analysis technology with strong anti-interference capabilities. Laser-induced breakdown spectroscopy, transient gamma neutron activation analysis, online Fourier transform infrared spectroscopy, and nuclear magnetic resonance techniques will contribute to the advancement of ore sorting equipment. Additionally, the improvement and joint application of high-speed and high-precision operation algorithms, such as peak area, principal component analysis, artificial neural network, partial least squares, and Monte Carlo library least squares methods, are essential for the future development of intelligent ore sorting equipment.
INTERNATIONAL JOURNAL OF MINERALS METALLURGY AND MATERIALS
(2022)
Article
Computer Science, Information Systems
Zixiang Wang, Shuxin Xie, Guodong Chen, Wenzheng Chi, Zihao Ding, Peng Wang
Summary: The separation of coal and gangue is a crucial aspect of coal mining, and an online flexible sorting model based on multi-information fusion has been proposed to effectively improve the accuracy of gangue sorting. Experimental results have shown that this model is able to accurately sort gangue of different shapes and sizes despite the high-speed movement of the belt.
Article
Engineering, Chemical
Wei Zhou, Wanghao Xia, Liangliang Liu, Liansheng Li, Qiuyu Zeng, Shujie Wang, Jinbo Zhu
Summary: This paper investigates the key technologies of underground gangue photoelectric separation, including gangue identification, jet nozzle separation, and process layout. The XAFS method is used to identify the differences in microscopic crystal properties of coal gangue, and numerical simulations are conducted to optimize the nozzle morphology and parameters. Multiple layout schemes for gangue photoelectric separation systems are proposed based on the development and mining system of a specific coal mine.
Article
Engineering, Multidisciplinary
Yongchao Zhang, Jianshi Wang, Zhiwei Yu, Shuai Zhao, Guangxia Bei
Summary: In this paper, the YOLOv4 algorithm based on deep learning is applied to detect coal gangue, and the combined use of optimization methods is shown to improve the algorithm's performance. Through comparisons with coal gangue test data sets and detection experiments, it is found that the YOLOv4 algorithm performs excellently in the field of coal gangue detection, and the use of optimization methods further enhances its performance.
Article
Computer Science, Information Systems
Qiang Liu, Jingao Li, Yusheng Li, Mingwang Gao
Summary: The paper introduces an improved YOLOv4 algorithm for intelligent and highly accurate recognition of coal and coal gangue, which outperforms other algorithms in terms of detection accuracy, speed, and performance by optimizing anchor values, anti-interference ability, and increasing the number of layers in the feature pyramid.
Article
Engineering, Multidisciplinary
Xi Wang, Yongcun Guo, Shuang Wang, Gang Cheng, Xinquan Wang, Lei He
Summary: In this study, a semantic segmentation network called SSNet_CG based on the PSPNet is proposed to rapidly identify coal and gangue under multi-scale, adhesion, and half-occlusion conditions. The method optimizes the backbone feature extraction network, embeds attention mechanisms, substitutes typical convolutions with depthwise separable and atrous convolutions, reduces the number of feature levels, and adds feature fusion channels. Experimental results show that the proposed method achieves the best effects with high accuracy and fast processing time in identifying multi-scale and partially blocked coals and gangues.
Article
Multidisciplinary Sciences
Ji-qiang Zhang, Xiang He, Ke Yang, Zhen Wei, Xin-Yuan Zhao, Jue-jing Fang
Summary: The basic characteristics, diffusion laws, and flow laws of coal gangue and coal gangue slurry were studied through various tests. The conveying performance of coal gangue slurry was tested and a simulation test of caving areas was conducted. The results showed the controlling factor for the conveying performance, the diffusion profile, and the spatial accumulation patterns of the slurry.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Chemical
Caie Zhang, Shuaishuai Lu
Summary: In this study, experiments were conducted to investigate the classification performance of coal slime. It was found that the misplacement of fine particles in the underflow was mainly caused by the presence of fine gangue components. Increasing the feed concentration appropriately can reduce the adverse effect of particle density on classification. This work provides insights into the migration mechanism of multi-component particles during the classification of coal slime.
