Due to the intrinsic complexity, there has been no widely accepted mechanics-based estimation model of the shear performance of Fiber-Reinforced Polymer (FRP)-reinforced concrete beams. Capitalizing on a large amount of previous experimental data, data-driven machine learning (ML) models could be potentially suitable for addressing this problem. In this paper, four existing shear design provisions are reviewed and four typical ML models are analyzed. The accuracy of codified methods and ML models are compared and analyzed based on our established extensive database of FRP-reinforced concrete beams with rectangular cross sections. A series of artificially selected features considering the shear-carrying mechanisms of FRP-reinforced beams are incorporated into the proposed ML models to show their influence on the model validity. Bayesian optimization is utilized to automatically tune the hyperparameters of different ML models. Compared to the most satisfying codified predictions from CSA S806, the best ML model, XGBoost, can provide more accurate and consistent predictions for the database, with R² enhanced by 15% and the MAE and RMSE reduced by 59% and 52%, respectively. With the selected features based on domain knowledge, the performance of ML models is further enhanced, shown by the most important features being the added ones. With outstanding performance on a large database and singular test, the ML approaches have great potential in guiding the shear design of FRP-reinforced concrete.

In this paper, the formation mechanism of a slightly inclined bedding mudstone landslide in the overlying mountain of the coal mining subsidence area of the Tanshan Coal Mine in Ningxia, China, is studied. By means of geotechnical investigation, indoor geotechnical tests, theoretical analysis and other technical means, we find the geological environment background of the study area and obtain the physical and mechanical property indexes of the mining landslide in the Tanshan Coal Mine. By combining the numerical simulation of discrete elements and finite elements, the macro deformation and failure law of the mining mudstone landslide and the displacement and stress nephogram of the failure process are discussed. The results show that the slightly inclined bedding mudstone landslide in the Tanshan Coal Mine is 850 m long from east to west, 500 m wide from north to south and 10,875,000 m³ in volume. It is composed of Jurassic mudstone and is a traction landslide caused by the coal mining subsidence area. The formation of the landslide is affected by internal factors and inducing factors. The internal factors are mainly geotechnical types and engineering geological properties, and the inducing factors are mainly coal mining activities and rainfall. By analyzing and summarizing the calculation process of the slope model prior to the landslide in 2D-Block and GeoStudio numerical simulation software, the sliding process of the slightly inclined bedding mudstone landslide in the Tanshan Coal Mine is divided into four stages: slope creep, slope deformation, landslide movement and landslide accumulation. GeoStudio software is used to calculate the stability of the Tanshan Coal Mine landslide under natural and rainfall conditions. The landslide is in a stable state under natural conditions and is basically stable under rainfall conditions. By comparing the calculation results of the limit equilibrium method and the finite element limit equilibrium method, we find that the calculated stability coefficient is more accurate when the appropriate constitutive model is selected. The research results have important reference significance for the prevention and control of the gently inclined bedding mudstone landslide of the overlying mountain in the coal mining subsidence area of the Loess Plateau.