The mechanical characteristics of transversely isotropic rocks are significantly different under various levels of inclination, and it is difficult to describe exactly the mechanical behaviour of transversely isotropic rocks. Assuming that rock consists of a great deal of microelements, and the microelement strength controlled by Mohr–Coulomb criterion follows the log normal distribution. The elastic modulus is used to reflect the anisotropy of rock, and the weak patches stiffness model is verified and employed to depict the variation of elastic modulus with different inclination angle. Based on basic damage mechanics theory and statistical method, a nonlinear statistical empirical model for transversely isotropic rocks is proposed under uniaxial compressive condition. In order to verify the correctness of the proposed model, comparison analyses between predicted results and experimental data taken from published literature are carried out, which have good consistency. Finally, the discussions on the influences of the distribution parameters ��, �� and elastic modulus with different inclination angle, ����, on proposed model is offered.

Ground settlement during and after tunnelling using TBM results in varying dynamic and static load action on the geo-stratum. It is an undesirable effect of tunnel construction causing damage to the surface and subsurface infrastructure, safety risk, and increased construction cost and quality issues. Ground settlement can be influenced by several factors, like method of tunnelling, tunnel geometry, location of tunnelling machine, machine operational parameters, depth & its changes, and mileage of recording point from starting point. In this study, a description and evaluation of the performance of the arti?cial neural network (ANN)was undertaken and a comparison with multiple linear regression (MLR) was carried out on ground settlement prediction. The performance of these models was evaluated using the coefficient of determination R2, root mean square error (RMSE) and mean absolute percentage error (MAPE). For ANN model, the R2, RMSE and MAPE were calculated as 0.9295, 4.2563 and 3.3372, respectively, while for MLR, the R2, RMSE and MAPE, were calculated as 0.5053, 11.2708, 6.3963 respectively. For ground settlement prediction, bothANNandMLRmethodswere able to predict significantly accurate results. It was further noted that the ANN performance was higher than that of the MLR.