The accurate distribution of joints on the tunnel face is crucial for assessing the stability and safety of surrounding rock during tunnel construction. This paper introduces the Mask R-CNN image segmentation algorithm, a state-of-the-art deep learning model, to achieve efficient and accurate identification and extraction of joints on tunnel face images. First, digital images of tunnel faces were captured and stitched, resulting in 286 complete images suitable for analysis. Then, the joints on the tunnel face were extracted using traditional image processing algorithms, the commonly used U-net image segmentation model, and the Mask R-CNN image segmentation model introduced in this paper to address the lack of recognition accuracy. Finally, the extraction results obtained by the three methods were compared. The comparison results show that the joint extraction method based on the Mask R-CNN image segmentation deep learning model introduced in this paper achieved the best joint extraction effect with a Dice similarity coefficient of 87.48%, outperforming traditional methods and the U-net model, which scored 60.59% and 75.36%, respectively, realizing accurate and efficient acquisition of tunnel face rock joints. These findings suggest that the Mask R-CNN model can be effectively implemented in real-time monitoring systems for tunnel construction projects.

The conversion between the relaxation modulus and creep compliance is a traditional research topic in viscoelastic materials. Generally, different methods have been used to solve the numerical solution based on convolution theory. However, the initial relaxation modulus (relaxation modulus at t = 0) has been difficult to obtain. This paper aimed to propose a fast calculation method to derive the initial relaxation modulus from the creep compliance. First, three groups of uniaxial static creep tests of asphalt mixtures were conducted to determine the creep compliance of the experimental data. Then, the calculation of the initial relaxation modulus from the creep compliance by three inversion methods (midpoint method, approximate method, and Laplace numerical inversion method) was evaluated. The results indicate that approximate method and Laplace numerical inversion method cannot calculate the initial relaxation modulus value, and the calculation results of the midpoint method can only approach the exact value infinitely, for which calculating the relaxation modulus at 0.0005 s requires 2000 s. The results can only approach the exact value infinitely and take a lot of computing time. Finally, a fast calculation method for the initial relaxation modulus is proposed and verified by Laplace initial value theorem, and this method can directly derive a simple expression for calculating the initial relaxation modulus without requiring computational time. The proposed calculation methods of the initial relaxation modulus for various viscoelastic models were then put forward. The research results provide an effective tool for obtaining the initial relaxation modulus accurately.