Faulting refers to the common and significant distress in Jointed Plain Concrete Pavement (JPCP), which has an adverse impact on the pavement roughness. Nevertheless, the existing fault prediction models continue to heavily rely on conventional linear regression techniques or basic machine learning approaches, which leaves room for improvement in training efficiency and interpretability. To enhance training efficiency and accuracy, this study developed five novel faulting prediction models. These models are based on five basic machine learning algorithms: Random Forest (RF), Additive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LightGBM), and Categorical Boost (CatBoost), combined with the tree-structured Parzen estimator (TPE). The five models are TPE-RF, TPE-AdaBoost, TPE-GBDT, TPE-LightGBM, and TPE-CatBoost. In addition to selecting the best-performing model, this study incorporated the Shapley Additive Explanation (SHAP) technique and developed TPE-SHAP-CatBoost to improve the interpretability of the model’s predictions. The process involved extracting historical data on pavement performance, including 17 variables, from the Long-Term Pavement Performance (LTPP) database for 160 instances of observation. Firstly, the Boruta method was used to identify the final set of input variables. Secondly, the TPE technique, which is a Bayesian optimization method, was applied to automatically select the optimal hyperparameters for the base models. Finally, SHAP was used to provide both global and local explanations of the model’s outputs. The results indicate that the TPE-CatBoost model achieves the highest accuracy with an R² value of 0.906. Furthermore, the TPE-SHAP-CatBoost model identified the primary factors influencing faulting by incorporating SHAP and provided explanations of the model’s results at both the global and local levels. These research findings highlight the ability of the proposed model to accurately predict faulting, providing precise and interpretable guidance for pavement maintenance while reducing workload for pavement engineers in data collection and management.

To study the energy evolution law and damage constitutive behavior of high-strength concrete based on the conventional triaxial compression tests of C60 and C70 high-strength concrete subjected to five different confining pressures, the failure characteristics of high-strength concrete are analyzed at different confining pressures, and the evolution of the input energy density, elastic strain energy density, and dissipation energy density with axial strain and confining pressure are quantified. Combined with a continuous damage theory and non-equilibrium statistical method, the ratio of dissipation energy density of concrete to dissipation energy density corresponding to peak stress is used as the mechanical parameter. Assuming that the mechanical parameter obeys the Weibull distribution laws, the statistical damage variable describing the damage characteristics of concrete were derived. According to the Lemaitre strain equivalent principle, the damage variable is introduced to the generalized Hooke law to establish the statistical damage constitutive model for high-strength concrete. The results show that: (1) the input energy density and dissipation energy density increases with the increase of axial strain, while the elastic strain energy density increases first and then decreases as a function of the axial strain and reaches the maximum value at the peak stress; (2) the input, elastic strain, and dissipated energy densities corresponding to the peak stress of the two high-strength concretes all increase as a function of confining pressure, and the elastic strain energy density corresponding to the peak stress increases linearly as a function of the confining pressure; (3) the statistical damage constitutive model results of C60 and C70 high-strength concrete are in good agreement with the test results, and the average relative standard deviations are only 3.64% and 3.99%. These outcomes verify the rationality and accuracy of the model.

The selection of an appropriate slurry ingredient and its percentage ratio is a vital and necessary task for engineers in slurry pipe jacking operations. However, traditional bentonite grouting materials are difficult to degrade because of their single and non-biodegradable composition. Nowadays crosslinked polymers have been widely considered due to their excellent performance and application in engineering practices, which enlighten novel polymer slurry in pipe jacking. This study innovatively proposed using boric acid crosslinked polymers added into polyacrylamide bentonite slurry, which not only solves the shortcomings of traditional grouting materials but also meets the general working performance requirements. The new slurry’s funnel viscosity, filter loss, water dissociation ratio and dynamic shear were tested according to an orthogonal experiment. Single factor range analysis was conducted to identify the optimal mix proportion based on an orthogonal design, and the formation behavior of mineral crystals and microstructure characteristics were evaluated by X-ray diffraction and scanning electron microscopy respectively. According to the results, guar gum and borax form a dense boric acid crosslinked polymer through cross-linking reaction. The internal structure grew tighter and more continuous as the crosslinked polymer concentration grew. It improved the anti-permeability plugging action and viscosity of slurries by 36.1~94.3%. The optimal proportions of sodium bentonite, guar gum, polyacrylamide, borax, and water were 10%, 0.2%, 0.25%, 0.1%, and 89.45% respectively. All these works indicated that the improvement of slurry composition by using boric acid crosslinked polymers was feasible.

In slurry pipe jacking, lubricant slurry is commonly used to sustain against the displacement and pressure of the overcut area and reduce the interface friction of pipelines. Therefore, a reasonable grouting pressure should ensure the stability of surrounding soils, which is raised as a new method in this study. Not only ensure the grouting pressure is not too small to support the stratum effectively and reduce the frictional resistance but also ensure that the grouting pressure will not be too large to produce excessive deformation and affect the surrounding environment. First of all, the influence of grouting pressure on the stability of surrounding soil is analyzed, and the mechanical model of slurry grouting expansion is established. Then, the minimum grouting pressure is designed from the critical balance between radial expansion tension by grouting and loose earth pressure by jacking excavation, and the maximum grouting pressure is designed from the critical expansion pressure caused by grouting splitting. Finally, the rationality of grouting pressure design is proved by the engineering example of a slurry pipe-jacking project near Haikou Meilan Airport and on-site GPR detection test. All these work aims to raise a new theoretical solution of grouting pressure and provide theoretical reference for similar projects.

With the development of coal resource extraction and wellbore construction proceeding towards deeper depths, the stability of drilling wellbore structures has become increasingly severe, even posing a barrier to the use of drilling method technology in deep wellbore construction. To address this issue, this study raised an optimized constraints method involving pre-throwing cement slurry to the bottom before wellbore decent, altering bottom constraints. Firstly, the critical depth and instability criterion of this optimized method was derived by catastrophe theory. Subsequently, the role of single-factor and multi-factor sensitivity analyses on critical depth was discussed. The engineering effects of optimized constraint methods were contrasted and examined in several drilling projects. Finally, the characteristic values of real engineering were computed using numerical techniques and ABAQUS2020 software, and the efficacy of optimization approaches was examined and validated. The results revealed that the critical depth increased by 41.39 ± 5%. The influence factors described in order of the degree were the counterweight water height, the elastic modulus, the thickness of the wellbore, and the self-weight of the wellbore, sequentially. The conclusion on structural stability between the numerical calculation solution and theoretical calculation solution was completely the same. The optimized constraints method can effectively improve the stability of the wellbore structure.