Search

The roof water inrush disaster induced by coal mining is becoming a vital bottleneck restricting mine safety. To accurately predict the water inrush position of the coal seam roof sandstone aquifer and accurately prevent and control it, this paper takes Lilou Coal Mine in Juye Coalfield as an example. Based on the comprehensive analysis of hydrogeological data, drilling data, and geophysiological data, this paper examines the water richness of the roof aquifer, the water insulation and geological structure, and the fracture development characteristics of the roof aquifer. Starting from the general side, nine factors, including fault strength index, tectonic intersection point, tip extinguishing point, development height of water conduction crack zone, roof sandstone aquifer thickness, aquifer drilling unit inrush, geophysical prospecting water-rich anomaly area, roof key layer thickness, roof aquifer thickness, brittle plastic rock thickness ratio, etc., form the roof plate roof. The main control factors for water inrush are deeply discussed. Through the spatial analysis function of GIS, unique drawings of different evaluation indicators are drawn, and the data are normalized. Combined with the AHP hierarchical analysis method, the corresponding weight is determined. Finally, a comprehensive water inrush risk assessment map of the roof of coal seam 3 in Lilou Coal Mine is obtained. Through the verification of the coal mine water inrush survey ledger over the years, it has been found that the evaluation results of the coal seam roof water inrush model are consistent with the actual situation. The evaluation results are reasonable and accurate, which can provide a reference basis for coal seam mining and water damage prevention and control in the future. [ABSTRACT FROM AUTHOR]

Large lifting equipment is used regularly in the maintenance operations of chemical plant installations, where safety controls must be carried out to ensure the safety of lifting operations. This paper presents a convolutional neural network (CNN) methodology, based on the PyTorch framework, to identify unsafe behavior among lifting operation drivers, specifically, by collecting 22,352 images of equipment lifting operations over a certain time period in a chemical plant. The lifting drivers' behavior was divided into eight categories, and a ResNet50 network model was selected to identify the drivers' behavior in the pictures. The results show that the proposed ResNet50 network model based on transfer learning achieves a 99.6% accuracy rate, a 99% recall rate and a 99% F1 value for the expected behaviors of eight lifting operation drivers. This knowledge regarding unsafe behavior in the chemical industry provides a new perspective for preventing safety accidents caused by the dangerous behaviors of lifting operation drivers. [ABSTRACT FROM AUTHOR]