MEMS Data-Driven Intelligent Identification of Rotation-Angle Response and Shear Band Position in Gravelly Soil Slopes

Identifying shear band locations is essential for precursor recognition and early warning of progressive failure in gravelly soil slopes. However, conventional displacement monitoring methods mainly capture macroscopic slope deformation and remain limited in detecting internal localized deformation and the spatial evolution of shear bands. To address this limitation, this study proposes an MEMS data-driven framework for predicting spatial rotation-angle responses and locating potential shear bands in gravelly soil slopes, with the aim of enhancing the perception of internal shear deformation and detecting potential instability zones. First, scaled laboratory model tests were conducted under different gravel contents, and MEMS sensors were embedded within the slope to measure cumulative rotation-angle responses during shear band formation. Second, based on a DEM model incorporating particle geometric morphology, the spatial differentiation of the rotation-angle field during shear band evolution was analyzed, and the experimental results were further validated. Finally, a shear band localization framework integrating PDL-GAN-based data augmentation with PCA + Gaussian regional rotation-angle field prediction was established. Potential shear band locations were then indirectly localized based on the positive–negative partitioning and abrupt amplitude changes in the predicted rotation angles. The results show that the DEM simulations agree well with the cumulative rotation-angle responses obtained from the laboratory tests, with mean absolute percentage errors of 9.79%, 6.03%, and 3.84% under the T1, T2, and T3 conditions, respectively. Within the shear band influence zone, the upper monitoring points mainly exhibit negative rotation-angle accumulation, whereas the lower monitoring points primarily show positive rotation-angle responses. A larger absolute rotation angle indicates a stronger controlling effect of the shear band on the corresponding monitoring point. The PCA + Gaussian model demonstrates strong overall performance in regional rotation-angle prediction, with MAE, RMSE, and CRPS values of 0.0803, 0.1024, and 0.0801, respectively. The model preserves the dominant deformation mode of the rotation-angle field and provides probabilistic prediction outputs. The proposed method enables the prediction of internal rotation-angle responses and facilitates the localization of potential shear band locations in gravelly soil slopes, providing data-driven technical support for precursor recognition and intelligent early warning of progressive slope failure.