Computer vision methods have been widely used in recent years for the detection of structural cracks. To address the issues of poor image quality and the inadequate performance of semantic segmentation networks under low-light conditions in tunnels, in this paper, infrared images are used, and a preprocessing method based on image fusion technology is developed. First, the DAISY descriptor and the perspective transform are applied for image alignment. Then, the source image is decomposed into high- and low-frequency components of different scales and directions using DT-CWT, and high- and low-frequency subband fusion rules are designed according to the characteristics of infrared and visible images. Finally, a fused image is reconstructed from the processed coefficients, and the fusion results are evaluated using the improved semantic segmentation network. The results show that using the proposed fusion method to preprocess images leads to a low false alarm rate and low missed detection rate in comparison to those using the source image directly or using the classical fusion algorithm.

The existing empirical methods of the seepage coefficient for clay have difficulty in parameter acquisition and are poor in calculation accuracy, and it is possible to find reasonable ones based on the mature empirical methods of coarse‐grained soil. Firstly, the permeation mechanism of clay was analysed including influencing factors, spatial process, and parameter calculation, and the ineffective and effective voids were defined; then the empirical methods of clay and coarse‐grained soil were summarised and listed. Secondly, clay was put equivalent to coarse‐grained soil according to bound‐water consolidation, and the parameter “equivalent void ratio” was introduced to establish the equivalent calculation methods. Finally, the liquid‐plastic limit method determining the volume of ineffective voids was explained, and the feasibility of equivalent calculation methods was evaluated by three examples. The results show that seepage, permeation, and effective permeation are three different concepts; groundwater permeates in clay via the effective void. For certain soil, the increasing sequence of permeability coefficients is the seepage coefficient, permeation coefficient, and effective permeation coefficient. Introduction of the “equivalent void ratio” unifies the calculation of the seepage coefficient for clay and coarse‐grained soil. The maximum of the bound‐water content is about 0.9 time the size of liquid limit. The Mesri equation and the equivalent calculation method of Terzaghi or Curson–Karman are suitable for calculating the seepage coefficient of clay for the closest results to experimental values.

Smoothed particle hydrodynamics (SPH) is a state-of-the-art numerical simulation method in fluid mechanics. It is a novel approach for modeling and comprehending complex fluid behaviors. In contrast to traditional grid-dependent techniques like finite element and finite difference methods, SPH utilizes a meshless, purely Lagrangian approach, offering significant advantages in fluid simulations. By leveraging a set of arbitrarily distributed particles to represent the continuous fluid medium, SPH enables the precise estimation of partial differential equations. This grid-free methodology effectively addresses many challenges associated with conventional methods, providing a more adaptable and efficient solution framework. SPH’s versatility is evident across a broad spectrum of applications, ranging from advanced computational fluid dynamics (CFD) to complex computational solid mechanics (CSM), and proves effective across various scales—from micro to macro and even astronomical phenomena. Although SPH excels in tackling problems involving multiple degrees of freedom, complex boundaries, and large discontinuous deformations, it is still in its developmental phase and has not yet been widely adopted. As such, a thorough understanding and systematic analysis of SPH’s foundational theories are critical. This paper offers a comprehensive review of the defining characteristics and theoretical foundations of the SPH method, supported by practical examples derived from the Navier–Stokes (N-S) equations. It also provides a critical examination of successful SPH applications across various fields. Additionally, the paper presents case studies of SPH’s application in tunnel and underground engineering based on practical engineering experiences and long-term on-site monitoring, highlighting SPH’s alignment with real-world conditions. The theory and application of SPH have thus emerged as highly dynamic and rapidly evolving research areas. The detailed theoretical analysis and case studies presented in this paper offer valuable insights and practical guidance for scholars and practitioners alike.