Transmission towers located above mined-out areas may experience collapse or instability due to mining-induced ground subsidence and deformation, which poses significant risks to the safe operation of power transmission lines. To clearly evaluate the deformation resistance and failure threshold of transmission towers under mining-induced ground deformation, this article examines a typical 220 kV self-supporting transmission tower located in a mining area of Northern Shaanxi Province through a detailed three-dimensional finite element model constructed and simulated using ANSYS 2022. The mechanical response and failure process of the tower structure were systematically simulated under five typical deformation conditions: tilt, horizontal compression, horizontal tension, tilt–compression, and tilt–tension. The results indicate that under individual deformation conditions, the critical deformation values of the tower are 35 mm/m for tilt, 10 mm/m for horizontal compression, and 8 mm/m for horizontal tension, demonstrating that the structure is most sensitive to horizontal tensile deformation. Under combined deformation conditions, the critical deformation values for the combined tilt–compression and tilt–tension conditions exhibited a marked reduction, reaching 8 mm/m and 6 mm/m. Compared to individual deformation conditions, transmission towers demonstrate a significantly higher susceptibility to structural failure under combined deformation conditions. The displacement at the tower head and the tower tilt angle exhibit a linear positive correlation with the values of ground surface deformation. Under individual deformation conditions, the tilt of the tower was approximately 0.903 times the tilt deformation value and 0.089 times the values of horizontal compression and tension deformation, indicating that tilt deformation exerts a more pronounced influence on the inclination of the tower. Under combined deformation conditions, the tilt of the tower reached approximately 0.981 times that of the tilt–compression deformation value and 0.829 times that of the tilt–tension deformation value. Compared to the tower tilt induced individually by horizontal compression or tension deformation, the tilt under combined deformation conditions demonstrated a significantly greater value. Under mining-induced ground deformation, a redistribution of support reactions occurs, exhibiting either nonlinear or linear increasing trends depending on the type of deformation. The findings of this article provide a theoretical basis and data support for disaster prevention and control, safety evaluation, and structural design of transmission lines in mining areas.

Given the severe water hazard in the coal seam roof of the Binchang mining area, existing research methods still primarily rely on traditional approaches such as empirical formula and numerical simulation—resulting in insufficient accuracy and convenience in predicting the height of the water-conducting fracture zone (WCFZ). By comprehensively considering three influencing factors—mining thickness, mining depth, and working face length—a data-driven approach was employed to construct a multiple nonlinear regression prediction model and a Convolutional Neural Network (CNN) prediction model based on 27 sets of measured data. Both models were subsequently applied to the ZF1403 and ZF1405 working faces in the Yadian coal mine. The results indicate that when considering only single factor of mining thickness, the coefficient of determination (R²) value of the multiple nonlinear regression model was 0.64. When considering all influencing factors, R² improved to 0.84. The mean absolute percentage error (MAPE) of multiple nonlinear regression model was 7.52%. The established CNN model achieved a R² of 0.97, a root mean square error (RMSE) of 9.78, and a MAPE of 4.67%. Compared to the Back Propagation Neural Network model, the prediction accuracy of the CNN model was significantly improved. The relative prediction errors of the developed height of WCFZ in the ZF1403 and ZF1405 working faces at Yadian mine were 6.30% and 2.54% for the multiple nonlinear regression model, respectively, and 0.97% and 3.15% for the CNN model, respectively. Both models met practical engineering requirements. This paper can provide reliable technical support for the prediction of water-conducting fracture zone height under mining conditions similar to the Binchang mining area.