Reservoir water-level fluctuations periodically alter the physical and mechanical properties of accumulation deposits in the bank slope zone, potentially triggering geological hazards such as collapses and landslides. This study developed an original laboratory mechanical testing system to systematically investigate the evolution of deformation and shear strength parameters in these accumulation deposits throughout the reservoir operation period. Tests conducted on the accumulation deposits in the Baijiabao bank slope demonstrate that under the coupled effects of anisotropic stress and cyclic wet–dry conditions, the compression modulus, cohesion, and internal friction angle decrease significantly, by 10.6%, 11.4%, and 13.2%, respectively. As the number of wet–dry cycles increases, the rate of reduction in these parameters gradually diminishes. Between the second and fourth cycles, the decreases in compression modulus, cohesion, and internal friction angle were 9.7%, 8.6%, and 6.9%, respectively. Beyond the eighth cycle, the values of these parameters stabilize with minimal further change.
Cracks serve as a critical indicator of tunnel structural degradation. Manual inspections are difficult to meet engineering requirements due to their time-consuming and labor-intensive nature, high subjectivity, and significant error rates, while traditional image processing methods exhibit poor performance under complex backgrounds and irregular crack morphologies. To address these limitations, this study developed a high-quality dataset of tunnel crack images and proposed an improved lightweight semantic segmentation network, LiteSqueezeSeg, to enable precise crack identification and quantification. The model was systematically trained and optimized using a dataset comprising 10,000 high-resolution images. Experimental results demonstrate that the proposed model achieves an overall accuracy of 95.15% in crack detection. Validation on real-world tunnel surface images indicates that the method effectively suppresses background noise interference and enables high-precision quantification of crack length, average width, and maximum width, with all relative errors maintained within 5%. Furthermore, an integrated intelligent detection system was developed based on the MATLAB (R2023b) platform, facilitating automated crack feature extraction and standardized defect grading. This system supports routine tunnel maintenance and safety assessment, substantially enhancing both inspection efficiency and evaluation accuracy. Through synergistic innovations in lightweight network architecture, accurate quantitative analysis, and standardized assessment protocols, this research establishes a comprehensive technical framework for tunnel crack detection and structural health evaluation, offering an efficient and reliable intelligent solution for tunnel condition monitoring.