Shale reservoir has an initial unloading effect during the natural uplift and erosion process, which causes the shale brittleness to change, affecting the design of the fracturing scheme. To consider this, the axial compression loading and confining pressure unloading experiment of shale is carried out, and then the influence of unloading rate on the mechanical parameters, failure characteristics, and the brittleness of rock are analyzed. What is more, a new evaluation method of brittleness characteristics that take the unloading effect into consideration is proposed. The conclusions are as follows: (1) The unloading rate has a weakening effect on the mechanical parameters, such as the destructive confining pressure and the residual strength of the samples. (2) The failure characteristics of shale specimens are a single shear failure in an oblique section under low unloading rate, and multiple shear zones accompanied with bedding fracture under high unloading rate. (3) The brittleness of shale samples is well verified by the brittleness index $B_{d1}$ and $B_{d2}$ during the loading path; nevertheless, it has shortage at the unloading path. This paper proposes a new brittleness evaluation method which can consider the influence of the different unloading rates and unloading points. Furthermore, there is a nice characterization between the brittleness damage and this method.

In tunnel construction, the prediction of the surrounding rock deformation is related to the construction safety and stability of the tunnel structure. In order to achieve an accurate prediction of the surrounding rock deformation in soft rock tunnel construction, a Long Short-Term Memory (LSTM) neural network is used to construct a prediction model of the vault settlement and the horizontal convergence of the upper conductor in soft rock tunnels. The crested porcupine optimisation (CPO) algorithm is used to realise the hyper-parameter optimisation of the LSTM model and to construct the framework of the calculation process of the CPO-LSTM model. Taking the soft rock section of the Baoshishan Tunnel as an example, the large deformation of the surrounding rock is measured and analysed in situ, and the monitoring data of arch settlement and superconducting level convergence are obtained, which are substituted into the CPO-LSTM model for calculation, and compared and analysed with traditional machine learning and optimisation algorithms. The results show that the CPO-LSTM model has an R² of 0.9982, a MAPE of 0.8595% and an RMSE of 0.1922, which are the best among all the models. In order to further improve the optimisation capability of the CPO, some improvements were made to the CPO and an Improved Crested Porcupine Optimiser (ICPO) was proposed. The ICPO-LSTM prediction model was established, and the ZK6 + 834 section was selected as a research object for comparison and analysis with the CPO-LSTM model. The results of the error analysis show that the prediction accuracy of the improved ICPO-LSTM model has been further improved, and the prediction accuracy of the model meets the requirements of guiding construction.

The failure of tailings dams has repeatedly occurred in China, which seriously threats eco-environment and social economy. The mechanical properties of non-saturated tailings are a matter of great concern, yet remain poorly understood. In this paper, engineering properties of non-saturated tailings are measured and complemented by analysis and interpretation from multiple perspectives. The results indicate that the soil–water characteristic curve, influenced by dry density, can be described with an appropriate model through parameter analysis. In order to calculate the stability of a typical tailings slope under different conditions, a new approach that considers the contribution of matric suction is elaborated in a sound theoretical framework.

It is of vital significance to accurately forecast the settlement of high fill subgrade, which is the foundation for disaster prevention and treatment of subgrade. According to the monitoring data of high fill subgrade, a novel model, called PSOMGVM model, based on particle swarm optimization (PSO) and Markov chain is proposed. Firstly, the typical characteristics of settlement curve are analyzed from the aspect of geomechanics theory and based on the grey theory, the grey Verhulst model (GVM) with unequal time‐interval is proposed. Then, according to the theory of Markov chain, the grey Verhulst model is built to revise the relative residuals of the GVM, in which the effects of volatility characteristics can be considered. Finally, the PSOMGVM model based on PSO algorithm and Markov chain is set up, which whitens the parameters of the grey interval. In order to demonstrate the fitness and the ability of the proposed model, five competing models are introduced to predict the settlement of the high fill subgrade of Xiangli Expressway in Yunnan Province. Through the analysis of APE, MAPE, and RMSE, it states that the accuracy and performance of the PSOMGVM model outperform the other five competing models for simulative and predictive periods.

The liquefaction of tailings is a common failure mode under earthquake actions. The traditional treatment measures of waste rubber have the disadvantages of environmental pollution and occupying soil resources. The combined treatment of waste rubber and tailings is very likely to have important engineering application and theoretical value, and the dynamic characteristics of the rubber‐tailings mixture (RTM) are essential and indispensable for handling them together. In this paper, the dynamic triaxial test was used to study the dynamic mechanical characteristics of the RTM. The test was divided into 5 groups with 54 valid samples. The effects of the rubber particle size, rubber content, consolidation pressure, pH value, and soaking time on the dynamic characteristics of the RTM were studied and discussed. The results show that the liquefaction cycle number of the RTM is 50% higher than that of tailings, and the particle cluster effect theory of the RTM is put forward. It will provide a theoretical basis and guidance for the treatment of the waste rubber and tailings.