Rubberized concrete (RC) has attracted more attention these years as it is an economical and environmental‐friendly construction material. Normally, the uniaxial compressive strength (UCS) of RC needs to be evaluated before application. In this study, an evolutionary random forest model (BRF) combining random forest (RF) and beetle antennae search (BAS) algorithms was proposed, which can be used for establishing the relationship between UCS of RC and its key variables. A total number of 138 cases were collected from the literature to develop and validate the BRF model. The results showed that the BAS can tune the RF effectively, and therefore, the hyperparameters of RF were obtained. The proposed BRF model can accurately predict the UCS of RC with a high correlation coefficient (0.96). Furthermore, the variable importance was determined, and the results showed that the age of RC is the most significant variable, followed by water‐cement ratio, fine rubber aggregate, coarse rubber aggregate, and coarse aggregate. This study provides a new method to access the strength of RC and can efficiently guide the design of RC in practice.

Predictive model and formula of jacking force has been well-established for circular pipe jacking in the past decades. However, the frictional mechanism of pipe–soil–slurry and jacking force prediction of rectangular pipe jacking has not well been understood. Nowadays, the rectangular pipe jacking is widely used, because of its over 20% larger effective usable area than that of circular pipe as underground facilities, with the same cross-sectional area. Nevertheless, the corresponding prediction models of thrust of rectangular pipe jacking are lacking. In order to further understand the frictional mechanism of slurry rectangular pipe jacking, five classical analytical calculation models have been proposed, considering the pipe–soil–slurry interaction, and prediction formulas are obtained. Then, 3D finite difference method was introduced to estimate the jacking force by using FLAC3D. Finally, three case studies have been carried out to validate the proposed models. The results show that the numerical and theoretical results have good consistency, and what is more, the measured jacking force can be well included within the ranges of analytical models presented in this paper, which can improve the thrust prediction of rectangular pipe jacking.

Roadway stability in extremely soft coal mass is a typical challenge in deep underground mines, as the most widely adopted support structure such as rock bolting, compound support system normally fails. This paper proposed a novel prereinforcement method for coal roadway, that is, jet grouting (JG) technique, to improve the quality of surrounding soft coal mass and form a stable support structure namely jet grouted coalcrete. The field and laboratory tests were conducted for evaluating the applicability of JG and the mechanical parameters of coalcrete. A numerical model was verified by comparing the calculated results with field measurements. According to the confirmed model, three typical JG support schemes were performed to assess the roadway stability after JG. The results showed that the proposed JG schemes can reduce the deformation and failure zone of the roadway and optimize the stress states around the roadway. The mechanism related to these advantages was investigated. This study provides a promising idea for supporting soft coal roadway in deep underground coal mines, which can promote the JG application in the field.

In maintaining the efficiency of coal mining, the stability of roadway plays a significant role, as it is closely related to the production of coal and the safety of personnel. In deep underground coal mines, the rheological deformation of roadway normally occurs, which affects its service life. To address this problem, in this paper, a novel high-efficiency Jet Grouting (JG) technique was presented, and its control effect on roadway stability was investigated. A creep test of a coal specimen in a laboratory scale was performed, and its creep behavior was revealed. The rheology of the coal mass surrounding the roadway was further analyzed according to the field-monitoring results of roadway deformation. A time-dependent numerical model with a Burger-creep visco-plastic model (CVISC) was established and validated by comparing the calculated displacement with in-situ measurement. The JG technique was tested in the field, and its applicability and practicability were confirmed. According to the validated model and field test results of JG, a numerical model with CVISC by JG support was established to analyze the effect of JG on the roadway. The results showed that the JG support can effectively reduce roadway deformation, optimize stress conditions, and reduce the extent of the plastic zone around the roadway. The rheological properties of the soft coal roadway were constrained and long-term stability was ensured. This pioneering work can guide the application of JG for the stability control of roadways and promote the sustainability of coal mining efficiently.