To meet the requirements of the mine's variable frequency ventilation system for underground air quality moni-toring,a mine air quality evaluation method based on an improved Random Forest algorithm is proposed.The method aims to accurately monitor the air quality inside the mine,providing important references for the popularization and application of the variable frequency ventilation system to effectively ensure safe production and protect miners' health.Firstly,the sources of pol-lutants in the mine air and their potential hazards to miners' health are analyzed,and five major pollutants(CO,SO2,H2S,NO2,and dust)are selected as evaluation factors to establish the evaluation standards.Secondly,the Random Forest algorithm is improved using the Area Under the Curve(AUC)of the Receiver Operating Characteristic(ROC)curve to comprehensively evaluate mine air quality.The experimental results show that the model performs well,with a minimum generalization error of only 0.017 7 and a maximum classification accuracy of 97.72%on the test data.Based on the improved algorithm,a mine air quality evaluation system was developed.This system can effectively assess mine air quality with high robustness and accuracy,providing new insights for smart mine construction and mine air quality evaluation.
Pile inventory is a common practice in terrestrial laser scanner applications. However, there are two main challenges when using the traditional terrestrial laser scanning (TLS) for pile inventory. One is the high cost and the other is the unreachability problem within a limited space. This letter develops a cost-effective system combining two single-pulse scanners and a rangefinder. The sensors are coupled together on a sliding rail to collect 3-D points for pile inventory. The proposed system is applied to an indoor scenario in a gold and copper open-pit mine. We investigate the effect of inclination angles on the point cloud. In addition, the generated point clouds are compared with those obtained by an advanced scanner in simultaneous localization and mapping configuration. The comparison shows higher completeness when using our proposed system. Cross-validation results show ~99.9% repeatability of the proposed system for pile inventory.
The stiffness theory of rockburst plays a crucial role in understanding and preventing rockburst events. This theory evaluates the severity of rockbursts through the difference in stiffness. As a fundamental theory, many new theories have emerged from the stiffness theory, and its applications in mines and deep tunnels are diverse. In this paper, we provide a systematic review of the development process, application status, and application field of rockburst stiffness theory from the perspective of theoretical derivation, laboratory testing, and field application. We also identify key and difficult problems in stiffness theory, such as the determination method of stiffness, the influence of post-peak slope, and the study of rockburst criteria. In addition, based on the existing issues related to stiffness determination, exploration of stiffness changes during rockburst development, and low adaptability in predicting rockburst intensity, we propose the influence of the blasting body-surrounding rock stiffness on the spatial-temporal characteristics, intensity, and mechanism of rockburst, dynamic variable stiffness tests, and stiffness theoretical criteria for determining the rockburst intensity as areas for further research on the stiffness theory of rockburst.
In recent years,with the rapid development of robot technology and artificial intelligence technology,more and more mining enterprises begin to use robots for inspection and monitoring,in order to improve production efficiency and reduce the cost of manual inspection.However,due to the complex and changeable mine environment,there are a large number of ob-stacles and dangerous factors,traditional inspection robots often cannot meet the actual demand,it is necessary to introduce some advanced scene understanding and machine vision technology,in order to improve the robot′s navigation and obstacle a-voidance ability.In this paper,a navigational obstacle avoidance method of mine inspection robot based on integrated scene un-derstanding and machine vision is studied.First of all,the mine environment is identified and positioned by machine vision technology to obtain the position and surrounding scene information of the current robot.Then,the scene understanding technol-ogy is used to analyze the mine scene,including identifying various ores,equipment and personnel,and detecting and classif-ying obstacles in the mine environment.Finally,the integrated scene understanding and machine vision information are applied to the navigation and obstacle avoidance control of the robot.The experimental results show that the proposed method can effec-tively improve the robot′s navigation and obstacle avoidance ability in complex mine environment,have certain significance for promoting the construction of intelligent mine,improving mine production efficiency and reducing inspection cost.
In order to effectively identify the danger area of slope and accurately judge the stability state of slope,a set of"face-point-surface"slope comprehensive evaluation method based on fuzzy comprehensive evaluation method,MSARMA method and FLAC3D was proposed.Firstly,according to the composition and structural characteristics of the on-site slope rock mass,disaster factors were summarized,while assignment criteria for discrete and continuous variables were divided based on the landslide body characteristics and spatiotemporal distribution.Following,based on the comprehensive evaluation principle of fuzzy mathematics,the high and steep side stability in the multi-factor influence regions was comprehensively evaluated,while the spatial division of the unstable region was determined.Finally,the slope potential slip surface in the unstable zone of the western side was utilized as the calculation model object,while the sensitivity analysis of the slope impact factor was conducted through the MSARMA method,and the sensitivity factors were determined.The FLAC3D finite difference method was utilized for numerical simulation analysis,and the conclusion was drawn.Taking Antaibao Open-pit Coal Mine as an example,its unstable area was divided and the evolution law of displacement field under sensitive factors such as seepage and vibration was ob-tained.The results showed that under natural conditions,the maximum displacements in X and Y directions of the slope are 30 cm and 41 cm,while under seepage conditions,the maximum displacements in X and Y directions of the northwest slope are 45 cm and 70 cm,respectively.Under the action of earthquake,the displacements at the bottom of the north slope and the west slope change little,while the displacement at the top is larger.Based on the above results of numerical simulation,the design scheme of slope reinforcement and monitoring in unstable region was proposed to ensure the stability of the whole slope.The in-tegrated evaluation method could provide reference for the stability analysis of similar high and steep rock slopes.
