Low-rank, high-sulfur coal resources are abundant and constitute an essential foundation for ensuring national energy security. The compound dry separation bed offers an effective approach for the removal of inorganic mineral impurities such as high-sulfur and high-ash components, thereby promoting the clean utilization of coal. This study focuses on addressing the challenge of real-time and precise identification of coal and gangue particles within the compound dry separation bed, where densely packed particles and complex textures hinder accurate recognition. To overcome this limitation, an improved texture-aware model, Texture-Aware YOLOv13 (TAYOLOv13), is proposed. The TA-YOLOv13 architecture integrates advanced modules including This model enhances feature extraction, multi-scale fusion, and model adaptability by incorporating the second-generation version of the ConvNext series of convolutional neural network architectures - Convolution Next Version 2 (ConvNextV2), Efficient Feature Representation Network (EfficentRep), and Omni-Dimensional Dynamic Convolution (ODConv), among others. ConvNextV2, EfficientRep, and ODConv, which collectively enhance feature extraction capability, multi-scale feature fusion, and model adaptability. Experimental results demonstrate that TA-YOLOv13 achieves a precision of 97.89%, recall of 97.91%, and mAP0.5 of 98.94% on the test dataset. The overall performance indicator mAP0.5:0.95 exhibits a significant improvement of 15.5% compared to the baseline model. Heatmap visualization further verifies the model's ability to effectively capture subtle textural differences between coal and gangue under complex sorting conditions. Furthermore, an intelligent closed-loop feedback control system was established based on the proposed visual perception model. Through a fuzzy PID controller, the system dynamically regulates key operational parameters such as airflow rate, vibration amplitude, and frequency. Under the optimal parameter combination (frequency 24-26 Hz, amplitude 2.2-2.6 mm, and air velocity 1.80-2.20 m/s), the intelligent dry separation of low-rank high-sulfur coal achieved remarkable separation efficiency: the clean coal contamination rate was below 2%, the clean coal loss rate was below 4%, and the clean coal yield reached 70.02% with ash content of 9.36% and sulfur content of 0.98%. The gangue yield was 29.98%, with ash content of 49.08% and sulfur content of 9.92%. Distinct gradient distributions of sulfur and ash content were observed across the bed, and the separation precision, represented by the Ep = 0.055 g/cm3. Overall, the proposed method realizes clean, efficient, and high-value upgrading of low-rank high-sulfur coal through the synergistic integration of accurate perception, intelligent decision-making, and optimized process control.
Titanium is widely regarded as a strategically important metal due to its outstanding properties and broad applications in metallurgy, aerospace, and energy sectors. However, with the gradual depletion of primary titanium ores, concerns over long-term supply security are becoming increasingly prominent. At present, less than 20
Red mud is an alkaline solid waste generated by the alumina industry. Its annual global emissions have exceeded 180 million tons, and its prolonged open storage is prone to causing soil alkalization and air pollution. Red mud is considered to be a potential secondary resource given its rich valuable metal content. To realize the efficient resource utilization of red mud and convert solid waste into useful resources as much as possible, related researchers have carried out various studies on the recovery of iron from red mud. The relevant literature in recent years was summarized and analyzed. The research progress of iron resource recovery technology from red mud and the resource utilization of its tailings were also reviewed. In terms of iron recovery technologies, the process principles, technical characteristics, and limitations of these technologies for traditional methods such as physical sorting, pyrometallurgy, and hydrometallurgy, as well as emerging technologies including bioleaching, biomass pyrolysis reduction, and electrochemistry, are highlighted. A comparative analysis of the applicability of various technologies provides theoretical support for the selection of iron recovery processes under different conditions. At the same time, for the characteristics of the tailings produced after iron extraction from red mud, the ways of resource utilization in the fields of building materials and cementitious materials are discussed in depth, so as to realize the efficient utilization of the components of red mud. Finally, based on the research results obtained above and the current problems of red mud resource utilization, the sustainable development direction of red mud resource utilization in the future is prospected.
Rock original structure is one of the major factors influencing rock fracture, and understanding the relationship between rock structure and fracture modes is essential for elucidating the failure mechanisms of geotechnical materials. However, the characteristics of rock’s internal structure and its relationship with the ultimate fracture mode remain unclear. To investigate this relationship and identify the impact mechanisms of the original structure during rock fracture, multistage loading experiments were conducted on siltstone using acoustic imaging technology. The results show that minerals and pores within the microstructure of rocks are spatially grouped into different regions, forming new macrostructures with distinct mechanical properties, known as heterogeneity structures. These heterogeneity structures are interwoven and control the final fracture pattern and main fracture shape of rocks. Based on systems engineering principles, we propose the concept of a “rock structure system” and define its hierarchical structure: the “rock monolithic layer (rock sample),” the “macroscopic structural body layer (heterogeneity structures),” and the “microscopic basic unit layer (mineral grains, microfractures, microporosity, etc.)”. This study bridges the gap between microscopic and macroscopic studies of rock fracture, providing significant contributions to the prediction and prevention of geological and engineering disasters.
This study adopted a combined strategy of Response Surface Methodology (RSM) and Multi-Objective Particle Swarm Optimization (MOPSO) to optimize the energy efficiency of an indirect liquid cooling system for electric construction vehicle air conditioning. First, an experimental setup of the cooling system was constructed to evaluate alternating current performance. Subsequently, a PSO-SVR prediction model was proposed to reduce the testing period and lay the foundation for establishing semi-empirical relationship. Following this, a response surface model was developed based on Box-Behnken design and RSM, incorporating input parameters (compressor speed, electronic valve opening, coolant inlet temperature, and pump speed) and objective functions (refrigeration capacity and power consumption). The model of accuracy was validated through Analysis of Variance (ANOVA). Finally, MOPSO was implemented based on the response model to maximize refrigeration capacity while minimize power consumption, and the optimization results were verified experimentally. The results demonstrated that the response surface model for refrigeration capacity and power consumption exhibited excellent performance, with maximum deviations between predicted and experimental values within 3