Article
Materials Science, Ceramics
Yongda Wang, Yuxuan Wang, Pei Nian, Wentao Wang, Dong Wei, Nan Xu, Zhixin Wu, Taotao Zhu, Yibin Wei
Summary: In this study, an in-situ reaction-bonded SiC membrane sintered at low temperature using coal gangue as the sintering aid was developed. The effects of sintering temperature and coal gangue proportion on the membrane properties were investigated. The optimized membrane exhibited excellent pore size, open porosity, bending strength and water permeability, making it suitable for high-performance applications.
CERAMICS INTERNATIONAL
(2023)
Article
Chemistry, Analytical
Hongwei Ma, Xiaorong Wei, Peng Wang, Ye Zhang, Xiangang Cao, Wenjian Zhou
Summary: This study proposes a multi-manipulator cooperative sorting method that improves the efficiency of coal gangue sorting by enhancing task allocation and trajectory planning algorithms.
Article
Chemistry, Analytical
Peng Wang, Hongwei Ma, Ye Zhang, Xiangang Cao, Xudong Wu, Xiaorong Wei, Wenjian Zhou
Summary: This paper proposes a dynamic gangue trajectory planning method for the manipulator synchronous tracking under multi-constraint conditions to solve the problems of grab failure and manipulator damage. The mathematical model of seven-segment manipulator trajectory planning is constructed first, and then the mathematical model of synchronous tracking of dynamic targets based on a time-minimum manipulator is constructed by taking the robot's acceleration, speed, and synchronization as constraints. The particle swarm optimization algorithm is used to solve the model, and the calculation results are put into the trajectory planning model of the manipulator to obtain the synchronous tracking trajectory. Simulation and experiments show that the method can ensure the synchronization of the position, speed, and acceleration of the moving target and the target after tracking, with an average position error of 2.1 mm and an average speed error of 7.4 mm/s. The robot has a high tracking accuracy, which further improves the robot's grasping stability and success rate.
Article
Engineering, Multidisciplinary
Pengcheng Yan, Quansheng Sun, Nini Yin, Lili Hua, Songhang Shang, Chaoyin Zhang
Summary: This study proposes an intelligent coal-gangue classification method based on multispectral imaging technology and target detection, which achieves high accuracy and speed in identifying coal-gangue. By collecting multispectral data, selecting bands with high recognition rate, and training with the improved YOLOv5 model, accurate identification and relative positioning of coal-gangue are achieved.
Article
Chemistry, Multidisciplinary
Fengqin Liu, Mingzhuang Xie, Guoqing Yu, Chaoyang Ke, Hongliang Zhao
Summary: This study focused on the catalytic effect of additives on the phase transformation process of coal gangue to enhance the separation of silica from alumina minerals, leading to increased resource utilization rate.
ACS SUSTAINABLE CHEMISTRY & ENGINEERING
(2021)
Article
Computer Science, Information Systems
Guanghui Xue, Sanxi Li, Peng Hou, Song Gao, Renjie Tan
Summary: This paper presents a detection algorithm for coal gangue sorting robot, which achieves faster detection speed and smaller model size through the use of lightweight networks and improvements in real-time performance. It also demonstrates good gangue detection performance.
INTERNET OF THINGS
(2023)
Article
Chemistry, Multidisciplinary
Yao Zhang, Yang Yang, Qingliang Zeng
Summary: The increasing demand for coal has led to over-exploitation of resources, resulting in a sharp increase in solid waste emissions, mainly gangue, which has imposed a heavy burden on the environment, economy, resources, and society of China. This study aims to achieve a balance between energy consumption and solid waste emission in the top coal caving process through coal gangue recognition based on multi-source time-frequency domain feature fusion (MS-TFDF-F).
