An internal geomembrane (GMB)–clay seepage control system is an important form of seepage control structure for rockfill dams. In order to investigate the stress and deformation characteristics of GMB in GMB–clay core-wall rockfill dams (GMCWRD) under different construction and operation conditions, the stress and deformation fields of GMCWRDs were calculated by numerical simulation under a variety of working conditions. The stress and deformation characteristics of the dam and GMB during the impoundment period were investigated, and the influences of the spreading thickness of the clay core-wall and the location of the GMB defects and hydraulic head on the stress and deformation of the GMB were analyzed. The results show that the maximum tensile strain of the GMB upstream of the clay core-wall during the impoundment period occurs at the anchorage of the GMB and the concrete cut-off, with a maximum tensile strain of 2.70%. With the increase in the spreading thickness of the clay core-wall, the maximum tensile stress and strain of the GMB fluctuated. Under the dam construction and foundation conditions in this paper, when the spreading thickness of the clay core-wall was 2 m, the tensile stress and strain of GMB were at the lowest level. As the defect location of the GMB decreases, the phreatic line of the dam gradually increases, and the seepage discharge of the dam and the tensile strain of the GMB gradually increase, with the maximum tensile strain of 3.98%. The maximum deformation of the GMB in each case is much smaller than the maximum elastic deformation range of the selected PVC GMB, and the conclusion of the study provides a certain scientific basis for the design and construction of the seepage control of the core rockfill dam.

To address the critical challenge of low diagnostic accuracy in multistate bearing fault diagnosis caused by inefficient discriminative feature extraction under varying operating conditions, this paper proposes a novel Parameter-weighted Viridis Image Encoding (PVIE) method. Unlike conventional image encoding techniques (e.g., GADF, GASF, MTF, RP) that often suffer from high computational complexity and limited feature separability in complex scenarios, PVIE integrates Variational Mode Decomposition (VMD) with a newly designed Parameter-weighted Euler Difference Feature Extraction (PWEDFE) module. This module explicitly enhances the nonlinearity and periodicity of fault signatures, mapping them into lightweight 2D feature images via Viridis Feature Value Mapping (VFVM). Extensive experiments on two benchmark datasets demonstrate that PVIE achieves exceptional diagnostic accuracies of 99.92 % and 99.74 %, respectively. Compared to state-of-the-art encoding methods, PVIE improves average accuracy by 21.06 % to 39.78 % while reducing diagnostic time by 53.3 %, significantly outperforming existing approaches in both accuracy and efficiency. Furthermore, the method exhibits robust performance under strong noise interference and small-sample scenarios. These results confirm that PVIE offers a substantial advancement over current research by providing a more discriminative, lightweight, and robust solution for real-time industrial fault diagnosis.