As an equipment failure that often occurs in coal production and transportation, belt conveyor failure usually requires many human and material resources to be identified and diagnosed. Therefore, it is urgent to improve the efficiency of fault identification, and this paper combines the internet of things (IoT) platform and the Light Gradient Boosting Machine (LGBM) model to establish a fault diagnosis system for the belt conveyor. Firstly, selecting and installing sensors for the belt conveyor to collect the running data. Secondly, connecting the sensor and the Aprus adapter and configuring the script language on the client side of the IoT platform. This step enables the collected data to be uploaded to the client side of the IoT platform, where the data can be counted and visualized. Finally, the LGBM model is built to diagnose the conveyor faults, and the evaluation index and K-fold cross-validation prove the model’s effectiveness. In addition, after the system was established and debugged, it was applied in practical mine engineering for three months. The field test results show: (1) The client of the IoT can well receive the data uploaded by the sensor and present the data in the form of a graph. (2) The LGBM model has a high accuracy. In the test, the model accurately detected faults, including belt deviation, belt slipping, and belt tearing, which happened twice, two times, one time and one time, respectively, as well as timely gaving warnings to the client and effectively avoiding subsequent accidents. This application shows that the fault diagnosis system of belt conveyors can accurately diagnose and identify belt conveyor failure in the coal production process and improve the intelligent management of coal mines.

We used the key stratum theory to establish a more realistic thin-plate mechanical model of elastic foundation clamped boundary and study the fracture mechanism of overlying strata during longwall mining. We analyzed the fracture characteristics and factors affecting fracture of the key stratum combined with the Mohr–Coulomb yield criterion. Besides, we used numerical simulation methods to verify the evolution pattern of the overlying strata fracture. The results show that the fracture mechanisms of the elastic foundation clamped structure’s key stratum varied depending on the position under longwall mining. The advanced coal wall area of the upper surface is a compressive-shear fracture. The center area of the lower surface is a tensile fracture. With the increase of the excavation length and the load of the key stratum, the central area and the advanced coal wall area of the long side are fractured before the advanced coal wall area of the short side. With the increase of flexural rigidity of the key stratum, the advanced coal wall area of the long side fractures before the central area and the advanced coal wall area of the short side. With the increase of the foundation modulus and the advanced load of the key stratum, the central area fractures before the surrounding advanced coal wall area. The advanced influence distance was positively correlated with the key stratum’s flexural rigidity and advanced load and negatively correlated with the foundation modulus and excavation length. The advanced influence distance was not affected by the load of the key stratum. The numerical simulation results show that, with the increase of the mining area, the fracture trace of overlying strata in goaf extended to the coal wall’s interior. The fracture range of overlying strata is larger than that of the miningd: area. This study has a practical value for water disasters, gas outbursts, and rock strata control.

The fracture characteristics and zoning model of overburden during longwall mining are the basis of coal mine disaster prevention. However, the existing theoretical model is inconsistent with the field measurement. In order to further research into the strata’s fracture characteristics and optimize the overburden’s zoning model, we used the elasticity and Winkler foundation theory to establish first fracture and periodic fracture mechanics models of clamped boundary supported by an elastic foundation with a key stratum as the research object. We analyzed the stress distribution characteristics and fracture evolution pattern of the mining-induced key stratum. We analyzed the zoning characteristics of mining-induced overburden and established the zoning model according to different fracture mechanisms. The results show that the key stratum formed a double “O-X” shaped interconnected fracture zone after the first fracture. The key stratum formed a double “C-K” shaped interconnected fracture zone after the periodic fracture. We divided the mining-induced overburden into three zones along the horizontal direction: the original rock zone, the inverted triangular compression-shear fracture zone, and the trapezoidal tensile fracture zone. The study revealed the mechanism of inverted step fracture in the separation zone, explained the fracture mechanism of the coal pillar support zone, and has significant theoretical value for the prevention and control of water disasters, gas outbursts, and strata movement.

Longwall top coal caving technology is one of the main methods of thick coal seam mining in China, and the classification evaluation of top coal cavability in longwall top coal caving working face is of great significance for improving coal recovery. However, the empirical or numerical simulation method currently used to evaluate the top coal cavability has high cost and low-efficiency problems. Therefore, in order to improve the evaluation efficiency and reduce evaluation the cost of top coal cavability, according to the characteristics of classification evaluation of top coal cavability, this paper improved and optimized the fuzzy neural network developed by Nauck and Kruse and establishes the fuzzy neural network prediction model for classification evaluation of top coal cavability. At the same time, in order to ensure that the optimized and improved fuzzy neural network has the ability of global approximation that a neural network should have, its global approximation is verified. Then use the data in the database of published papers from CNKI as sample data to train, verify and test the established fuzzy neural network model. After that, the tested model is applied to the classification evaluation of the top coal cavability in 61,107 longwall top coal caving working face in Liuwan Coal Mine. The final evaluation result is that the top coal cavability grade of the 61,107 longwall top coal caving working face in Liuwan Coal Mine is grade II, consistent with the engineering practice.

The dust produced by transportation roads is the primary source of PM2.5 pollution in opencast coal mines. However, China’s opencast coal mines lack an efficient and straightforward construction scheme of monitoring and management systems and a short-term prediction model to support dust control. In this study, by establishing a PM2.5 and other real-time environmental information to monitor, manage, visualize and predict the Internet of things monitoring and prediction system to solve these problems. This study solves these problems by establishing an Internet of things monitoring and prediction system, which can monitor PM2.5 and other real-time environmental information for monitoring, management, visualization, and prediction. We use Lua language to write interface protocol code in the APRUS adapter, which can simplify the construction of environmental monitoring system. The Internet of things platform has a custom visualization scheme, which is convenient for managers without programming experience to manage sensors and real-time data. We analyze real-time data using a time series model in Python, and RMSE and MAPE evaluate cross-validation results. The evaluation results show that the average RMSE of the ARIMA (4,1,0) and Double Exponential Smoothing models are 12.68 and 8.34, respectively. Both models have good generalization ability. The average MAPE of the fitting results are 10.5% and 1.7%, respectively, and the relative error is small. Because the ARIMA model has a more flexible prediction range and strong expansibility, and ARIMA model shows good adaptability in cross-validation, the ARIMA model is more suitable as the short-term prediction model of the prediction system. The prediction system can continuously predict PM2.5 dust through the ARIMA model. The monitoring and prediction system is very suitable for managers of opencast coal mines to prevent and control road dust.