Rock Particle Motion Information Detection Based on Video Instance Segmentation

The detection of rock particle motion information is the basis for revealing particle motion laws and quantitative analysis. Such a task is crucial in guiding engineering construction, preventing geological disasters, and verifying numerical models of particles. We propose a machine vision method based on video instance segmentation (VIS) to address the motion information detection problem in rock particles under a vibration load. First, we designed a classification loss function based on Arcface loss to improve the Mask R-CNN. This loss function introduces an angular distance based on SoftMax loss that distinguishes the objects and backgrounds with higher similarity. Second, this method combines the abovementioned Mask R-CNN and Deep Simple Online and Real-time Tracking (Deep SORT) to perform rock particle detection, segmentation, and tracking. Third, we utilized the equivalent ellipse characterization method for segmented particles, integrating with the proportional calibration algorithm to test the translation and detecting the rotation by calculating the change in the angle of the ellipse’s major axis. The experimental results show that the improved Mask R-CNN obtains an accuracy of 93.36% on a self-created dataset and also has some advantages on public datasets. Combining the improved Mask R-CNN and Deep SORT could fulfill the VIS with a low ID switching rate while successfully detecting movement information. The average detection errors of translation and rotation are 5.10% and 14.49%, respectively. This study provides an intelligent scheme for detecting movement information of rock particles.

Analysis on the Difference of Impact Response between Single Coal-Rock Particle and the Box Structure-Based Tail Beam

In the process of coal caving, the basis of identifying coal and rock by the vibration signal is the difference of the tail beam response when coal-rock impacts the tail beam, and the tail beam in the hydraulic support is a complex box structure with multiplate transverse and longitudinal welding, and the response difference of the box structure-based tail beam under the impact of coal-rock is not clear. Therefore, this paper studies the response difference of box structure-based tail beam when coal-rock particle impacts on the box structure-based tail beam. Firstly, through the construction and analysis of the impact theoretical model of the coal-rock particle and metal plate, it is found that the complex box structure of the tail beam makes it extremely difficult to establish the impact theoretical model of the coal-rock and box structure-based tail beam, so it is impossible to directly study the response of the box structure-based tail beam when the coal-rock impacts on the box structure-based tail beam by the theoretical method. Therefore, the impact simulation model of coal-rock particle and box structure-based tail beam is further established. Through the changes of kinetic energy and internal energy of the box structure-based tail beam system, the contact response of collision contact zone, and noncollision contact zone of the box structure-based tail beam, the response difference of box structure-based tail beam when coal-rock particle impacts on the box structure-based tail beam is analyzed. Then, by changing the impact speed and contact mode of the coal-rock particle, the effects of impact speed and the contact mode on the response difference of the box structure-based tail beam are studied separately. The conclusion shows that the response difference of the box structure-based tail beam under the impact of the coal particle and rock particle is obvious, and the difference increases as the impact speed increases, and the difference increases as the contact range increases.

Optimization of medium–low-grade phosphorus rock carbothermal reduction process by response surface methodology

Phosphorus extraction from phosphorus rock was conducted by carbothermal reduction with silica and coke. The effects of reaction temperature, reaction time, coke excess coefficient, molar ratio of silicon–calcium, and phosphorus rock particle size on the phosphorus reduction rate were investigated by the response surface methodology (RSM). The central composite design (CCD) with five factors and five levels was used to explore the effects of variables’ interactions on the phosphorus reduction rate. The results showed that there are significant interactions between reaction time and temperature; reaction temperature and molar ratio of silicon–calcium; reaction temperature and phosphorus rock particle size; coke excess coefficient and molar ratio of silicon–calcium; and coke excess coefficient and phosphorus rock particle size. The optimum conditions in the experimental range are reaction time 92 min, reaction temperature 1340°C, coke excess coefficient 1.27, molar ratio of silicon–calcium 1.28, and phosphorus rock particle size 75–106 µm, which were derived from the quadratic statistic model. Under these conditions, the phosphorus reduction rate can reach 96.88%, which is close to the model prediction value 99.40%. The optimized carbothermal reduction conditions of phosphorus rock by the RSM are helpful to reduce the energy cost of thermal phosphoric acid process.

Influence of water and rock particle contents on the shear behaviour of a SRM

The contents of both water and rock particles are important factors affecting the mechanical strength of a soil–rock mixture (SRM) filled subgrade in the western mountainous area of China. Therefore, the purpose of this paper is to study the mechanisms of reconstituted landslide deposit samples with different water and rock particle contents by analysing the characteristics of shear strength, volumetric strain and ‘jumping’ phenomenon via large-scale direct shear tests. The results show that the influence of water content on shear strength is greater than the influence of rock particle content under a lower normal stress, and the results are reversed in the case of a higher normal stress. The effect of water content on the equivalent cohesion is bigger, especially for the sample with a high rock particle content. The friction angle of the specimen with same water content increases with the increasing rock particle content, but when the number of rock particles increases to a certain extent, there is a little effect on the friction angle. However, the friction angle decreases with increasing water content at the same rock particle content. Specimens with the same rock particle content change from dilation to compression with increasing water content. Finally, the continuous stage of the ‘intense jumping’ at different water content has been analysed. The ‘jumping’ phenomenon of samples with low water and rock particle content will first strengthen and then weaken the samples with increasing normal stress.

Effect of Rock Particle Content on the Mechanical Behavior of a Soil-Rock Mixture (SRM) via Large-Scale Direct Shear Test

The mechanical strength of the landslide deposits directly affects the safety and operation of the roads in the western mountainous area of China. Therefore, the research is aimed at studying the mechanisms of a landslide deposit sample with different rock particle contents by analyzing its characteristics of the stress-strain behavior, the “jumping” phenomenon, the volumetric strain, and the shear strength parameters via a large-scale direct shear test. Stress-strain results show that stress-strain curves can be divided into 3 different stages: liner elastic stage, yielding stage, and strain-hardening stage. The shear strength of SRM behaves more like “soil” at a lower rock particle content and behaves more like “rock joints” at a higher rock particle content. Characteristics of the “jumping” phenomenon results show that the “intense jumping” stage becomes obvious with the increasing rock particle content and the normal stress. However, the lower the rock particle content is, the more obvious the “jumping” phenomenon under the same normal stress is. Volumetric strain results show that the sample with a lower rock particle content showed a dilatancy behavior under the low normal stress and shrinkage behavior under the high normal stress. The dilatancy value becomes smaller with the increasing normal stress. The maximum shear stress value of the rock particle content corresponds to the maximum value of dilatancy or shrinkage. We also conclude that the intercept of the Mohr failure envelope of the soil-rock mixture should be called the “equivalent cohesion,” not simply called the “cohesion.” The higher the normal stress and rock particle content are, the bigger the equivalent cohesion and the internal friction angle is.