Detecting pavement cracks is critical for road safety and infrastructure management. Traditional methods, relying on manual inspection and basic image processing, are time-consuming and prone to errors. Recent deep-learning (DL) methods automate crack detection, but many still struggle with variable crack patterns and environmental conditions. This study aims to address these limitations by introducing the MaskerTransformer, a novel hybrid deep learning model that integrates the precise localization capabilities of Mask Region-based Convolutional Neural Network (Mask R-CNN) with the global contextual awareness of Vision Transformer (ViT). The research focuses on leveraging the strengths of both architectures to enhance segmentation accuracy and adaptability across different pavement conditions. We evaluated the performance of the MaskerTransformer against other state-of-the-art models such as U-Net, Transformer U-Net (TransUNet), U-Net Transformer (UNETr), Swin U-Net Transformer (Swin-UNETr), You Only Look Once version 8 (YoloV8), and Mask R-CNN using two benchmark datasets: Crack500 and DeepCrack. The findings reveal that the MaskerTransformer significantly outperforms the existing models, achieving the highest Dice Similarity Coefficient (DSC), precision, recall, and F1-Score across both datasets. Specifically, the model attained a DSC of 80.04% on Crack500 and 91.37% on DeepCrack, demonstrating superior segmentation accuracy and reliability. The high precision and recall rates further substantiate its effectiveness in real-world applications, suggesting that the MaskerTransformer can serve as a robust tool for automated pavement crack detection, potentially replacing more traditional methods.

To address the challenge of real-time adjustment for unit explosive consumption in underwater drilling and blasting operations, this study proposes a predictive approach for estimating the uniaxial compressive strength (UCS) of rock and determining the optimal explosive unit consumption based on borehole drilling parameters. Utilizing drilling pressure(F), rotational pressure(N), and drilling rate(V) as principal borehole drilling parameters, a linear regression analysis was performed to derive a predictive equation correlating these variables with the rock′s UCS. Based on the correspondence between explosive unit consumption and rock firmness coefficient, and incorporating depth correction factors, the analysis reveals consistent consumption patterns under identical water depth conditions. For sandstone and shale formations, explosive consumption remains consistent across different depths: 0.65~1.00 kg/m at 0 meters, 0.88~1.36 kg/m at 10 m, 0.93~1.43 kg/m at 20 m, and 0.94~1.45 kg/m at 50 m. Similarly, siltstone and mudstone exhibit identical consumption rates: 0.25~0.65 kg/m at 0 m, 0.34~0.88 kg/m at 10 m, 0.36~0.93 kg/m at 20 m, and 0.36~0.94 kg/m at 50 m. The proposed real-time adjustment method facilitates dynamic optimization of explosive specific charge, offering practical guidance for minimizing explosive consumption and enhancing blast efficiency in underwater drilling and blasting operations.

Accurate acquisition of blasting vibration signals is essential for analyzing the harmful effects of blasting operations. However, geological conditions, electromagnetic interference, and instrument errors can introduce significant high-frequency noise into the collected signals, leading to distortion and inaccurate data interpretation. To address this issue, a signal decomposition algorithm based on Ospley Optimization Algorithm(OOA) is proposed to optimize Variational Mode Decomposition(VMD). Multiscale Permutation Entropy(MPE) is also employed to construct a noise reduction model for tunnel blasting vibration signals. OOA is iteratively applied to determine the optimal VMD parameters(K & α) and obtain the intrinsic mode formula(IMF) using the maximum information coefficient as the fitness function. The MPE values of each decomposed signal are then used to identify the noise components, which are removed to reconstruct the denoised signal. This coupled algorithm was applied to analyze the blasting effects in Dashan Tunnel, Yunnan Province. The results demonstrate that the proposed optimization algorithm effectively decomposes the signal and eliminates noise without significantly affecting the low-frequency energy. The OOA-VMD denoising method′s performance is superior to the complete ensemble empirical mode decomposition(CEEMD) and conventional VMD algorithm, thereby verifying its reliability.

To address the instability problem of shallow-buried tunnel with unsymmetrical pressure under blasting, the potential energy equation of surrounding rock was derived by considering both blasting damage and water weakening effect. Using the cusp catastrophe theory and its calculation method, a catastrophe instability criterion of surrounding rock mass in a shallow-buried tunnel with unsymmetrical pressure under blasting was established. Then, the effects of water weakening, blasting damage and unsymmetrical pressure on the instability of the surrounding rock mass were discussed. Taking Dayangan tunnel in the national high-speed G5615(Tianbao-Malipo section) as an example, a catastrophe criterion k of surrounding rock mass under different working conditions was calculated according to the physical and mechanical parameters of surrounding rock and the results of the field acoustic wave test. Meanwhile, a shallow-buried tunnel's surrounding rock stability state with unsymmetrical pressure was determined. The results show that the necessary condition for abrupt instability in shallow-buried tunnels with biased pressure under blasting is the abrupt failure criterion k<1, indicating a potential state of abrupt instability. The degree of bias pressure is the critical internal factor affecting tunnel instability surrounding rock mass. Additionally, the greater the degree of bias pressure, the more prone the tunnel is to sudden instability. The practical evaluation results are consistent with the field observations, verifying the practicability and validity of the criterion.

The seismic wave signal acquisition will result in the mixed noise in the measured signal due to the monitoring environment, test system and other factors, and the existence of noise will lead to the distortion of the time-frequency analysis results of the signal Hilbert-Huang Transform. There are two reasons. One is that the empirical mode decomposition(EMD) algorithm will obtain the intrinsic mode function(IMF) component with modal confusion phenomenon when processing the blasting seismic wave signal containing noise; The other reason is that because the Hilbert transform is constrained by the Bedrosian theorem, which will produce negative instantaneous frequencies when dealing with modal confusion components. These lead to huge analytical errors. In order to obtain real blasting vibration properties, HHT should be improved. Complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN) can be obtained by adding adaptive noise signal to EMD. Then normalized Hilbert transform is performed on the IMF obtained by CEEMDAN, and an improved normalized Hilbert transform(INHT) is obtained. Through the above two steps, the CEEMDAN-INHT time-frequency analysis algorithm can be established. In order to verify that the algorithm can effectively improve the time-frequency analysis accuracy of the noise-containing blasting seismic wave vibration signal, a comparative study on the time-frequency analysis of the HHT and CEEMDAN-INHT noise-containing simulated vibration signals is carried out. Finally, CEEMDAN-INHT is used in the time-frequency analysis of blasting seismic wave signals in an underground cavern, and it is found that the algorithm can effectively overcome the inherent mode confusion of EMD, and at the same time obtain the time-frequency-energy characteristic parameters reflecting the real blasting vibration attributes. It is of practical significance to carry out resonance analysis of blasting excavation in caverns from the perspective of frequency and energy, and to realize blasting seismic wave hazard control.