The influence of acid solution and immersion time on the physicomechanical properties of sandstone is investigated. Uniaxial compression tests on sandstone samples are conducted to determine the variations of relative mass, deformation, and strength characteristics of sandstone subjected to different pH sulfuric acid corrosion values. The changes of pH and Mg²⁺ and Ca²⁺ concentration of immersion solutions are monitored during soaking. The corrosion mechanism of sandstone attacked by the acid solution is discussed with the results of SEM tests. Based on the nondestructive CT scanning test, the damage variables of acid‐corroded sandstone are deduced, and the damage degree of sandstone is quantitatively analyzed. The results indicate that the deformation characteristics of sandstone samples under acid attack are characterized by the softening of rock, and the softening degree gradually increases with the increase of the acidity and the soaking time. The peak strength of sandstone samples declines as soaking time extends. The chemical effects lead to a large amount of dissolution of the rock mineral assemblage, resulting in the large‐scale development of the pores inside the rock, which changes the macroscopic mechanical properties. The damage variables of acid corrosion sandstone based on CT numbers are deduced, and the quantitative relationship between damage variables and immersion time is established, which provides a basis for constructing a damage constitutive model of sandstone in the acidic environment.

With the rise of the fourth industrial revolution, traditional methods of analyzing investment have been transformed into intelligent methods under big data and the Internet of Things. This has created a new approach to solving practical engineering problems. This paper examines the formation and evolution of the application of inversion theory in tunnel and underground engineering, summarizing research progress using traditional and intelligent inversion analysis methods to identify three types of target unknown quantities in tunnels and underground projects: initial ground stress, support structure load, and tunnel characteristic parameters. It also offers an outlook on how to optimize inversion analysis methods to solve more challenging and complex tunneling problems in the context of informatization, digitalization, and intelligence. In the current research process of tunnel and underground space engineering problems, the inversion theory system has been improved, but inversion analysis methods still face many challenges. These include the low reliability of initial ground stress inversion under complex geological conditions, the lack of indicators to objectively evaluate the accuracy of inversion analysis, and the high costs of intelligent inversion analysis means. Moving forward in the context of big data and the information era, the future development direction for inversion theory and inversion methods in tunnel and underground space engineering is to combine new monitoring technology, computer vision technology, and simulation analysis technology to establish multifaceted intelligent inversion analysis models.

With the advent of the era of big data and information technology, deep learning (DL) has become a hot trend in the research field of artificial intelligence (AI). The use of deep learning methods for parameter inversion, disease identification, detection, surrounding rock classification, disaster prediction, and other tunnel engineering problems has also become a new trend in recent years, both domestically and internationally. This paper briefly introduces the development process of deep learning. By reviewing a number of published papers on the application of deep learning in tunnel engineering over the past 20 years, this paper discusses the intelligent application of deep learning algorithms in tunnel engineering, including collapse risk assessment, water inrush prediction, crack identification, structural stability evaluation, and seepage erosion in mountain tunnels, urban subway tunnels, and subsea tunnels. Finally, it explores the future challenges and development prospects of deep learning in tunnel engineering.

The 28 days cured cement mortar samples were soaked in HCl (pH = 1 and 2) and H₂O (pH = 7) solutions for 90 days. By monitoring the ion concentration of H⁺ and Ca²⁺ and measuring the changes in weight loss, longitudinal wave velocity, and uniaxial compressive strength values of the corroded mortar, the physicochemical and mechanical properties of the mortar specimens were studied. Experimental results indicate that the process of the mortar sample subjected to HCL erosion has apparent stage characteristics. In the initial stage of corrosion, the chemical reaction increased the porosity of the specimen, which leads to the decrease of longitudinal wave velocity of the samples. At the same time, the corrosion solution continuously penetrates into the mortar pore system, which leads to the increase of the mass, and it is considered that the diffusion process plays a leading role during this period. Moreover, the colloidal compounds generated by the chemical reaction can not only fill the pore space but also block the continuous reaction, which led to the increase of the longitudinal wave velocity of the specimen. With the prolonging of corrosion time and infiltration path, the pH value and the concentration of Ca²⁺ tend to be stable, the diffusion action is weakened, and the chemical reaction is continuous, which led to the decrease of the mass and wave velocity gradually. It is considered that the chemical reaction plays a leading role in this process. Based on the induction and analysis of the test results, a generalized porosity model regarding the increase of the porosity and the decrease of effective bearing area of the mortar sample was proposed. The relation between the uniaxial compressive strength and the corrosion time of the corroded mortar is deduced, and the unknown parameters are determined based on the regression analysis of the test data.

During the excavation process of a large-span variable cross-section of a tunnel, the deformation and stress characteristics of the surrounding rock supporting the structure are complex, and construction control is difficult. Based on an actual tunnel project, the mechanical effect and deformation characteristics of the surrounding rock and support structure of a large-span variable cross-section tunnel during its excavation and support process were studied via numerical simulation. The construction method, using the bench method to excavate and set up the transition section in the variable cross-section, was proposed. Based on the numerical simulation results, two optimized excavation schemes were proposed and analyzed to address the construction method conversion problems in constructing large-span variable cross-section tunnels. The rationality of the optimized construction scheme was verified through a comparison with field monitoring data. The research results show that the three-bench temporary inverted arch method supported by the temporary vertical portal frame has good applicability in constructing the large-span variable cross-section tunnel. This scheme can effectively control the stress concentration and excessive deformation of the surrounding rock in the large-span variable cross-section tunnel. The numerical simulation results agree with the field monitoring data, which verifies the rationality of analyzing the construction mechanical effects of variable cross-section tunnels and selecting construction schemes through numerical simulation. The research results can provide reference for the construction of similar tunnel projects.