With accelerated urbanization and aging infrastructure, the safety and durability of civil engineering structures face significant challenges, making structural health monitoring (SHM) a critical approach to ensuring engineering safety. The Bayesian network, as a probabilistic reasoning tool, offers a novel technological pathway for SHM due to its strengths in handling uncertainties and multi-source data fusion. This study systematically reviews the core applications of the Bayesian network in SHM, including damage prediction, data fusion, uncertainty modeling, and decision support. By integrating multi-source sensor data with probabilistic inference, the Bayesian network enhances the accuracy and reliability of monitoring systems, providing a theoretical foundation for damage identification, risk early warning, and optimization of maintenance strategies. The study presents a comprehensive review that systematically unifies the theoretical framework of BN with SHM applications, addressing the gap between probabilistic reasoning and real-world infrastructure management. The research outcomes hold significant theoretical and engineering implications for advancing SHM technology development, reducing operational and maintenance costs, and ensuring the safety of public infrastructure.

Serious floor heave in gob-side entry retaining (GER) with fully-mechanized gangue backfilling mining affects the transportation and ventilation safety of the mine. A theoretical mechanical model for the floor of gob-backfilled GER was established. The effects of the mechanical properties of floor strata, the granular compaction of backfilling area (BFA), the vertical support of roadside support body (RSB), and the stress concentration of the solid coal on the floor heave of the gob-backfilled GER were studied. The results show that the floor heave increases with the increase of the coal seam buried depth, and decreases with the increase of the floor rock elastic modulus. The development depth of the plastic zone decreases with the increase of the c and φ value of the floor rock, and increases with the increase of the stress concentration factor of the solid coal. The development depth of the plastic zone in the test mine reached 2.68 m. The field test and monitoring results indicate that the comprehensive control scheme of adjusting backfilling pressure, deep grouting reinforcement, shallow opening stress relief slots, and surface pouring can effectively control the floor heave. The roof-floor displacement is reduced by 73.8% compared to that with the original support scheme. The roadway section meets the design and application requirements when the deformation stabilizes, demonstrating the rationality of the mechanical model. The research results overcome the technical bottleneck of floor heave control of fully-mechanized backfilling GER, providing a reliable basis for the design of a floor heave control scheme.

To counter the technical difficulties faced by gob-side entry retaining (GER) under multiple complex mining geological conditions in China, this paper introduces a GER method with fully mechanized gangue backfilling mining. A similar materials simulation experiment was conducted to simulate the gob-backfilled GER process by using the similar model test system containing an independently developed horizontal pushing load device. The experimental results show that the compaction speed of the backfilling area (BFA) can be improved, and the main roof subsidence can be reduced by increasing the horizontal pushing load and reducing the attenuation rate of the stress in BFA. The designed roadside backfill body (RBB) containing a flexible cushion is adaptive to the given deformation of the main roof, thus reducing the stress concentration of the RBB. The field test results show that when a 2 MPa horizontal pushing load is exerted in the BFA, arranging a 200 mm high-water-material flexible cushion can cause the BFA to swiftly change to the compaction stage. After stabilized deformation, the roadway section satisfies the design and application requirements. The feasibility and rationality of the GER with the fully mechanized gangue backfilling mining are proved, providing a safe, efficient, and environmentally friendly mining method without using a coal pillar.

Development of a safe and economical roadside support body (RSB) material is the key to successful backfilling gob‐side entry retaining (GER). By means of laboratory tests, this paper studied the effects of the water‐cement ratio, aggregate content, and age on the contractibility and resistance increasing speed, compressive strength, and postpeak carrying capacity of the concrete with gangues as an aggregate. It also discussed the rationality and adaptability of gangue concrete as a RSB material for backfilling GER. The experimental results show that the compressive strength of gangue concrete increases with age, and that the strength of gangue concrete demonstrates a nonlinear decreasing trend with the increase of the cementing material’s water‐cement ratio. The water‐cement ratio in the range of 0.46–0.60 has the most significant regulation effect on the strength of gangue concrete. Mixing with a certain amount of coal gangue enhances the postpeak carrying capacity of concrete, preventing the sample from impact failure. The field experimental results report that as a RSB material, gangue concrete can meet the design and application requirements of GER with gangue backfilling mining. A RSB material featuring high safety, high waste utilization rate, fast construction speed, and low costs is provided.

The coal seam and the roof of the roadway bear loads together in the underground engineering of coal mine. Especially for the roadway driven along the roof, its deformation is completely different from that arranged in the complete rock stratum. Accurately knowing the mechanical mechanism of coal-rock combined body can help understand the deformation and failure modes of such roadways. This article started with tests of coal-rock combined samples with different height ratios, based on the test results, a strain softening damage constitutive model of coal-rock combined body and a method for solving the parameters of the model were proposed, and the influence of the model parameters was discussed. The test results show that the stress peak value and residual strength of the coal-rock combined samples are negatively correlated with the proportion of coal in the coal-rock combined samples, and have a positive correlation with the confining pressure. The damage constitutive model fitted the test curve well. The model can accurately describe the stress-strain curve of coal-rock combined samples, and can reflect the influence of different height ratios of coal and rock samples and confining pressures. The effects of model parameters were discussed based on the damage constitutive model, which are expected to be widely used in underground engineering.

A fractal discrete fracture network based model was proposed for the gas production prediction from a fractured shale reservoir. Firstly, this model was established based on the fractal distribution of fracture length and a fractal permeability model of shale matrix which coupled the multiple flow mechanisms of slip flow, Knudsen diffusion, surface diffusion, and multilayer adsorption. Then, a numerical model was formulated with the governing equations of gas transport in both a shale matrix and fracture network system and the deformation equation of the fractured shale reservoir. Thirdly, this numerical model was solved within the platform of COMSOL Multiphysics (a finite element software) and verified through three fractal discrete fracture networks and the field data of gas production from two shale wells. Finally, the sensitivity analysis was conducted on fracture length fractal dimension, pore size distribution, and fracture permeability. This study found that cumulative gas production increases up to 113% when the fracture fractal length dimension increases from 1.5 to the critical value of 1.7. The gas production rate declines more rapidly for a larger fractal dimension (up to 1.7). Wider distribution of pore sizes (either bigger maximum pore size or smaller minimum pore size or both) can increase the matrix permeability and is beneficial to cumulative gas production. A linear relationship is observed between the fracture permeability and the cumulative gas production. Thus, the fracture permeability can significantly impact shale gas production.