Technical parameters of drawing and coal-gangue field movements of a fully mechanized large mining height top coal caving working face

Under fully mechanized, large mining height top coal caving conditions, the shield beam slope angle of the support increases due to the enlargement of the top coal breaking and caving space. This results in a change of the caving window location and dimensions and, therefore, the granular coal-gangue movement and flows provide new characteristics during top coal caving. The main inferences we draw are as follows. Firstly, after shifting the supports, the caved top coal layer line and the coal gangue boundary line become steeper and are clearly larger than those under common mining heights. Secondly, during the top coal caving procedure, the speed of the coal-gangue flow increases and at the same drawing interval, the distance between the coal-gangue boundary line and the top beam end is reduced. Thirdly, affected by the drawing ratio, the slope angle of the shield beam and the dimensions of the caving window, it is easy to mix the gangue. A rational drawing interval will cause the coal-gangue boundary line to be slightly behind the down tail boom lower boundary. This rational drawing interval under conditions of large mining heights has been analyzed and determined.

Study on activity evaluation of activated coal-gangue and the hydration process

Chemical compositions, mineral compositions and the activated mechanism of the coal-gangue were analyzed. And pozzolana activities of the coal-gangue were evaluated after activated. Moreover, hydration heat and hydration compositions of activated coal-gangue-calcium oxide system, as well as hydration degree and hardened paste microstructures of activated coal-gangue-cement system were studied. Results show that pozzolana activities of the activated coal-gangue root in amorphous SiO2 and activated Al2O3. With the exciting of gypsum, the reaction of activated coal-gangue and Ca（OH） 2 would produce hydration products as ettringite, calcium silicate hydrate, and calcium aluminate. The relationship between the curing age and the content of Ca （OH）2 in coal-gangue-cement system was ascertained. Unhydrated particles in the coalogangue-cement paste were more than that in the neat cement paste at the same hydration periods, and even existed at the later stage of hydration. Furthermore, the activated coal-gangue could inhibit growth and gathering of the calcium oxide crystal, and improve the structure of hardened cement paste.

STATNet:One-stage coal-gangue detector based on deep learning algorithm for real industrial application

Coal-gangue object detection has attracted substantial attention because it is the core of realizing vision-based intelligent and green coal separation. However, most existing studies have been focused on laboratory datasets and prioritized model lightweight. This makes the coal-gangue object detection challenging to adapt to the complex and harsh scenes of real production environments. Therefore, our project collected and labeled image datasets of coal and gangue under real production conditions from a coal preparation plant. We then designed a one-stage object model, named STATNet, following the “backbone-neck-head” architecture with the aim of enhancing the detection accuracy under industrial coal preparation scenarios. The proposed model utilizes Swin Transformer as backbone module to extract multi-scale features, improved path augmentation feature pyramid network (iPAFPN) as neck module to enrich feature fusion, and task-aligned head (TAH) as head module to mitigate conflicts and misalignments between classification and localization tasks. Experimental results on a real-world industrial dataset demonstrate that the proposed STATNet model achieves an impressive AP50 of 89.27 %, significantly surpassing several state-of-the-art baseline models by 2.02 % to 5.58 %. Additionally, it exhibits stronger robustness in resisting image corruption and perturbation. These findings demonstrate its promising prospects in practical coal and gangue separation applications.